Machine learning using institution-specific multi-modal electronic health records improves mortality risk prediction for cardiac surgery patients.
Machine learning using institution-specific multi-modal electronic health records improves mortality risk prediction for cardiac surgery patients.
复制标题
DOI：
10.1016/j.xjon.2023.03.010
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Iyengar, Ravi
中科院分区：
文献类型：
--
作者：
Weiss, Aaron J;Yadaw, Arjun S;Meretzky, David L;Levin, Matthew A;Adams, David H;McCardle, Ken;Pandey, Gaurav;Iyengar, Ravi
胸外科医生协会的风险评分被广泛用于评估特定心脏手术的发病率和死亡率风险，但可能并不是在所有患者中都表现最佳。在一组接受心脏手术的患者中，我们开发了一个基于数据驱动的、特定于机构的基于机器学习的模型，该模型来自多模式电子健康记录，并与胸科外科医生协会的模型进行了比较。纳入了2011至2016年间接受心脏手术的所有成年患者。提取了常规的电子健康记录管理、人口统计学、临床、血流动力学、实验室、药理学和程序数据特征。结果是术后死亡率。该数据库被随机分为培训(开发)和测试(评估)队列。使用6个评价指标对使用4种分类算法建立的模型进行了比较。将最终模型的性能与胸科外科学会的模型在7个指标的外科手术中进行了比较。共有6392名患者被纳入，并通过4016个特征进行描述。总死亡率为3.0%(n=9193)。仅使用没有丢失数据的特征(336个特征)的XGBoost算法产生了性能最佳的预测值。当应用于测试集时，预测器表现良好(F-MEASURE=0.978；精度=0.756；召回率=0.795；准确率=0.986；接收器操作特征曲线下面积=0.978；精度-召回曲线下面积(=0.804))。当在测试集中的索引程序上进行评估时，极端梯度助推器始终显示出比胸科外科学会模型更好的性能。使用特定于机构的多模式电子健康记录的机器学习模型，与护理标准、人群衍生的胸科外科医生协会模型相比，可能会提高预测接受心脏手术的个体患者死亡率的性能。特定于机构的模型可能提供对基于人群的风险预测的补充洞察力，以帮助患者层面的决策。
The Society of Thoracic Surgeons risk scores are widely used to assess risk of morbidity and mortality in specific cardiac surgeries but may not perform optimally in all patients. In a cohort of patients undergoing cardiac surgery, we developed a data-driven, institution-specific machine learning–based model inferred from multi-modal electronic health records and compared the performance with the Society of Thoracic Surgeons models. All adult patients undergoing cardiac surgery between 2011 and 2016 were included. Routine electronic health record administrative, demographic, clinical, hemodynamic, laboratory, pharmacological, and procedural data features were extracted. The outcome was postoperative mortality. The database was randomly split into training (development) and test (evaluation) cohorts. Models developed using 4 classification algorithms were compared using 6 evaluation metrics. The performance of the final model was compared with the Society of Thoracic Surgeons models for 7 index surgical procedures. A total of 6392 patients were included and described by 4016 features. Overall mortality was 3.0% (n = 193). The XGBoost algorithm using only features with no missing data (336 features) yielded the best-performing predictor. When applied to the test set, the predictor performed well (F-measure = 0.775; precision = 0.756; recall = 0.795; accuracy = 0.986; area under the receiver operating characteristic curve = 0.978; area under the precision-recall curve = 0.804). eXtreme Gradient Boosting consistently demonstrated improved performance over the Society of Thoracic Surgeons models when evaluated on index procedures within the test set. Machine learning models using institution-specific multi-modal electronic health records may improve performance in predicting mortality for individual patients undergoing cardiac surgery compared with the standard-of-care, population-derived Society of Thoracic Surgeons models. Institution-specific models may provide insights complementary to population-derived risk predictions to aid patient-level decision making.
影响因子：
3.7
作者：
Loghmanpour NA;Druzdzel MJ;Antaki JF
通讯作者：
Antaki JF