The development of computerized healthcare has been powered by diagnostic imaging and machine learning techniques. In particular, recent advances in deep learning have opened a new era in support of multimedia healthcare distribution. For earlier detection of Alzheimer’s disease, the study suggested the Improved Deep Learning Algorithm (IDLA) and statistically significant text information. The specific information in clinical text includes the age, sex and genes of the person and apolipoprotein E; the brain function is established using resting-state functional data (MRI) for the measurement of connectivity in the brain regions. A specialized network of autoencoders is used in earlier diagnosis to distinguish between natural aging and disorder progression. The suggested approach incorporates effectively biased neural network functionality and allows a reliable Alzheimer’s disease recognition. In comparison with conventional classifiers depends on time series R-fMRI results, the proposed deep learning algorithm has improved significantly and, in the best cases, the standard deviation reduced by 45%, indicating the forecast model is more reliable and efficient in relation to conventional methodologies. The work examines the benefits of improved deep learning algorithms from recognizing high-dimensional information in healthcare and can lead to the early diagnosis and prevention of Alzheimer’s disease.

中文翻译：

---

用于早期检测阿尔茨海默病的静息状态 fMRI 和改进的深度学习算法

诊断成像和机器学习技术推动了计算机化医疗保健的发展。特别是，深度学习的最新进展开启了支持多媒体医疗保健分发的新时代。为了更早地检测阿尔茨海默病，该研究建议使用改进的深度学习算法 (IDLA) 和具有统计意义的文本信息。临床文本中的具体信息包括人的年龄、性别和基因以及载脂蛋白E；大脑功能是使用静息状态功能数据 (MRI) 建立的，用于测量大脑区域的连通性。在早期诊断中使用专门的自动编码器网络来区分自然衰老和疾病进展。建议的方法结合了有效的偏置神经网络功能，并允许可靠的阿尔茨海默病识别。与依赖时间序列R-fMRI结果的传统分类器相比，所提出的深度学习算法有了显着的改进，在最好的情况下，标准偏差降低了45%，表明预测模型相对于传统的预测模型更加可靠和高效。方法论。这项工作检查了改进的深度学习算法在医疗保健中识别高维信息的好处，并可以导致阿尔茨海默病的早期诊断和预防。在最好的情况下，标准偏差减少了 45%，表明预测模型相对于传统方法更加可靠和高效。这项工作检查了改进的深度学习算法在医疗保健中识别高维信息的好处，并可以导致阿尔茨海默病的早期诊断和预防。在最好的情况下，标准偏差减少了 45%，表明预测模型相对于传统方法更加可靠和高效。这项工作检查了改进的深度学习算法在医疗保健中识别高维信息的好处，并可以导致阿尔茨海默病的早期诊断和预防。