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.
Poor medication adherence in heart failure can lead to poor health, but many clinicians are unable to determine who would benefit from interventions to address adherence. We will build machine learning models to identify patients at risk of not taking their medicines using an approach that minimizes potential biases. Electronic health record data will be used in these models, allowing them to be incorporated into interventions to improve medication adherence and reduce the disease burden of heart failure.
