Saha Shumit, Ross Heather, Velmovitsky Pedro Elkind, Wang Chloe X, Vishram-Nielsen Julie K K, Manlhiot Cedric, Wang Bo, Cafazzo Joseph A
Centre for Digital Therapeutics, Techna Institute, University Health Network, Toronto, ON, Canada.
Institute of Health Policy, Management, and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada.
Sci Rep. 2025 Aug 22;15(1):30979. doi: 10.1038/s41598-025-16376-9.
Heart failure (HF) is a condition with periods of stability interrupted by periods of worsening symptoms, known as decompensation episodes. Digital interventions are promising tools to alleviate burdens on HF management through automated alerts at the earliest decompensation sign. To accomplish this, our lab developed Medly, an expert system-enhanced digital therapeutic program for HF patients. Medly's algorithm is a knowledge-based system that analyzes weight, blood pressure, and heart rate and sends automated alerts to clinicians and patients if deterioration is identified. Rules were set conservatively to account for false negatives. However, reducing false negatives resulted in an increase in false positives, which can lead to unnecessary clinical workload. Further, patients' electronic health records (EHR) were not used when developing the rules-based algorithm. This study aimed to enhance Medly's performance with machine learning and include a richer set of data, including EHR, for predicting decompensated HF episodes. We performed a retrospective study using XGBoost for the binary classification of whether the patient needed to be contacted for a possible decompensation episode. Features included blood pressure, weight change, heart rate, and EHR data (e.g., blood work, medication history). We further performed interpretability analysis to investigate the importance of including EHR data in the model. The enhanced algorithm achieved 98.08% accuracy, 95.26% sensitivity, 98.86% specificity, and a PPV of 88.18% - a marked improvement over the 55.8% in the rules-based algorithm. EHR data, mainly B-type natriuretic peptide (BNP) and total cholesterol, was crucial in predicting decompensation and correcting false-positive alerting.
心力衰竭（HF）是一种症状稳定期会被症状恶化期（即失代偿发作期）打断的疾病。数字干预是很有前景的工具，可通过在最早出现失代偿迹象时发出自动警报来减轻HF管理的负担。为实现这一目标，我们实验室开发了Medly，这是一个为HF患者提供的专家系统增强型数字治疗方案。Medly的算法是一个基于知识的系统，可分析体重、血压和心率，并在识别出病情恶化时向临床医生和患者发送自动警报。规则设定得较为保守，以应对假阴性情况。然而，减少假阴性导致假阳性增加，这可能会导致不必要的临床工作量。此外，在开发基于规则的算法时未使用患者的电子健康记录（EHR）。本研究旨在通过机器学习提高Medly的性能，并纳入更丰富的数据集（包括EHR）来预测失代偿性HF发作。我们使用XGBoost进行了一项回顾性研究，对患者是否需要因可能的失代偿发作而被联系进行二元分类。特征包括血压、体重变化、心率和EHR数据（如血液检查、用药史）。我们还进行了可解释性分析，以研究在模型中纳入EHR数据的重要性。增强后的算法准确率达到98.08%，灵敏度为95.26%，特异性为98.86%，阳性预测值为88.18%，与基于规则的算法的55.8%相比有显著提高。EHR数据，主要是B型利钠肽（BNP）和总胆固醇，对于预测失代偿和纠正假阳性警报至关重要。
