Study: Researchers Use EHRs to Develop Online Predictor of Patient Health Needs

Researchers developed an electronic medical record (EMR)-based online risk model that anticipated the healthcare utilization of patients for a six-month period, according to a study published in the Journal of Medical Internet Research.

Using data from Maine’s statewide health information exchange (HIE), or HealthInfoNet, researchers analyzed a cohort of more than 1.2 million patients constructed with the preceding 12-month EMR. Each patient’s next six-month healthcare resource utilization was retrospectively scored and a decision tree-based predictive model was developed, according to researchers.

The risk model was then integrated into the Maine HIE to forecast patients’ healthcare utilization over the next six months.

According to a statement from the researchers, the model was effective as prospectively predicted risks were consistent with patients’ healthcare utilization over the next six months, across all payers, all diseases and all demographic groups.

“The model and associated online applications were designed for tracking the evolving nature of total population risk, in a longitudinal manner, for health care resource utilization. It will enable more effective care management strategies driving improved patient outcomes,” the researchers wrote.