Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the confounders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data.

As one of the most common neurobehavioral diseases in school-age children, Attention Deficit Hyperactivity Disorder (ADHD) has been increasingly studied in recent years. But it is still a challenge problem to accurately identify ADHD patients from healthy persons. To address this issue, we propose a dual subspace classification algorithm by using individual resting-state Functional Connectivity (FC). In detail, two subspaces respectively containing ADHD and healthy control features, called as dual subspaces, are learned with several subspace measures, wherein a modified graph embedding measure is employed to enhance the intra-class relationship of these features. Therefore, given a subject (used as test data) with its FCs, the basic classification principle is to compare its projected component energy of FCs on each subspace and then predict the ADHD or control label according to the subspace with larger energy. However, this principle in practice works with low efficiency, since the dual subspaces are unstably obtained from ADHD databases of small size. Thereby, we present an ADHD classification framework by a binary hypothesis testing of test data. Here, the FCs of test data with its ADHD or control label hypothesis are employed in the discriminative FC selection of training data to promote the stability of dual subspaces. For each hypothesis, the dual subspaces are learned from the selected FCs of training data. The total projected energy of these FCs is also calculated on the subspaces. Sequentially, the energy comparison is carried out under the binary hypotheses. The ADHD or control label is finally predicted for test data with the hypothesis of larger total energy. In the experiments on ADHD-200 dataset, our method achieves a significant classification performance compared with several state-of-the-art machine learning and deep learning methods, where our accuracy is about 90% for most of ADHD databases in the leave-one-out cross-validation test.

Background The over-use of antibiotics in clinical domains is causing an alarming increase in bacterial resistance, thus endangering their effectiveness as regards the treatment of highly recurring severe infectious diseases. Whilst Clinical Guidelines (CGs) focus on the correct prescription of antibiotics in a narrative form, Clinical Decision Support Systems (CDSS) operationalize the knowledge contained in CGs in the form of rules at the point of care. Despite the efforts made to computerize CGs, there is still a gap between CGs and the myriad of rule technologies (based on different logic formalisms) that are available to implement CDSSs in real clinical settings. Objective To helpCDSS designers to determine the most suitable rule-based technology (medical-oriented rules, production rules and semantic web rules) with which to model knowledge from CGs for the prescription of antibiotics. We propose a framework of criteria for this purpose that is extensible to more generic CGs. Materials and methods Our proposal is based on the identification of core technical requirements extracted from both literature and the analysis of CGs for antibiotics, establishing three dimensions for analysis: language expressivity, interoperability and industrial aspects. We present a case study regarding the John Hopkins Hospital (JHH) Antibiotic Guidelines for Urinary Tract Infection (UTI), a highly recurring hospital acquired infection. We have adopted our framework of criteria in order to analyse and implement these CGs using various rule technologies: HL7 Arden Syntax, general-purpose Production Rules System (Drools), HL7 standard Rule Interchange Format (RIF), Semantic Web Rule Language (SWRL) and SParql Inference Notation (SPIN) rule extensions (implementing our own ontology for UTI). Results We have identified the main criteria required to attain a maintainable and cost-affordable computable knowledge representation for CGs. We have represented the JHH UTI CGs knowledge in a total of 12 Arden Syntax MLMs, 81 Drools rules and 154 ontology classes, properties and individuals. Our experiments confirm the relevance of the proposed set of criteria and show the level of compliance of the different rule technologies with the JHH UTI CGs knowledge representation. Conclusions The proposed framework of criteria may help clinical institutions to select the most suitable rule technology for the representation of CGs in general, and for the antibiotic prescription domain in particular, depicting the main aspects that lead to Computer Interpretable Guidelines (CIGs), such as Logic expressivity (Open/Closed World Assumption, Negation-As-Failure), Temporal Reasoning and Interoperability with existing HIS and clinical workflow. Future work will focus on providing clinicians with suggestions regarding new potential steps for CGs, considering process mining approaches and CGs Process Workflows, the use of HL7 FHIR for HIS interoperability and the representation of Knowledge-as- a-Service (KaaS).

Running a cost-effective human blood transfusion supply chain challenges decision makers in blood services world-wide. In this paper, we develop a Markov decision process with the objective of minimising the overall costs of internal and external collections, storing, producing and disposing of blood bags, whilst explicitly considering the probability that a donated blog bag will perish before demanded. The model finds an optimal policy to collect additional bags based on the number of bags in stock rather than using information about the age of the oldest item. Using data from the literature, we validate our model and carry out a case study based on data from a large blood supplier in South America. The study helped achieve an overall increase of 4.5% in blood donations in one year.

Background Deep learning has always been at the forefront of scientific research. It has also been applied to medical research. Hereditary spinocerebellar ataxia (SCA) is characterized by gait abnormalities and is usually evaluated semi-quantitatively by scales. However, more detailed gait characteristics of SCA and related objective methods have not yet been established. Therefore, the purpose of this study was to evaluate the gait characteristics of SCA patients, as well as to analyze the correlation between gait parameters, clinical scales, and imaging on deep learning. Methods Twenty SCA patients diagnosed by genetic detection were included in the study. Ten patients who were tested via functional magnetic resonance imaging (fMRI) were included in the SCA imaging subgroup. All SCA patients were evaluated with the International Cooperative Ataxia Rating Scale (ICARS) and Scale for the Assessment and Rating of Ataxia (SARA) clinical scales. The gait control group included 16 healthy subjects, and the imaging control group included seven healthy subjects. Gait data consisting of 10 m of free walking of each individual in the SCA group and the gait control group were detected by wearable gait-detection equipment. Stride length, stride time, velocity, supporting-phase percentage, and swinging-phase percentage were extracted as gait parameters. Cerebellar volume and the midsagittal cerebellar proportion in the posterior fossa (MRVD) were calculated according to MR. Results There were significant differences in stride length, velocity, supporting-phase percentage, and swinging-phase percentage between the SCA group and the gait control group. The stride length and stride velocity of SCA groups were lower while supporting phase was longer than those of the gait control group. SCA group's velocity was negatively correlated with both the ICARS and SARA scores. The cerebellar volume and MRVD of the SCA imaging subgroup were significantly smaller than those of the imaging control group. MRVD was significantly correlated with ICARS and SARA scores, as well as stride velocity variability. Conclusion SCA gait parameters were characterized by a reduced stride length, slower walking velocity, and longer supporting phase. Additionally, a smaller cerebellar volume correlated with an increased irregularity in gait. Gait characteristics exhibited considerable clinical relevance to hereditary SCA. We conclude that a combination of gait parameters, ataxia scales, and MRVD may represent more objective markers for clinical evaluations of SCA.

In this paper, the urinary bladder cancer diagnostic method which is based on Multi-Layer Perceptron and Laplacian edge detector is presented. The aim of this paper is to investigate the implementation possibility of a simpler method (Multi-Layer Perceptron) alongside commonly used methods, such as Deep Learning Convolutional Neural Networks, for the urinary bladder cancer detection. The dataset used for this research consisted of 1997 images of bladder cancer and 986 images of non-cancer tissue. The results of the conducted research showed that using Multi-Layer Perceptron trained and tested with images pre-processed with Laplacian edge detector are achieving AUC value up to 0.99. When different image sizes are compared it can be seen that the best results are achieved if 50×50 and 100×100 images were used.

