An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data,British Journal of Anaesthesia

当前位置： X-MOL 学术 › Br. J. Anaesth. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data
British Journal of Anaesthesia ( IF 9.1 ) Pub Date : 2019-10-15 , DOI: 10.1016/j.bja.2019.07.030
Brian L Hill ₁ , Robert Brown ₁ , Eilon Gabel ₂ , Nadav Rakocz ₁ , Christine Lee ₃ , Maxime Cannesson ₂ , Pierre Baldi ₄ , Loes Olde Loohuis ₅ , Ruth Johnson ₁ , Brandon Jew ₆ , Uri Maoz ₇ , Aman Mahajan ₈ , Sriram Sankararaman ₉ , Ira Hofer ₂ , Eran Halperin ₁₀

Affiliation

Department of Computer Science, University of California, Los Angeles, CA, USA.
Department of Anaesthesiology and Perioperative Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA.
Department of Anaesthesiology and Perioperative Care, University of California, Irvine, CA, USA; Department of Biomedical Engineering, University of California, Irvine, CA, USA.
Department of Biomedical Engineering, University of California, Irvine, CA, USA; Department of Computer Science, University of California, Irvine, CA, USA.
Center for Neurobehavioral Genetics, Semel Institute for Neuroscience and Human Behaviour, University of California, Los Angeles, CA, USA.
Bioinformatics Interdepartmental Program, University of California, Los Angeles, CA, USA.
Department of Anaesthesiology and Perioperative Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA; Crean College of Health and Behavioural Sciences, Chapman University, Orange, CA, USA; Schmid College of Science and Technology, Chapman University, Orange, CA, USA; Institute for Interdisciplinary Brain and Behavioural Sciences, Chapman University, Orange, CA, USA; Anderson School of Management at UCLA, Los Angeles, CA, USA; Biology and Bioengineering, California Institute of Technology, Pasadena, CA, USA.
Department of Anaesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, PA, USA.
Department of Computer Science, University of California, Los Angeles, CA, USA; Department of Human Genetics, University of California, Los Angeles, CA, USA.
Department of Computer Science, University of California, Los Angeles, CA, USA; Department of Anaesthesiology and Perioperative Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, USA; Department of Human Genetics, University of California, Los Angeles, CA, USA; Department of Biomathematics, University of California, Los Angeles, CA, USA.

Background

Rapid, preoperative identification of patients with the highest risk for medical complications is necessary to ensure that limited infrastructure and human resources are directed towards those most likely to benefit. Existing risk scores either lack specificity at the patient level or utilise the American Society of Anesthesiologists (ASA) physical status classification, which requires a clinician to review the chart.

Methods

We report on the use of machine learning algorithms, specifically random forests, to create a fully automated score that predicts postoperative in-hospital mortality based solely on structured data available at the time of surgery. Electronic health record data from 53 097 surgical patients (2.01% mortality rate) who underwent general anaesthesia between April 1, 2013 and December 10, 2018 in a large US academic medical centre were used to extract 58 preoperative features.

Results

Using a random forest classifier we found that automatically obtained preoperative features (area under the curve [AUC] of 0.932, 95% confidence interval [CI] 0.910–0.951) outperforms Preoperative Score to Predict Postoperative Mortality (POSPOM) scores (AUC of 0.660, 95% CI 0.598–0.722), Charlson comorbidity scores (AUC of 0.742, 95% CI 0.658–0.812), and ASA physical status (AUC of 0.866, 95% CI 0.829–0.897). Including the ASA physical status with the preoperative features achieves an AUC of 0.936 (95% CI 0.917–0.955).

Conclusions

This automated score outperforms the ASA physical status score, the Charlson comorbidity score, and the POSPOM score for predicting in-hospital mortality. Additionally, we integrate this score with a previously published postoperative score to demonstrate the extent to which patient risk changes during the perioperative period.

中文翻译：

基于机器学习的自动化模型使用易于提取的术前电子健康记录数据预测术后死亡率

背景

有必要在术前快速识别医疗并发症风险最高的患者，以确保将有限的基础设施和人力资源用于最有可能受益的患者。现有的风险评分要么缺乏患者层面的特异性，要么利用美国麻醉师协会 (ASA) 的身体状况分类，这需要临床医生审查图表。

方法

我们报告了使用机器学习算法（特别是随机森林）来创建完全自动化的评分，该评分仅基于手术时可用的结构化数据来预测术后住院死亡率。2013 年 4 月 1 日至 2018 年 12 月 10 日期间在美国一家大型学术医疗中心接受全身麻醉的 53 097 名手术患者（死亡率 2.01%）的电子健康记录数据被用于提取 58 个术前特征。

结果

使用随机森林分类器，我们发现自动获得的术前特征（曲线下面积 [AUC] 为 0.932，95% 置信区间 [CI] 0.910–0.951）优于术前评分以预测术后死亡率 (POSPOM) 评分（AUC 为 0.660， 95% CI 0.598–0.722）、Charlson 合并症评分（AUC 为 0.742，95% CI 0.658–0.812）和 ASA 身体状况（AUC 为 0.866，95% CI 0.829–0.897）。将 ASA 身体状况与术前特征包括在内，AUC 达到 0.936（95% CI 0.917–0.955）。