Generalizable prediction of medication adherence in heart failure

心力衰竭药物依从性的普遍预测

• 批准号: 10365929
• 负责人: Samrachana Adhikari
• 金额: $ 74.71万
• 依托单位: NEW YORK UNIVERSITY SCHOOL OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-03-15 至 2026-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10365929
• 关键词: Address; Adherence; Algorithms; Big Data; Calibration; Cessation of life; Clinical; Clinical Data; Communities; Complex; Data; Data Element; Development; Economic Factors; Electronic Health Record; Ensure; Goals; Health; Health system; Healthcare Systems; Heart failure; Individual; Intervention; Lead; Link; Location; Machine Learning; Malignant Neoplasms; Measurement; Medicine; Modeling; Neighborhoods; Outcome; Patient-Focused Outcomes; Patients; Performance; Pharmaceutical Preparations; Pharmacy facility; Population Heterogeneity; Process; Provider; Race; Risk; Risk Factors; System; Techniques; Time; Update; Urban Health; Validation; Work; algorithm development; base; burden of illness; clinical care; contextual factors; electronic data; evidence base; flexibility; health data; high risk; hospital readmission; hospitalization rates; improved; improved outcome; innovation; machine learning algorithm; machine learning model; medication compliance; medication nonadherence; mortality; novel; patient population; patient subsets; point of care; population based; prediction algorithm; predictive modeling; social; social determinants; social factors; social health determinants; socioeconomics; supervised learning; tool

Project Summary/Abstract Heart failure (HF) is associated with high rates of hospitalization and mortality. While a number of evidence- based therapies have been shown to improve outcomes for patients with HF, nearly half of these patients are not regularly taking their medications. Although medication adherence can be improved through timely interventions, it is challenging for clinicians to accurately identify and predict medication non-adherence at the point of care. The challenge persists partly because medication adherence is a complex process influenced by an interplay of a multitude of patient-, provider-, system-, community-, and therapy-related factors. This gap in identifying patients at risk of non-adherence can be addressed through increasing availability of relevant data from electronic health records (EHRs), which affords the potential to make accurate, real time predictions of adherence in HF. In particular, recent linkages of EHR and pharmacy data has created opportunity for incorporation of prior medication fills into EHR-based adherence prediction models that are updated continuously. Using machine learning (ML) techniques with such data allows for incorporation of a large number of intercorrelated risk factors and their interactions into models and for accommodating continuous updates as new information becomes available. Our objective is to build a ML-based algorithm to predict adherence among patients with HF. The specific aims are: 1) to develop supervised ML algorithms to predict medication adherence among HF patients, using EHR clinical data, linked pharmacy fill data, and location- based social determinants data from a large, urban health system that cares for a diverse patient population; 2) to assess fairness of the developed algorithms by evaluating cross-validated prediction and calibration on patient subgroups based on social and economic factors, to ensure that the desirable prediction performance is maintained for the diverse groups; and 3) to assess generalizability of the algorithms through validation in a second large, urban health system caring for a diverse population. Our approach is innovative and novel in several ways. First, we will take advantage of linkages between pharmacy fill information and the EHR to incorporate pharmacy data in our models. Second, we utilize geocoding of patient addresses combined with publicly available data to incorporate neighborhood-level social determinants of health, which are among the most important predictors of adherence, into our models. Third, we will assess fairness of the model by evaluating the predictive performance and calibration on patients from diverse backgrounds. Fourth, we will ensure generalizability of the prediction algorithm by developing it in one diverse health system and validating the algorithm in a second diverse health system. These models will be developed such that they can be used for point-of-care adherence prediction. Our long term goal is to be able to implement them into the EHR, at which point they can be incorporated into interventions to address medication adherence and, ultimately, improve both adherence and clinical outcomes for patients with HF.

项目总结/摘要 心力衰竭（HF）与高住院率和死亡率相关。尽管有一些证据- 基础治疗已被证明可以改善HF患者的结局，近一半的患者 不定期服药。虽然药物治疗的依从性可以通过及时 由于干预措施的限制，临床医生在治疗期间准确识别和预测药物不依从性是一项挑战。 护理点。挑战仍然存在，部分原因是药物依从性是一个复杂的过程， 许多患者、提供者、系统、社区和治疗相关因素的相互作用。中的这一空白 通过增加相关数据的可用性，可以识别存在不依从风险的患者 从电子健康记录（EHR），它提供了准确的潜力，真实的时间预测， HF中的依从性。特别是，最近EHR和药房数据的联系为以下方面创造了机会： 将先前的药物治疗填充合并到更新的基于EHR的依从性预测模型中 不断地。使用机器学习（ML）技术与这些数据允许纳入一个大的 将相互关联的风险因素及其相互作用纳入模型， 随着新信息的出现而更新。我们的目标是建立一个基于ML的算法来预测 HF患者的依从性。具体目标是：1）开发监督ML算法来预测 HF患者的药物依从性，使用EHR临床数据，链接的药房填充数据和位置- 基于来自照顾不同患者人群的大型城市卫生系统的社会决定因素数据; 2） 通过评估交叉验证的预测和校准来评估所开发算法的公平性， 基于社会和经济因素的患者亚组，以确保理想的预测性能 为不同的群体保持;和3）通过在一个 第二个大的城市卫生系统照顾不同的人口。我们的方法是创新和新颖的， 几种方式。首先，我们将利用药房配药信息和EHR之间的联系， 将药房数据纳入我们的模型。其次，我们利用患者地址的地理编码， 公共可用数据，以纳入社区一级的健康社会决定因素，这些因素是 最重要的依从性预测因素纳入我们的模型中。第三，我们将评估模型的公平性， 评估来自不同背景的患者的预测性能和校准。四是 通过在一个不同的卫生系统中开发预测算法并进行验证，确保预测算法的通用性 在第二个不同的健康系统中的算法。这些模型将被开发，以便它们可以用于 用于即时护理依从性预测。我们的长期目标是能够将它们实施到EHR中， 在这一点上，他们可以被纳入干预措施，以解决药物依从性，最终， 改善HF患者的依从性和临床结局。