Kim Rachel S, Simon Steven, Powers Brett, Sandhu Amneet, Sanchez Jose, Borne Ryan T, Tumolo Alexis, Zipse Matthew, West J Jason, Aleong Ryan, Tzou Wendy, Rosenberg Michael A
Colorado Center for Personalized Medicine, University of Colorado School of Medicine, Aurora, CO, United States.
Division of Cardiology, University of Colorado School of Medicine, Aurora, CO, United States.
JMIR Med Inform. 2021 Dec 6;9(12):e29225. doi: 10.2196/29225.
The identification of an appropriate rhythm management strategy for patients diagnosed with atrial fibrillation (AF) remains a major challenge for providers. Although clinical trials have identified subgroups of patients in whom a rate- or rhythm-control strategy might be indicated to improve outcomes, the wide range of presentations and risk factors among patients presenting with AF makes such approaches challenging. The strength of electronic health records is the ability to build in logic to guide management decisions, such that the system can automatically identify patients in whom a rhythm-control strategy is more likely and can promote efficient referrals to specialists. However, like any clinical decision support tool, there is a balance between interpretability and accurate prediction.
This study aims to create an electronic health record-based prediction tool to guide patient referral to specialists for rhythm-control management by comparing different machine learning algorithms.
We compared machine learning models of increasing complexity and used up to 50,845 variables to predict the rhythm-control strategy in 42,022 patients within the University of Colorado Health system at the time of AF diagnosis. Models were evaluated on the basis of their classification accuracy, defined by the F1 score and other metrics, and interpretability, captured by inspection of the relative importance of each predictor.
We found that age was by far the strongest single predictor of a rhythm-control strategy but that greater accuracy could be achieved with more complex models incorporating neural networks and more predictors for each participant. We determined that the impact of better prediction models was notable primarily in the rate of inappropriate referrals for rhythm-control, in which more complex models provided an average of 20% fewer inappropriate referrals than simpler, more interpretable models.
We conclude that any health care system seeking to incorporate algorithms to guide rhythm management for patients with AF will need to address this trade-off between prediction accuracy and model interpretability.
为被诊断为心房颤动（AF）的患者确定合适的节律管理策略，仍然是医疗服务提供者面临的一项重大挑战。尽管临床试验已经确定了可能需要采用心率控制或节律控制策略以改善预后的患者亚组，但房颤患者的临床表现和危险因素范围广泛，使得这些方法具有挑战性。电子健康记录的优势在于能够内置逻辑来指导管理决策，这样系统就能自动识别更有可能采用节律控制策略的患者，并促进高效地转诊至专科医生处。然而，与任何临床决策支持工具一样，在可解释性和准确预测之间需要取得平衡。
本研究旨在创建一种基于电子健康记录的预测工具，通过比较不同的机器学习算法，来指导房颤患者转诊至专科医生处进行节律控制管理。
我们比较了复杂度不断增加的机器学习模型，并使用多达50845个变量来预测科罗拉多大学健康系统内42022例房颤诊断时患者的节律控制策略。根据F1评分和其他指标定义的分类准确性以及通过检查每个预测因子的相对重要性得出的可解释性，对模型进行评估。
我们发现，年龄是节律控制策略迄今为止最强的单一预测因子，但结合神经网络的更复杂模型以及为每位参与者纳入更多预测因子，能够实现更高的准确性。我们确定，更好的预测模型的影响主要体现在节律控制不适当转诊率方面，其中更复杂的模型比更简单、更具可解释性的模型平均减少20%的不适当转诊。
我们得出结论，任何寻求纳入算法以指导房颤患者节律管理的医疗保健系统，都需要解决预测准确性和模型可解释性之间这种权衡。