In the last few years, hospitals have been collecting a large amount of health related digital data for patients. This includes clinical test reports, treatment updates and disease diagnosis. The information extracted from this data is used for clinical decisions and treatment recommendations. Among health recommender systems, collaborative filtering technique has gained a significant success. However, traditional collaborative filtering algorithms are facing challenges such as data sparsity and scalability, which leads to a reduction in system accuracy and efficiency. In a clinical setting, the recommendations should be accurate and timely. In this paper, an improvised collaborative filtering technique is proposed, which is based on clustering and sub-clustering. The proposed methodology is applied on a supervised set of data for four different types of cardiovascular diseases including angina, non-cardiac chest pain, silent ischemia, and myocardial infarction. The patient data is partitioned with respect to their corresponding disease class, which is followed by k-mean clustering, applied separately on each disease partition. A query patient once directed to the correct disease partition requires to get similarity scores from a reduced sub-cluster, thereby improving the efficiency of the system. Each disease partition has a separate process for recommendation, which gives rise to modularization and helps in improving scalability of the system. The experimental results demonstrate that the proposed modular clustering based recommender system reduces the spatial search domain for a query patient and the time required for providing accurate recommendations. The proposed system improves upon the accuracy of recommendations as demonstrated by the precision and recall values. This is significant for health recommendation systems particularly for those related to cardiovascular diseases.

The decompressive laminectomy is a common operation for treatment of lumbar spinal stenosis. The tools for grinding and drilling are used for fenestration and internal fixation, respectively. The state recognition is one of the main technologies in robot-assisted surgery, especially in tele-surgery, because surgeons have limited perception during remote-controlled robot-assisted surgery. The novelty of this paper is that a state recognition system is proposed for the robot-assisted tele-surgery. By combining the learning methods and traditional methods, the robot from the slave-end can think about the current operation state like a surgeon, and provide more information and decision suggestions to the master-end surgeon, which aids surgeons work safer in tele-surgery. For the fenestration, we propose an image-based state recognition method that consists a U-Net derived network, grayscale redistribution and dynamic receptive field assisting in controlling the grinding process to prevent the grinding-bit from crossing the inner edge of the lamina to damage the spinal nerves. For the internal fixation, we propose an audio and force-based state recognition method that consists signal features extraction methods, LSTM-based prediction and information fusion assisting in monitoring the drilling process to prevent the drilling-bit from crossing the outer edge of the vertebral pedicle to damage the spinal nerves. Several experiments are conducted to show the reliability of the proposed system in robot-assisted surgery.

Antibiotic resistance is one of the major challenges we face in modern times. Antibiotic use, especially their overuse, is the single most important driver of antibiotic resistance. Efforts have been made to reduce unnecessary drug prescriptions, but limited work is devoted to optimising dosage regimes when they are prescribed. The design of antibiotic treatments can be formulated as an optimisation problem where candidate solutions are encoded as vectors of dosages per day. The formulation naturally gives rise to competing objectives, as we want to maximise the treatment effectiveness while minimising the total drug use, the treatment duration and the concentration of antibiotic experienced by the patient. This article combines a recent mathematical model of bacterial growth including both susceptible and resistant bacteria, with a multi-objective evolutionary algorithm in order to automatically design successful antibiotic treatments. We consider alternative formulations combining relevant objectives and constraints. Our approach obtains shorter treatments, with improved success rates and smaller amounts of drug than the standard practice of administering daily fixed doses. These new treatments consistently involve a higher initial dose followed by lower tapered doses.

Early detection of skin cancer is very important and can prevent some skin cancers, such as focal cell carcinoma and melanoma. Although there are several reasons that have bad impacts on the detection precision. Recently, the utilization of image processing and machine vision in medical applications is increasing. In this paper, a new image processing based method has been proposed for the early detection of skin cancer. The method utilizes an optimal Convolutional neural network (CNN) for this purpose. In this paper, improved whale optimization algorithm is utilized for optimizing the CNN. For evaluation of the proposed method, it is compared with some different methods on two different datasets. Simulation results show that the proposed method has superiority toward the other compared methods.

Objective Epistasis identification is critical for determining susceptibility to human genetic diseases. The rapid development of technology has enabled scalability to make multifactor dimensionality reduction (MDR) measurements an effective calculation tool that achieves superior detection. However, the classification of high-risk (H) or low-risk (L) groups in multidrug resistance operations calls for extensive research. Methods and material In this study, an improved fuzzy sigmoid (FS) method using the membership degree in MDR (FSMDR) was proposed for solving the limitations of binary classification. The FS method combined with MDR measurements yielded an improved ability to distinguish similar frequencies of potential multifactor genotypes. Results We compared our results with other MDR-based methods and FSMDR achieved superior detection rates on simulated data sets. The results indicated that the fuzzy classifications can provide insight into the uncertainty of H/L classification in MDR operation. Conclusion FSMDR successfully detected significant epistasis of coronary artery disease in the Wellcome Trust Case Control Consortium data set.

Deep Neural Network (DNN), as a deep architectures, has shown excellent performance in classification tasks. However, when the data has different distributions or contains some latent non-observed factors, it is difficult for DNN to train a single model to perform well on the classification tasks. In this paper, we propose mixture model based on DNNs (MoNNs), a supervised approach to perform classification tasks with a gating network and multiple local expert models. We use a neural network as a gating function and use DNNs as local expert models. The gating network split the heterogeneous data into several homogeneous components. DNNs are combined to perform classification tasks in each component. Moreover, we use EM (Expectation Maximization) as an optimization algorithm. Experiments proved that our MoNNs outperformed the other compared methods on determination of diabetes, determination of benign or malignant breast cancer, and handwriting recognition. Therefore, the MoNNs can solve the problem of data heterogeneity and have a good effect on classification tasks.

Synonym mapping between phenotype concepts from different terminologies is difficult because terminology databases have been developed largely independently. Existing maps of synonymous phenotype concepts from different terminology databases are highly incomplete, and manually mapping is time consuming and laborious. Therefore, building an automatic method for predictive mapping of synonymous phenotypes is of special importance. We propose a classifier-based phenotype mapping prediction model (CPM) to predict synonymous relationships between phenotype concepts from different terminology databases. The model takes network semantic representations of phenotypes as input and predicts synonymous relationships by training binary classifiers with a voting strategy. We compared the performance of the CPM with a similarity-based phenotype mapping prediction model (SPM), which predicts mapping based on the ranked cosine similarity of candidate mapping concepts. Based on a network representation N2V-TFIDF, with a majority voting strategy method MV, the CPM achieved accuracy of 0.943, which was 15.4% higher than that of the SPM using the cosine similarity method (0.789) and 23.8% higher than that of the SSDTM method (0.724) proposed in our previous work.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays an important role in diagnosis and grading of brain tumors. Although manual DCE biomarker extraction algorithms boost the diagnostic yield of DCE-MRI by providing quantitative information on tumor prognosis and prediction, they are time-consuming and prone to human errors. In this paper, we propose a fully-automated, end-to-end system for DCE-MRI analysis of brain tumors. Our deep learning-powered technique does not require any user interaction, it yields reproducible results, and it is rigorously validated against benchmark and clinical data. Also, we introduce a cubic model of the vascular input function used for pharmacokinetic modeling which significantly decreases the fitting error when compared with the state of the art, alongside a real-time algorithm for determination of the vascular input region. An extensive experimental study, backed up with statistical tests, showed that our system delivers state-of-the-art results while requiring less than 3 min to process an entire input DCE-MRI study using a single GPU.

Our aim is to develop a machine learning (ML) model that can predict dementia in a general patient population from multiple health care institutions one year and three years prior to the onset of the disease without any additional monitoring or screening. The purpose of the model is to automate the cost-effective, non-invasive, digital pre-screening of patients at risk for dementia. Towards this purpose, routine care data, which is widely available through Electronic Medical Record (EMR) systems is used as a data source. These data embody a rich knowledge and make related medical applications easy to deploy at scale in a cost-effective manner. Specifically, the model is trained by using structured and unstructured data from three EMR data sets: diagnosis, prescriptions, and medical notes. Each of these three data sets is used to construct an individual model along with a combined model which is derived by using all three data sets. Human-interpretable data processing and ML techniques are selected in order to facilitate adoption of the proposed model by health care providers from multiple institutions. The results show that the combined model is generalizable across multiple institutions and is able to predict dementia within one year of its onset with an accuracy of nearly 80% despite the fact that it was trained using routine care data. Moreover, the analysis of the models identified important predictors for dementia. Some of these predictors (e.g., age and hypertensive disorders) are already confirmed by the literature while others, especially the ones derived from the unstructured medical notes, require further clinical analysis.

