Improving the Prediction of Persistent High Health Care Utilizers: Retrospective Analysis Using Ensemble Methodology.

BACKGROUND: A small proportion of high-need patients persistently use the bulk of health care services and incur disproportionate costs. Population health management (PHM) programs often refer to these patients as persistent high utilizers (PHUs). Accurate PHU prediction enables PHM programs to better align scarce health care resources with high-need PHUs while generally improving outcomes. While prior research in PHU prediction has shown promise, traditional regression methods used in these studies have yielded limited accuracy. OBJECTIVE: We are seeking to improve PHU predictions with an ensemble approach in a retrospective observational study design using insurance claim records. METHODS: We defined a PHU as a patient with health care costs in the top 20% of all patients for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in next 24 months. Our study population included 165,595 patients in the Johns Hopkins Health Care plan, with 8359 (5.1%) patients identified as PHUs in 2014 and 2015. We assessed the performance of several standalone machine learning methods and then an ensemble approach combining multiple models. RESULTS: The candidate ensemble with complement naïve Bayes and random forest layers produced increased sensitivity and positive predictive value (PPV; 49.0% and 50.3%, respectively) compared to logistic regression (46.8% and 46.1%, respectively). CONCLUSIONS: Our results suggest that ensemble machine learning can improve prediction of care management needs. Improved PPV implies reduced incorrect referral of low-risk patients. With the improved sensitivity/PPV balance of this approach, resources may be directed more efficiently to patients needing them most.

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data.

BACKGROUND: A high proportion of health care services are persistently utilized by a small subpopulation of patients. To improve clinical outcomes while reducing costs and utilization, population health management programs often provide targeted interventions to patients who may become persistent high users/utilizers (PHUs). Enhanced prediction and management of PHUs can improve health care system efficiencies and improve the overall quality of patient care. OBJECTIVE: The aim of this study was to detect key classes of diseases and medications among the study population and to assess the predictive value of these classes in identifying PHUs. METHODS: This study was a retrospective analysis of insurance claims data of patients from the Johns Hopkins Health Care system. We defined a PHU as a patient incurring health care costs in the top 20% of all patients' costs for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in 2014-2015. We applied latent class analysis (LCA), an unsupervised clustering approach, to identify patient subgroups with similar diagnostic and medication patterns to differentiate variations in health care utilization across PHUs. Logistic regression models were then built to predict PHUs in the full population and in select subpopulations. Predictors included LCA membership probabilities, demographic covariates, and health utilization covariates. Predictive powers of the regression models were assessed and compared using standard metrics. RESULTS: We identified 164,221 patients with continuous enrollment between 2013 and 2015. The mean study population age was 19.7 years, 55.9% were women, 3.3% had ≥1 hospitalization, and 19.1% had 10+ outpatient visits in 2013. A total of 8359 (5.09%) patients were identified as PHUs in both 2014 and 2015. The LCA performed optimally when assigning patients to four probability disease/medication classes. Given the feedback provided by clinical experts, we further divided the population into four diagnostic groups for sensitivity analysis: acute upper respiratory infection (URI) (n=53,232; 4.6% PHUs), mental health (n=34,456; 12.8% PHUs), otitis media (n=24,992; 4.5% PHUs), and musculoskeletal (n=24,799; 15.5% PHUs). For the regression models predicting PHUs in the full population, the F1-score classification metric was lower using a parsimonious model that included LCA categories (F1=38.62%) compared to that of a complex risk stratification model with a full set of predictors (F1=48.20%). However, the LCA-enabled simple models were comparable to the complex model when predicting PHUs in the mental health and musculoskeletal subpopulations (F1-scores of 48.69% and 48.15%, respectively). F1-scores were lower than that of the complex model when the LCA-enabled models were limited to the otitis media and acute URI subpopulations (45.77% and 43.05%, respectively). CONCLUSIONS: Our study illustrates the value of LCA in identifying subgroups of patients with similar patterns of diagnoses and medications. Our results show that LCA-derived classes can simplify predictive models of PHUs without compromising predictive accuracy. Future studies should investigate the value of LCA-derived classes for predicting PHUs in other health care settings.

Mobile app validation: a digital health scorecard approach.

While digital health solutions continue to grow in number and in complexity, the ability for stakeholders in healthcare to easily discern quality lags far behind. This challenge is in part due to the lack of a transparent and standardized approach to validation. Evaluation of mobile health applications (apps) is further burdened by low barriers to development and direct-to-user marketing, leading to a crowded and confusing landscape. In this context, we investigated the pragmatic application of a previously described framework for digital health validation, the Digital Health Scorecard, in a cohort of 22 popular mobile health oncology apps. The apps evaluated using this framework performed poorly, scoring 49.4% across all evaluation criteria as a group. Performance across component domains varied considerably with cost scoring highest at 100%, usability at 56.7%, technical at 37.3%, and clinical at 15.9%. satisfaction of prospectively determined end-user requirements derived from patient, family, and clinician consensus scored 37.2%. While cost outperformed consistently and usability was adequate, the results also suggested that apps suffered from significant technical limitations, were of limited clinical value, and generally did not do what end users wanted. These large gaps further support the need for transparent and standardized evaluation to help all stakeholders in healthcare improve the quality of mobile health.

Digital health: a path to validation.

Digital health solutions continue to grow in both number and capabilities. Despite these advances, the confidence of the various stakeholders - from patients and clinicians to payers, industry and regulators - in medicine remains quite low. As a result, there is a need for objective, transparent, and standards-based evaluation of digital health products that can bring greater clarity to the digital health marketplace. We believe an approach that is guided by end-user requirements and formal assessment across technical, clinical, usability, and cost domains is one possible solution. For digital health solutions to have greater impact, quality and value must be easier to distinguish. To that end, we review the existing landscape and gaps, highlight the evolving responses and approaches, and detail one pragmatic framework that addresses the current limitations in the marketplace with a path toward implementation.