Predicting Risk of Hospitalization or Death Among Patients Receiving Primary Care in the Veterans Health Administration

Abstract

Prediction models using electronic clinical data accurately identified patients with elevated risk for hospitalization or death. This information can enhance the coordination of care for patients with complex clinical conditions.

Disruptive Models in Primary Care: Caring for High-Needs, High-Cost Populations

“…8 As a result, the term Bhigh-needs, high-cost^(HNHC) has emerged to describe these patients. 9,10 Sophisticated algorithms incorporating comorbidities, 11 socioeconomic factors, behavioral health and substance abuse diagnoses, geographic factors, and qualitative feedback from providers and staff have been developed for identifying HNHC patients (see Fig. 1).…”

Resources and Capabilities of the Department of Veterans Affairs to Provide Timely and Accessible Care to Veterans

“…Rates of mortality declined more quickly in VA over time than in non-VA settings (Borzecki et al, 2010). Veterans treated in VA and non-VA settings also experienced similar mortality rates (Wang et al, 2013a;Berlowitz et al, 2005). Adjusted mortality was lower among Veterans who used VA care compared with male Medicare Advantage beneficiaries over 65 years of age (Selim, Berlowitz, et al, 2010;Selim, Kazis, Qian, et al, 2009;Selim et al, 2006;Selim et al, 2007).…”

“…Care management is an active area of research and development in VA and other organizations. For this reason, we did not attempt to document the complete inventory of IT capabilities that support care management in VA, which includes a wide range of functionalities such as registries, dashboards, and predictive analytics (Wang et al, 2013a). Few such programs have been formally evaluated and it is difficult to assess the capability without such an evaluation.…”

Partnered Research in Healthcare Delivery Redesign for High-Need, High-Cost Patients: Development and Feasibility of an Intensive Management Patient-Aligned Care Team (ImPACT)

“…Patients were eligible for the program if their total VA healthcare costs were in the top 5 % between 1 October 2011 and 30 June 2012, or if their risk for one-year hospitalization was in the top 5 % (using a VA risk-prediction algorithm). 43 Patients were excluded if they were already enrolled in another intensive management program (e.g., mental health intensive case management, home-based primary care, palliative care) or if they were hospitalized or in long-term care for over half of the baseline period. Selected patients were approached during hospitalizations, emergency department visits, before or after clinical appointments, and by letter and telephone.…”