Cancer is the second leading cause of death after cardiovascular diseases. Out of all types of cancer, brain cancer has the lowest survival rate. Brain tumors can have different types depending on their shape, texture, and location. Proper diagnosis of the tumor type enables the doctor to make the correct treatment choice and help save the patient's life. There is a high need in the Artificial Intelligence field for a Computer Assisted Diagnosis (CAD) system to assist doctors and radiologists with the diagnosis and classification of tumors. Over recent years, deep learning has shown an optimistic performance in computer vision systems. In this paper, we propose an enhanced approach for classifying brain tumor types using Residual Networks. We evaluate the proposed model on a benchmark dataset containing 3064 MRI images of 3 brain tumor types (Meningiomas, Gliomas, and Pituitary tumors). We have achieved the highest accuracy of 99% outperforming the other previous work on the same dataset.

Motivation Emergency Departments’ (ED) modern triage systems implemented worldwide are solely based upon medical knowledge and experience. This is a limitation of these systems, since there might be hidden patterns that can be explored in big volumes of clinical historical data. Intelligent techniques can be applied to these data to develop clinical decision support systems (CDSS) thereby providing the health professionals with objective criteria. Therefore, it is of foremost importance to identify what has been hampering the application of such systems for ED triage. Objectives The objective of this paper is to assess how intelligent CDSS for triage have been contributing to the improvement of quality of care in the ED as well as to identify the challenges they have been facing regarding implementation. Methods We applied a standard scoping review method with the manual search of 6 digital libraries, namely: ScienceDirect, IEEE Xplore, Google Scholar, Springer, MedlinePlus and Web of Knowledge. Search queries were created and customized for each digital library in order to acquire the information. The core search consisted of searching in the papers’ title, abstract and key words for the topics “triage”, “emergency department”/“emergency room” and concepts within the field of intelligent systems. Results From the review search, we found that logistic regression was the most frequently used technique for model design and the area under the receiver operating curve (AUC) the most frequently used performance measure. Beside triage priority, the most frequently used variables for modelling were patients’ age, gender, vital signs and chief complaints. The main contributions of the selected papers consisted in the improvement of a patient's prioritization, prediction of need for critical care, hospital or Intensive Care Unit (ICU) admission, ED Length of Stay (LOS) and mortality from information available at the triage. Conclusions In the papers where CDSS were validated in the ED, the authors found that there was an improvement in the health professionals’ decision-making thereby leading to better clinical management and patients’ outcomes. However, we found that more than half of the studies lacked this implementation phase. We concluded that for these studies, it is necessary to validate the CDSS and to define key performance measures in order to demonstrate the extent to which incorporation of CDSS at triage can actually improve care.

The structured report is a new trend for the preparation and manipulation of radiological examination reports. The structuring of the radiological report data can bring many benefits and advantages over other existing methodologies. Research and studies about the structured radiological report are highly relevant in clinical and academic subjects, improving medical practice, reducing unobserved problems by radiologists, improving reporting practices and medical diagnoses. Exposing the benefits, advantages and potential of the structured radiological report is important in encouraging the acceptance and implementation of this method by radiology professionals who are still somewhat resistant. The present review highlights the factors that contribute to the consolidation of adopting the structured radiology report methodology, addressing a variety of studies focused on the structuring of the radiological report. This integrative review of the literature is proposed by searching publications and journals databases (CAPES – Coordination of Improvement of Higher-Level Personnel, SciELO – Scientific Electronic Library Online, and PubMed – Publisher Medline) to develop a complete and unified understanding of the subject, so that it becomes a major part of evidence-based initiatives.

An overview of the applications of deep learning for ophthalmic diagnosis using retinal fundus images is presented. We describe various retinal image datasets that can be used for deep learning purposes. Applications of deep learning for segmentation of optic disk, optic cup, blood vessels as well as detection of lesions are reviewed. Recent deep learning models for classification of diseases such as age-related macular degeneration, glaucoma, and diabetic retinopathy are also discussed. Important critical insights and future research directions are given.

In today’s world, cardiovascular diseases are prevalent becoming the leading cause of death; more than half of the cardiovascular diseases are due to Coronary Heart Disease (CHD) which generates the demand of predicting them timely so that people can take precautions or treatment before it becomes fatal. For serving this purpose a Modified Artificial Plant Optimization (MAPO) algorithm has been proposed which can be used as an optimal feature selector along with other machine learning algorithms to predict the heart rate using the fingertip video dataset which further predicts the presence or absence of Coronary Heart Disease in an individual at the moment. Initially, the video dataset has been pre-processed, noise is filtered and then MAPO is applied to predict the heart rate with a Pearson correlation and Standard Error Estimate of 0.9541 and 2.418 respectively. The predicted heart rate is used as a feature in other two datasets and MAPO is again applied to optimize the features of both datasets. Different machine learning algorithms are then applied to the optimized dataset to predict values for presence of current heart disease. The result shows that MAPO reduces the dimensionality to the most significant information with comparable accuracies for different machine learning models with maximum dimensionality reduction of 81.25%. MAPO has been compared with other optimizers and outperforms them with better accuracy.

Obstetric ultrasound examination of physiological parameters has been mainly used to estimate the fetal weight during pregnancy and baby weight before labour to monitor fetal growth and reduce prenatal morbidity and mortality. However, the problem is that ultrasound estimation of fetal weight is subject to population’s difference, strict operating requirements for sonographers, and poor access to ultrasound in low-resource areas. Inaccurate estimations may lead to negative perinatal outcomes. This study aims to predict fetal weight at varying gestational age in the absence of ultrasound examination within a certain accuracy. We consider that machine learning can provide an accurate estimation for obstetricians alongside traditional clinical practices, as well as an efficient and effective support tool for pregnant women for self-monitoring. We present a robust methodology using a data set comprising 4212 intrapartum recordings. The cubic spline function is used to fit the curves of several key characteristics that are extracted from ultrasound reports. A number of simple and powerful machine learning algorithms are trained, and their performance is evaluated with real test data. We also propose a novel evaluation performance index called the intersection-over-union (loU) for our study. The results are encouraging using an ensemble model consisting of Random Forest, XGBoost, and LightGBM algorithms. The experimental results show the loU between predicted range of fetal weight at any gestational age that is given by the ensemble model and ultrasound respectively. The machine learning based approach applied in our study is able to predict, with a high accuracy, fetal weight at varying gestational age in the absence of ultrasound examination.

Paralyzed patients were increasing day by day. Some of the neurodegenerative diseases like amyotrophic lateral sclerosis, Brainstem Leison, Stupor and Muscular dystrophy affect the muscle movements in the body. The affected persons were unable to migrate. To overcome from their problem they need some assistive technology with the help of bio signals. Electrooculogram (EOG) based Human Computer Interaction (HCI) is one of the technique used in recent days to overcome such problem. In this paper we clearly check the possibilities of creating nine states HCI by our proposed method. Signals were captured through five electrodes placed on the subjects face around the eyes. These signals were amplified with ADT26 bio amplifier, filtered with notch filter, and processed with reference power and band power techniques to extract features to detect the eye movements and mapped with Time Delay Neural Network to classify the eye movements to generate control signal to control external hardware devices. Our experimental study reports that maximum average classification of 91.09% for reference power feature and 91.55%-for band power feature respectively. The obtained result confirms that band power features with TDNN network models shows better performance than reference features for all subjects. From this outcome we conclude that band power features with TDNN network models was more suitable for classifying the eleven difference eye movements for individual subjects. To validate the result obtained from this method we categorize the subjects in age wise to check the accuracy of the system. Single trail analysis was conducted in offline to identify the recognizing accuracy of the proposed system. The result summarize that band power features with TDNN network models exceed the reference power with TDNN network model used in this study. Through the outcome we conclude that that band power features with TDNN network was more suitable for designing EOG based HCI in offline mode.

