Campbell Elizabeth A, Bose Saurav, Masino Aaron J
Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, United States of America.
Department of Biomedical Informatics, Columbia University Medical Center, New York, New York, United States of America.
PLOS Digit Health. 2024 Oct 23;3(10):e0000642. doi: 10.1371/journal.pdig.0000642. eCollection 2024 Oct.
Electronic Health Records (EHRs) are increasingly used to develop machine learning models in predictive medicine. There has been limited research on utilizing machine learning methods to predict childhood obesity and related disparities in classifier performance among vulnerable patient subpopulations. In this work, classification models are developed to recognize pediatric obesity using temporal condition patterns obtained from patient EHR data in a U.S. study population. We trained four machine learning algorithms (Logistic Regression, Random Forest, Gradient Boosted Trees, and Neural Networks) to classify cases and controls as obesity positive or negative, and optimized hyperparameter settings through a bootstrapping methodology. To assess the classifiers for bias, we studied model performance by population subgroups then used permutation analysis to identify the most predictive features for each model and the demographic characteristics of patients with these features. Mean AUC-ROC values were consistent across classifiers, ranging from 0.72-0.80. Some evidence of bias was identified, although this was through the models performing better for minority subgroups (African Americans and patients enrolled in Medicaid). Permutation analysis revealed that patients from vulnerable population subgroups were over-represented among patients with the most predictive diagnostic patterns. We hypothesize that our models performed better on under-represented groups because the features more strongly associated with obesity were more commonly observed among minority patients. These findings highlight the complex ways that bias may arise in machine learning models and can be incorporated into future research to develop a thorough analytical approach to identify and mitigate bias that may arise from features and within EHR datasets when developing more equitable models.
电子健康记录（EHRs）越来越多地用于开发预测医学中的机器学习模型。利用机器学习方法预测儿童肥胖症以及弱势群体亚群中分类器性能的相关差异的研究有限。在这项工作中，我们开发了分类模型，以利用从美国研究人群的患者EHR数据中获得的时间条件模式来识别儿童肥胖症。我们训练了四种机器学习算法（逻辑回归、随机森林、梯度提升树和神经网络），将病例和对照分类为肥胖阳性或阴性，并通过自抽样方法优化超参数设置。为了评估分类器的偏差，我们按人群亚组研究了模型性能，然后使用排列分析来确定每个模型最具预测性的特征以及具有这些特征的患者的人口统计学特征。各分类器的平均AUC-ROC值一致，范围为0.72 - 0.80。虽然通过模型在少数群体亚组（非裔美国人和参加医疗补助计划的患者）中表现更好发现了一些偏差迹象。排列分析显示，在具有最具预测性诊断模式的患者中，弱势群体亚组的患者占比过高。我们假设我们的模型在代表性不足的群体上表现更好，因为与肥胖更密切相关的特征在少数族裔患者中更常见。这些发现凸显了机器学习模型中可能出现偏差的复杂方式，并且可以纳入未来的研究中，以开发一种全面的分析方法，在开发更公平的模型时识别和减轻可能由特征以及EHR数据集中产生的偏差。