Individuals with neurodegenerative attacks loose the entire motor neuron movements. These conditions affect the individual actions like walking, speaking impairment and totally make the person in to locked in state (LIS). To overcome the miserable condition the person need rehabilitation devices through a Brain Computer Interfaces (BCI) to satisfy their needs. BMI using Electroencephalogram (EEG) receives the mental thoughts from brain and converts into control signals to activate the exterior communication appliances in the absence of biological channels. To design the BCI, we conduct our study with three normal male subjects, three normal female subjects and three ALS affected individuals from the age of 20–60 with three electrode systems for four tasks. One Dimensional Local Binary Patterns (LBP) technique was applied to reduce the digitally sampled features collected from nine subjects was treated with Grey wolf optimization Neural Network (GWONN) to classify the mentally composed words. Using these techniques, we compared the three types of subjects to identify the performances. The study proves that subjects from normal male categories performance was maximum compared with the other subjects. To assess the individual performance of the subject, we conducted the recognition accuracy test in offline mode. From the accuracy test also, we obtained the best performance from the normal male subjects compared with female and ALS subjects with an accuracy of 98.33 %, 95.00 % and 88.33 %. Finally our study concludes that patients with ALS attack need more training than that of the other subjects.

Due to growth in population, Individual persons with disabilities are increasing daily. To overcome the disability especially in Locked in State (LIS) due to Spinal Cord Injury (SCI), we planned to design four states moving robot from four imagery tasks signals acquired from three electrode systems by placing the electrodes in three positions namely T1, T3 and FP1. At the time of the study we extract the features from Continuous Wavelet Transform (CWT) and trained with Optimized Neural Network model to analyze the features. The proposed network model showed the highest performances with an accuracy of 93.86 % then that of conventional network model. To confirm the performances we conduct offline test. The offline test also proved that new network model recognizing accuracy was higher than the conventional network model with recognizing accuracy of 97.50 %. To verify our result we conducted Information Transfer Rate (ITR), from this analysis we concluded that optimized network model outperforms the other network models like conventional ordinary Feed Forward Neural Network, Time Delay Neural Network and Elman Neural Networks with an accuracy of 21.67 bits per sec. By analyzing classification performances, recognizing accuracy and Information Transformation Rate (ITR), we concluded that CWT features with optimized neural network model performances were comparably greater than that of normal or conventional neural network model and also the study proved that performances of male subjects was appreciated compared to female subjects.

Today’s life assistive devices were playing significant role in our life to communicate with others. In that modality Human Computer Interface (HCI) based Electrooculogram (EOG) playing vital part. By using this method we can able to overcome the conventional methods in terms of performance and accuracy. To overcome such problem we analyze the EOG signal from twenty subjects to design nine states EOG based HCI using five electrodes system to measure the horizontal and vertical eye movements. Signals were preprocessed to remove the artifacts and extract the valuable information from collected data by using band power and Hilbert Huang Transform (HHT) and trained with Pattern Recognition Neural Network (PRNN) to classify the tasks. The classification results of 92.17% and 91.85% were shown for band power and HHT features using PRNN architecture. Recognition accuracy was analyzed in offline to identify the possibilities of designing HCI. We compare the two feature extraction techniques with PRNN to analyze the best method for classifying the tasks and recognizing single trail tasks to design the HCI. Our experimental result confirms that for classifying as well as recognizing accuracy of the collected signals using band power with PRNN shows better accuracy compared to other network used in this study. We compared the male subjects performance with female subjects to identify the performance. Finally we compared the male as well as female subjects in age group wise to identify the performance of the system. From that we concluded that male performance was appreciable compared with female subjects as well as age group between 26 to 32 performance and recognizing accuracy were high compared with other age groups used in this study.

Epilepsy is the most common neurological disorder in humans. Electroencephalogram is a prevalent tool for diagnosing the epileptic seizure activity in clinical, which provides valuable information for understanding the physiological mechanisms behind epileptic disorders. Approximate entropy and recurrence quantification analysis are nonlinear analysis tools to quantify the complexity and recurrence behaviors of non-stationary signals, respectively. Convolutional neural networks are powerful class of models. In this paper, a new method for automatic epileptic electroencephalogram recordings based on the approximate entropy and recurrence quantification analysis combined with a convolutional neural network were proposed. The Bonn dataset was used to assess the proposed approach. The results indicated that the performance of the epileptic seizure detection by approximate entropy and recurrence quantification analysis is good (all of the sensitivities, specificities and accuracies are greater than 80%); especially the sensitivity, specificity and accuracy of the recurrence rate achieved 92.17%, 91.75% and 92.00%. When combines the approximate entropy and recurrence quantification analysis features with convolutional neural networks to automatically differentiate seizure electroencephalogram from normal recordings, the classification result can reach to 98.84%, 99.35% and 99.26%. Thus, this makes automatic detection of epileptic recordings become possible and it would be a valuable tool for the clinical diagnosis and treatment of epilepsy.

Background Futurists have predicted that new autonomous technologies, embedded with artificial intelligence (AI) and machine learning (ML), will lead to substantial job losses in many sectors disrupting many aspects of healthcare. Mental health appears ripe for such disruption given the global illness burden, stigma, and shortage of care providers. Objective To characterize the global psychiatrist community’s opinion regarding the potential of future autonomous technology (referred to here as AI/ML) to replace key tasks carried out in mental health practice. Design Cross sectional, random stratified sample of psychiatrists registered with Sermo, a global networking platform open to verified and licensed physicians. Main outcome measures We measured opinions about the likelihood that AI/ML tools would be able to fully replace – not just assist – the average psychiatrist in performing 10 key psychiatric tasks. Among those who considered replacement likely, we measured opinions about how many years from now such a capacity might emerge. We also measured psychiatrist’s perceptions about whether benefits of AI/ML would outweigh the risks. Results Survey respondents were 791 psychiatrists from 22 countries representing North America, South America, Europe and Asia-Pacific. Only 3.8 % of respondents felt it was likely that future technology would make their jobs obsolete and only 17 % felt that future AI/ML was likely to replace a human clinician for providing empathetic care. Documenting and updating medical records (75 %) and synthesizing information (54 %) were the two tasks where a majority predicted that AI/ML could fully replace human psychiatrists. Female- and US-based doctors were more uncertain that the benefits of AI would outweigh risks than male- and non-US doctors, respectively. Around one in 2 psychiatrists did however predict that their jobs would be substantially changed by AI/ML. Conclusions Our findings provide compelling insights into how physicians think about AI/ML which in turn may help us better integrate technology and reskill doctors to enhance mental health care.

The general public’s attitudes, demands, and expectations regarding medical AI could provide guidance for the future development of medical AI to satisfy the increasing needs of doctors and patients. The objective of this study is to investigate public perceptions, receptivity, and demands regarding the implementation of medical AI. An online questionnaire was designed to investigate the perceptions, receptivity, and demands of general public regarding medical AI between October 13 and October 30, 2018. The distributions of the current achievements, public perceptions, receptivity, and demands among individuals in different lines of work (i.e., healthcare vs non-healthcare) and different age groups were assessed by performing descriptive statistics. The factors associated with public receptivity of medical AI were assessed using a linear regression model. In total, 2,780 participants from 22 provinces were enrolled. Healthcare workers accounted for 54.3 % of all participants. There was no significant difference between the healthcare workers and non-healthcare workers in the high proportion (99 %) of participants expressing acceptance of AI (p = 0.8568), but remarkable distributional differences were observed in demands (p < 0.001 for both demands for AI assistance and the desire for AI improvements) and perceptions (p < 0.001 for safety, validity, trust, and expectations). High levels of receptivity (approximately 100 %), demands (approximately 80 %), and expectations (100 %) were expressed among different age groups. The receptivity of medical AI among the non-healthcare workers was associated with gender, educational qualifications, and demands and perceptions of AI. There was a very large gap between current availability of and public demands for intelligence services (p < 0.001). More than 90 % of healthcare workers expressed a willingness to devote time to learning about AI and participating in AI research. The public exhibits a high level of receptivity regarding the implementation of medical AI. To date, the achievements have been rewarding, and further advancements are required to satisfy public demands. There is a strong demand for intelligent assistance in many medical areas, including imaging and pathology departments, outpatient services, and surgery. More contributions are imperative to facilitate integrated and advantageous implementation in medical AI.

Multichannel transcranial magnetic stimulation (mTMS) is a therapeutic method to improve psychiatric diseases, which has a flexible working pattern used to different applications. In order to make the electric field distribution in the brain meet the treatment expectations, we have developed a novel multi-swam particle swarm optimizer (NMSPSO) to optimize the current configuration of double layer coil array. To balance the exploration and exploitation abilities, three novel improved strategies are used in NMSPSO based on multi-swarm particle swarm optimizer. Firstly, a novel information exchange strategy is achieved by individual exchanges between sub-swarms. Secondly, a novel leaning strategy is used to control knowledge dissemination in the population, which not only increases the diversity of the particles but also guarantees the convergence. Finally, a novel mutation strategy is introduced, which can help the population jump out of the local optimum for better exploration ability. The method is examined on a set of well-known benchmark functions and the results show that NMSPSO has better performance than many particle swarm optimization variants. And the superior electric field distribution in mTMS can be obtained by NMSPSO to optimize the current configuration of the double layer coil array.

The recognition of cardiac arrhythmia in minimal time is important to prevent sudden and untimely deaths. The proposed work includes a complete framework for analyzing the Electrocardiogram (ECG) signal. The three phases of analysis include 1) the ECG signal quality enhancement through noise suppression by a dedicated filter combination; 2) the feature extraction by a devoted wavelet design and 3) a proposed hidden Markov model (HMM) for cardiac arrhythmia classification into Normal (N), Right Bundle Branch Block (RBBB), Left Bundle Branch Block (LBBB), Premature Ventricular Contraction (PVC) and Atrial Premature Contraction (APC). The main features extracted in the proposed work are minimum, maximum, mean, standard deviation, and median. The experiments were conducted on forty-five ECG records in MIT BIH arrhythmia database and in MIT BIH noise stress test database. The proposed model has an overall accuracy of 99.7% with a sensitivity of 99.7% and a positive predictive value of 100%. The detection error rate for the proposed model is 0.0004. This paper also includes a study of the cardiac arrhythmia recognition using an IoMT (Internet of Medical Things) approach.

A subject of extensive research interest in the Brain Computer Interfaces (BCIs) niche is motor imagery (MI), where users imagine limb movements to control the system. This interest is owed to the immense potential for its applicability in gaming, neuro-prosthetics and neuro-rehabilitation, where the user’s thoughts of imagined movements need to be decoded. Electroencephalography (EEG) equipment is commonly used for keeping track of cerebrum movement in BCI systems. The EEG signals are recognized by feature extraction and classification. The current research proposes a Hybrid-KELM (Kernel Extreme Learning Machine) method based on PCA (Principal Component Analysis) and FLD (Fisher's Linear Discriminant) for MI BCI classification of EEG data. The performance and results of the method are demonstrated using BCI competition dataset III, and compared with those of contemporary methods. The proposed method generated an accuracy of 96.54%.

Background Despite the expanding use of machine learning (ML) in fields such as finance and marketing, its application in the daily practice of clinical medicine is almost non-existent. In this systematic review, we describe the various areas within clinical medicine that have applied the use of ML to improve patient care. Methods A systematic review was performed in accordance with the PRISMA guidelines using Medline(R), EBM Reviews, Embase, Psych Info, and Cochrane Databases, focusing on human studies that used ML to directly address a clinical problem. Included studies were published from January 1, 2000 to May 1, 2018 and provided metrics on the performance of the utilized ML tool. Results A total of 1909 unique publications were reviewed, with 378 retrospective articles and 8 prospective articles meeting inclusion criteria. Retrospective publications were found to be increasing in frequency, with 61% of articles published within the last 4 years. Prospective articles comprised only 2% of the articles meeting our inclusion criteria. These studies utilized a prospective cohort design with an average sample size of 531. Conclusion The majority of literature describing the use of ML in clinical medicine is retrospective in nature and often outlines proof-of-concept approaches to impact patient care. We postulate that identifying and overcoming key translational barriers, including real-time access to clinical data, data security, physician approval of “black box” generated results, and performance evaluation will allow for a fundamental shift in medical practice, where specialized tools will aid the healthcare team in providing better patient care.

Background and Objective The measurement of Carotid Intima Media Thickness (CIMT) in ultrasound images can be used to detect the presence of atherosclerotic plaques. Usually, the CIMT estimation strategy is semi-automatic, since it requires: 1) a manual examination of the ultrasound image for the localization of a Region Of Interest (ROI), a fast and useful operation when only a small number of images need to be measured; and 2) an automatic delineation of the CIM region within the ROI. The existing efforts for automating the process have replicated the same two-step structure, resulting in two consecutive independent approaches. In this work, we propose a fully automatic single-step approach based on semantic segmentation that allows us to segment the plaque and to estimate the CIMT in a fast and useful manner for large data sets of images. Methods Our single-step approach is based on Densely Connected Convolutional Neural Networks (DenseNets) for semantic segmentation of the whole image. It has two remarkable characteristics: (1) it avoids ROI definition, and (2) it captures multi-scale contextual information in the complete image interpretation, due to the concatenation of feature maps carried out in DenseNets. Once the input image is segmented, a straightforward method for CIMT estimation and plaque detection is applied. Results The proposed method has been validated with a large data set (REGICOR) of more than 8,000 images, corresponding to two territories of the Carotid Artery: Common Carotid Artery (CCA) and Bulb. Among them, a subset of 331 images has been used to evaluate the performance of semantic segmentation (≈90% for train, ≈10% for test). The experimental results demonstrated that our method outperforms other deep models and shallow approaches found in the literature. In particular, our CIMT estimation reaches a correlation coefficient of 0.81, and a CIMT mean error of 0.02 mm and 0.06 mm in CCA and Bulb images, respectively. Furthermore, the accuracy for plaque detection is 96.45% and 78.09% in CCA and Bulb, respectively. To test the generalization power, the method has also been tested with another data set (NEFRONA) that includes images acquired with different equipment. Conclusions The validation carried out demonstrates that the proposed method is accurate and objective for both plaque detection and CIMT measurement. Moreover, the robustness and generalization capacity of the method have been proven with two different data sets.

As a crucial step of biological event extraction, event trigger identification has attracted much attention in recent years. Deep representation methods, which have the superiorities of less feature engineering and end-to-end training, show better performance than statistical methods. While most deep learning methods have been done on sentence-level event extraction, there are few works taking document context into account, losing potentially informative knowledge that is beneficial for trigger detection. In this paper, we propose a variational neural approach for biomedical event extraction, which can take advantage of latent topics underlying documents. By adopting a joint modeling manner of topics and events, our model is able to produce more meaningful and event-indicative words compare to prior topic models. In addition, we introduce a language model embeddings to capture context-dependent features. Experimental results show that our approach outperforms various baselines in a commonly used multi-level event extraction corpus.

Objective Electronic Medical Records (EMRs) contain temporal and heterogeneous doctor order information that can be used for treatment pattern discovery. Our objective is to identify “right patient”, “right drug”, “right dose”, “right route”, and “right time” from doctor order information. Methods We propose a fusion framework to extract typical treatment patterns based on multi-view similarity Network Fusion (SNF) method. The multi-view SNF method involves three similarity measures: content-view similarity, sequence-view similarity and duration-view similarity. An EMR dataset and two metrics were utilized to evaluate the performance and to extract typical treatment patterns. Results Experimental results on a real-world EMR dataset show that the multi-view similarity network fusion method outperforms all the single-view similarity measures and also outperforms the existing similarity measure methods. Furthermore, we extract and visualize typical treatment patterns by clustering analysis. Conclusion The extracted typical treatment patterns by combining doctor order content, sequence, and duration views can provide data-driven guidelines for artificial intelligence in medicine and help clinicians make better decisions in clinical practice.

Nowadays, Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated to be a valid complementary diagnostic tool for early detection and diagnosis of breast cancer. However, without a CAD (Computer Aided Detection) system, manual DCE-MRI examination can be difficult and error-prone. The early stage of breast tissue segmentation, in a typical CAD, is crucial to increase reliability and reduce the computational effort by reducing the number of voxels to analyze and removing foreign tissues and air. In recent years, the deep convolutional neural networks (CNNs) enabled a sensible improvement in many visual tasks automation, such as image classification and object recognition. These advances also involved radiomics, enabling high-throughput extraction of quantitative features, resulting in a strong improvement in automatic diagnosis through medical imaging. However, machine learning and, in particular, deep learning approaches are gaining popularity in the radiomics field for tissue segmentation. This work aims to accurately segment breast parenchyma from the air and other tissues (such as chest-wall) by applying an ensemble of deep CNNs on 3D MR data. The novelty, besides applying cutting-edge techniques in the radiomics field, is a multi-planar combination of U-Net CNNs by a suitable projection-fusing approach, enabling multi-protocol applications. The proposed approach has been validated over two different datasets for a total of 109 DCE-MRI studies with histopathologically proven lesions and two different acquisition protocols. The median dice similarity index for both the datasets is 96.60 % (±0.30 %) and 95.78 % (±0.51 %) respectively with p < 0.05, and 100% of neoplastic lesion coverage.

The representation of knowledge based on first-order logic captures the richness of natural language and supports multiple probabilistic inference models. Although symbolic representation enables quantitative reasoning with statistical probability, it is difficult to utilize with machine learning models as they perform numerical operations. In contrast, knowledge embedding (i.e., high-dimensional and continuous vectors) is a feasible approach to complex reasoning that can not only retain the semantic information of knowledge, but also establish the quantifiable relationship among embeddings. In this paper, we propose a recursive neural knowledge network (RNKN), which combines medical knowledge based on first-order logic with a recursive neural network for multi-disease diagnosis. After the RNKN is efficiently trained using manually annotated Chinese Electronic Medical Records (CEMRs), diagnosis-oriented knowledge embeddings and weight matrixes are learned. The experimental results confirm that the diagnostic accuracy of the RNKN is superior to those of four machine learning models, four classical neural networks and Markov logic network. The results also demonstrate that the more explicit the evidence extracted from CEMRs, the better the performance. The RNKN gradually reveals the interpretation of knowledge embeddings as the number of training epochs increases.

In this paper, we propose a novel method for the detection of small lesions in digital medical images. Our approach is based on a multi-context ensemble of convolutional neural networks (CNNs), aiming at learning different levels of image spatial context and improving detection performance. The main innovation behind the proposed method is the use of multiple-depth CNNs, individually trained on image patches of different dimensions and then combined together. In this way, the final ensemble is able to find and locate abnormalities on the images by exploiting both the local features and the surrounding context of a lesion. Experiments were focused on two well-known medical detection problems that have been recently faced with CNNs: microcalcification detection on full-field digital mammograms and microaneurysm detection on ocular fundus images. To this end, we used two publicly available datasets, INbreast and E-ophtha. Statistically significantly better detection performance were obtained by the proposed ensemble with respect to other approaches in the literature, demonstrating its effectiveness in the detection of small abnormalities.

Lung cancer is the leading cause of cancer death worldwide. Early detection of lung cancer is helpful to provide the best possible clinical treatment for patients. Due to the limited number of radiologist and the huge number of chest x-ray radiographs (CXR) available for observation, a computer-aided detection scheme should be developed to assist radiologists in decision-making. While deep learning showed state-of-the-art performance in several computer vision applications, it has not been used for lung nodule detection on CXR. In this paper, a deep learning-based lung nodule detection method was proposed. We employed patch-based multi-resolution convolutional networks to extract the features and employed four different fusion methods for classification. The proposed method shows much better performance and is much more robust than those previously reported researches. For publicly available Japanese Society of Radiological Technology (JSRT) database, more than 99% of lung nodules can be detected when the false positives per image (FPs/image) was 0.2. The FAUC and R-CPM of the proposed method were 0.982 and 0.987, respectively. The proposed approach has the potential of applications in clinical practice.

Data analysis and management of huge volumes of medical data have attracted enormous attention, since discovering knowledge from the data can benefit both caregivers and patients. In this paper, we focus on learning disease labels from medical data of patients in Intensive Care Units (ICU). Specifically, we extract features from two main sources, medical charts and notes. We apply the Bag-of-Words (BoW) model to encode the features. Different from most of the existing multi-label learning algorithms that take correlations among diseases into consideration, our model learns disease specific features to benefit the discrimination of different diseases. To achieve this, we first construct features specific to each disease by conducting clustering analysis on its positive and negative instances, and then perform training and testing by querying the clustering results. Extensive experiments have been conducted on a real-world Intensive Care Units (ICU) database. Evaluation results have shown that our proposed method has better performance against all other compared multi-label learning methods.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by repetitive behaviors, narrow interests, and deficits in social interaction and communication ability. An increasing emphasis is being placed on the development of innovative digital and mobile systems for their potential in therapeutic applications outside of clinical environments. Due to recent advances in the field of computer vision, various emotion classifiers have been developed, which have potential to play a significant role in mobile screening and therapy for developmental delays that impair emotion recognition and expression. However, these classifiers are trained on datasets of predominantly neurotypical adults and can sometimes fail to generalize to children with autism. The need to improve existing classifiers and develop new systems that overcome these limitations necessitates novel methods to crowdsource labeled emotion data from children. In this paper, we present a mobile charades-style game, Guess What?, from which we derive egocentric video with a high density of varied emotion from a 90-second game session. We then present a framework for semi-automatic labeled frame extraction from these videos using meta information from the game session coupled with classification confidence scores. Results show that 94%, 81%, 92%, and 56% of frames were automatically labeled correctly for categories disgust, neutral, surprise, and scared respectively, though performance for angry and happy did not improve significantly from the baseline.

OBJECTIVE Automatic artery/vein (A/V) segmentation from fundus images is required to track blood vessel changes occurring with many pathologies including retinopathy and cardiovascular pathologies. One of the clinical measures that quantifies vessel changes is the arterio-venous ratio (AVR) which represents the ratio between artery and vein diameters. This measure significantly depends on the accuracy of vessel segmentation and classification into arteries and veins. This paper proposes a fast, novel method for semantic A/V segmentation combining deep learning and graph propagation. METHODS A convolutional neural network (CNN) is proposed to jointly segment and classify vessels into arteries and veins. The initial CNN labeling is propagated through a graph representation of the retinal vasculature, whose nodes are defined as the vessel branches and edges are weighted by the cost of linking pairs of branches. To efficiently propagate the labels, the graph is simplified into its minimum spanning tree. RESULTS The method achieves an accuracy of 94.8% for vessels segmentation. The A/V classification achieves a specificity of 92.9% with a sensitivity of 93.7% on the CT-DRIVE database compared to the state-of-the-art-specificity and sensitivity, both of 91.7%. CONCLUSION The results show that our method outperforms the leading previous works on a public dataset for A/V classification and is by far the fastest. SIGNIFICANCE The proposed global AVR calculated on the whole fundus image using our automatic A/V segmentation method can better track vessel changes associated to diabetic retinopathy than the standard local AVR calculated only around the optic disc.

In recent years, there is a rapid increase in the population of elderly people. However, elderly people may suffer from the consequences of cognitive decline, which is a mental health disorder that primarily affects cognitive abilities such as learning, memory, etc. As a result, the elderly people may get dependent on caregivers to complete daily life tasks. Detecting the early indicators of dementia before it gets worsen and warning the caregivers and medical doctors would be helpful for further diagnosis. In this paper, the problem of activity recognition and abnormal behaviour detection is investigated for elderly people with dementia. First of all, the paper presents a methodology for generating synthetic data reflecting on some behavioural difficulties of people with dementia given the difficulty of obtaining real-world data. Secondly, the paper explores Convolutional Neural Networks (CNNs) to model patterns in activity sequences and detect abnormal behaviour related to dementia. Activity recognition is considered as a sequence labelling problem, while abnormal behaviour is flagged based on the deviation from normal patterns. Moreover, the performance of CNNs is compared against the state-of-art methods such as Naïve Bayes (NB), Hidden Markov Models (HMMs), Hidden Semi-Markov Models (HSMM), Conditional Random Fields (CRFs). The results obtained indicate that CNNs are competitive with those state-of-art methods.

Since a significant number of frequent laboratory blood tests are unnecessary and these tests may have complications, developing a system that could identify unnecessary tests is essential. In this paper, a value prediction approach is presented to predict the values of Calcium and Hematocrit laboratory blood tests for upper gastrointestinal bleeding patients and patients with unspecified hemorrhage in their gastrointestinal tract. The data have been extracted from the MIMIC-II database. By considering the issues of MIMIC-II in the process of data extraction and using expert knowledge, comprehensive preprocessing has been performed to validate the data. The first prediction system is developed using zero order Takagi-Sugeno fuzzy modeling and the sequential forward selection method. The results of this prediction system for target laboratory tests are promising. In the second proposed prediction system, patients are clustered using their comorbidity information before the final prediction phase. For each cluster, a medication feature is constructed and added to the data for the final feature selection. Although it was expected that clustering patients based on comorbidity data could improve the results of value prediction, the results were not improved in average. The reason for this could be the small number of abnormal laboratory test samples and their dispersion in clusters. These abnormal values would be more dispersed in the model with clustering phase, when they are scattered over different clusters.

In the context of cancer delineation using positron emission tomography datasets, we present an innovative approach which purpose is to tackle the real-time, three-dimensional segmentation task in a full, or at least nearly full automatized way. The approach comprises a preliminary initialization phase where the user highlights a region of interest around the cancer on just one slice of the tomographic dataset. The algorithm takes care of identifying an optimal and user-independent region of interest around the anomalous tissue and located on the slice containing the highest standardized uptake value so to start the successive segmentation task. The three-dimensional volume is then reconstructed using a slice-by-slice marching approach until a suitable automatic stop condition is met. On each slice, the segmentation is performed using an enhanced local active contour based on the minimization of a novel energy functional which combines the information provided by a machine learning component, the discriminant analysis in the present study. As a result, the whole algorithm is almost completely automatic and the output segmentation is independent from the input provided by the user. Phantom experiments comprising spheres and zeolites, and clinical cases comprising various body districts (lung, brain, and head and neck), and two different radio-tracers (18 F-fluoro-2-deoxy-d-glucose, and 11C-labeled Methionine) were used to assess the algorithm performances. Phantom experiments with spheres and with zeolites showed a dice similarity coefficient above 90% and 80%, respectively. Clinical cases showed high agreement with the gold standard (R2 = 0.98). These results indicate that the proposed method can be efficiently applied in the clinical routine with potential benefit for the treatment response assessment, and targeting in radiotherapy.

Computer vision-based clinical gait analysis is the subject of permanent research. However, there are very few datasets publicly available; hence the comparison of existing methods between each other is not straightforward. Even if the test data are in an open access, existing databases contain very few test subjects and single modality measurements, which limit their usage. The contributions of this paper are three-fold. First, we propose a new open-access multi-modal database acquired with the Kinect v.2 camera for the task of gait analysis. Second, we adapt to use the skeleton joint orientation data to calculate kinematic gait parameters to match golden-standard MOCAP systems. We propose a new set of features based on 3D low-limbs flexion dynamics to analyze the symmetry of a gait. Third, we design a Long-Short Term Memory (LSTM) ensemble model to create an unsupervised gait classification tool. The results show that joint orientation data provided by Kinect can be successfully used in an inexpensive clinical gait monitoring system, with the results moderately better than reported state-of-the-art for three normal/pathological gait classes.

Case-Based Reasoning (CBR) is a form of analogical reasoning in which the solution for a (new) query case is determined using a database of previous known cases with their solutions. Cases similar to the query are retrieved from the database, and then their solutions are adapted to the query. In medicine, a case usually corresponds to a patient and the problem consists of classifying the patient in a class of diagnostic or therapy. Compared to "black box" algorithms such as deep learning, the responses of CBR systems can be justified easily using the similar cases as examples. However, this possibility is often under-exploited and the explanations provided by most CBR systems are limited to the display of the similar cases. In this paper, we propose a CBR method that can be both executed automatically as an algorithm and presented visually in a user interface for providing visual explanations or for visual reasoning. After retrieving similar cases, a visual interface displays quantitative and qualitative similarities between the query and the similar cases, so as one can easily classify the query through visual reasoning, in a fully explainable manner. It combines a quantitative approach (visualized by a scatter plot based on Multidimensional Scaling in polar coordinates, preserving distances involving the query) and a qualitative approach (set visualization using rainbow boxes). We applied this method to breast cancer management. We showed on three public datasets that our qualitative method has a classification accuracy comparable to k-Nearest Neighbors algorithms, but is better explainable. We also tested the proposed interface during a small user study. Finally, we apply the proposed approach to a real dataset in breast cancer. Medical experts found the visual approach interesting as it explains why cases are similar through the visualization of shared patient characteristics.

An antigen is a protein capable of triggering an effective immune system response. Protective antigens are the ones that can invoke specific and enhanced adaptive immune response to subsequent exposure to the specific pathogen or related organisms. Such proteins are therefore of immense importance in vaccine preparation and drug design. However, the laboratory experiments to isolate and identify antigens from a microbial pathogen are expensive, time consuming and often unsuccessful. This is why Reverse Vaccinology has become the modern trend of vaccine search, where computational methods are first applied to predict protective antigens or their determinants, known as epitopes. In this paper, we propose a novel, accurate computational model to identify protective antigens efficiently. Our model extracts features directly from the protein sequences, without any dependence on functional domain or structural information. After relevant features are extracted, we have used Random Forest algorithm to rank the features. Then Recursive Feature Elimination (RFE) and minimum redundancy maximum relevance (mRMR) criterion were applied to extract an optimal set of features. The learning model was trained using Random Forest algorithm. Named as Antigenic, our proposed model demonstrates superior performance compared to the state-of-the-art predictors on a benchmark dataset. Antigenic achieves accuracy, sensitivity and specificity values of 78.04%, 78.99% and 77.08% in 10-fold cross-validation testing respectively. In jackknife cross-validation, the corresponding scores are 80.03%, 80.90% and 79.16% respectively. The source code of Antigenic, along with relevant dataset and detailed experimental results, can be found at https://github.com/srautonu/AntigenPredictor. A publicly accessible web interface has also been established at: http://antigenic.research.buet.ac.bd.

A capsule endoscopy examination of the human small bowel generates a large number of images that have high similarity. In order to reduce the time it takes to review the high similarity images, clinicians will increase the playback speed, typically to 15 frames per second [1]. Associated with this behaviour is an increased probability of overlooking an image that may contain an abnormality. An alternative option to increasing the playback speed is the application of abnormality detection systems to detect abnormalities such as ulcers, tumors, polyps and bleeding. However, applying all of these detection systems requires significant computing time and still produces numerous images with high similarity depending on the specificity of the utilized detection systems. An interesting approach to reduce viewing time is the application of a frame reduction system that reduces the number of images by omitting those with a high similarity of information. The advantage of such a system is that the specialist only needs to review a single image that technically represents a series of images with high similarity. This reduces the total number of images that a specialist must review and importantly, images containing any abnormality are not removed from the review, but simply reduced in number. Thus, the current study developed a frame reduction system using various color models using Bayer images for color texture and a modified local binary pattern (LBP) for structural information. The proposed system achieved a reduction ratio of 93.87%, which is higher than the existing systems and required lesser computation due to the utilization of Bayer images.

Anemia in children is becoming a worldwide problem owing to the unawareness among people regarding the disease, its causes and preventive measures. This study develops a decision support system using data mining techniques that are applied to a database containing data about nutritional factors for children. The data set was taken from NFHS-4, a survey conducted by the Government of India in 2015-16. The work attempts to predict anemia among children and establish a relation between mother's health and diet during pregnancy and its effects on anemic status of her child. It aims to help parents and clinicians to understand the influence of an infant's feeding practices and diet on his/her health and provide guidelines regarding diet to prevent anemia. Earlier, systems were built on computer using medical experts' advicewhich was then translated into algorithms for use. However, this method was time consuming thus, artificial intelligence came into play utilizing knowledge discovery and data mining tools for predictive modeling. The two techniques, decision tree and association rule mining has been applied and compared to select more appropriate technique for this particular task and a model is proposed in the healthcare domain with the aim to reduce the risk of the blood-related disease anemia.

Patients with multiple medical conditions (comorbidity) pose major challenges to clinical decision support systems, since the different Clinical Practice Guidelines (CPG) often involve adverse interactions, such as drug-drug or drug-disease interactions. Moreover, opportunities often exist for optimizing care and resources across multiple CPG. These challenges have been taken up in the state of the art, with many approaches focusing on the static integration of comorbid CIG. Nevertheless, we observe that many aspects often change dynamically over time, in ways that cannot be foreseen - such as delays in care tasks, resource availability, test outcomes, and acute comorbid conditions. To ensure the clinical safety and effectiveness of integrating multiple comorbid CIG, these execution-time difficulties must be considered. Further, when dealing with comorbid conditions, we remark that clinical practitioners typically consider multiple complex solutions, depending on the patient's health profile. Hence, execution-time flexibility, based on dynamic health parameters, is needed to effectively and safely cope with comorbid conditions. In this work, we introduce a flexible, knowledge-driven and execution-time approach to comorbid CIG integration, based on an OWL ontology with clearly defined integration semantics.

INTRODUCTION Visual field testing via standard automated perimetry (SAP) is a commonly used glaucoma diagnosis method. Applying machine learning techniques to the visual field test results, a valid clinical diagnosis of glaucoma solely based on the SAP data is provided. In order to reflect structural-functional patterns of glaucoma on the automated diagnostic models, we propose composite variables derived from anatomically grouped visual field clusters to improve the prediction performance. A set of machine learning-based diagnostic models are designed that implement different input data manipulation, dimensionality reduction, and classification methods. METHODS Visual field testing data of 375 healthy and 257 glaucomatous eyes were used to build the diagnostic models. Three kinds of composite variables derived from the Garway-Heath map and the glaucoma hemifield test (GHT) sector map were included in the input variables in addition to the 52 SAP visual filed locations. Dimensionality reduction was conducted to select important variables so as to alleviate high-dimensionality problems. To validate the proposed methods, we applied four classifiers-linear discriminant analysis, naïve Bayes classifier, support vector machines, and artificial neural networks-and four dimensionality reduction methods-Pearson correlation coefficient-based variable selection, Markov blanket variable selection, the minimum redundancy maximum relevance algorithm, and principal component analysis- and compared their classification performances. RESULTS For all tested combinations, the classification performance improved when the proposed composite variables and dimensionality reduction techniques were implemented. The combination of total deviation values, the GHT sector map, support vector machines, and Markov blanket variable selection obtains the best performance: an area under the receiver operating characteristic curve (AUC) of 0.912. CONCLUSION A glaucoma diagnosis model giving an AUC of 0.912 was constructed by applying machine learning techniques to SAP data. The results show that dimensionality reduction not only reduces dimensions of the input space but also enhances the classification performance. The variable selection results show that the proposed composite variables from visual field clustering play a key role in the diagnosis model.

Low-dose Computed Tomography (CT) imaging is a most commonly used medical imaging modality. Though the reduction in dosage reduces the risk due to radiation, it leads to an increase in noise level. Hence, it is a mandatory requirement to include a noise reduction technique as a pre- and/or post-processing step for better disease diagnosis. The nuclear norm minimization has attracted a great deal of research interest in contemporary years. This paper proposes a low-rank approximation based approach for denoising of CT images by effectively utilizing the global spatial correlation and local smoothness properties. The tensor nuclear norm is used to describe the global properties and the tensor total variation is used to characterize the local smoothness as well as to improve global smoothness. The resulting optimization problem is solved by the Alternative Direction Method of Multipliers (ADMM) technique. Experimental results on simulated and real CT data prove that the proposed methods outperform the state-of-art works.

Classification systems such as ICD-10 for diagnoses or the Swiss Operation Classification System (CHOP) for procedure classification in the clinical treatment are essential for clinical management and information exchange. Traditionally, classification codes are assigned manually or by systems that rely upon concept-based or rule-based classification methods. Such methods can reach their limit easily due to the restricted coverage of handcrafted rules and of the vocabulary in underlying terminological systems. Conventional machine learning approaches normally depend on selected features within a human annotated training set. However, it is quite laborious to obtain a well labeled data set and its generation can easily be influenced by accumulative errors caused by human factors. To overcome this, we will present our processing pipeline for query matching realized through neural networks within the task of medical procedure classification. The pipeline is built upon convolutional neural networks (CNN) and autoencoder with logistic regression. On the task of relevance determination between query and category text, the autoencoder based method has achieved a micro F1 score of 70.29%, while the convolutional based method has reached a micro F1 score of 60.86% with high efficiency. These two algorithms are compared in experiments with different configurations and baselines (SVM, logistic regression) with respect to their suitability for the task of automatic encoding. Advantages and limitations are discussed.

Association measures quantify the observed likelihood a term pair co-occurs versus their predicted co-occurrence together if by chance. This is based both on the terms' individual occurrence frequencies, and their mutual co-occurrence frequencies. One application of association scores is estimating semantic relatedness, which is critical for many natural language processing applications, such as clustering of biomedical and clinical documents and the development of biomedical terminologies and ontololgies. In this paper we propose a method of generating association scores between biomedical concepts to estimate semantic relatedness. We use co-occurrence statistics between Unified Medical Language System (UMLS) concepts to account for lexical variation at the synonymous level, and introduce a process of concept expansion that exploits hierarchical information from the UMLS to account for lexical variation at the hyponymous level. State of the art results are achieved on several standard evaluation datasets, and an in depth analysis of hyper-parameters is presented.

This article presents our steps to integrate complex and partly unstructured medical data into a clinical research database with subsequent decision support. Our main application is an integrated faceted search tool, accompanied by the visualisation of results of automatic information extraction from textual documents. We describe the details of our technical architecture (open-source tools), to be replicated at other universities, research institutes, or hospitals. Our exemplary use cases are nephrology and mammography. The software was first developed in the nephrology domain and then adapted to the mammography use case. We report on these case studies, illustrating how the application can be used by a clinician and which questions can be answered. We show that our architecture and the employed software modules are suitable for both areas of application with a limited amount of adaptations. For example, in nephrology we try to answer questions about the temporal characteristics of event sequences to gain significant insight from the data for cohort selection. We present a versatile time-line tool that enables the user to explore relations between a multitude of diagnosis and laboratory values.