For the study, a team of researchers from Indianapolis-based Indiana University developed two decision models to predict whether patients at an unidentified safety-net hospital would need social service referrals, such as mental health, dietitian or social work services. One decision model used clinical data, while the other used clinical data alongside community-level socioeconomic and public health data.
The researchers found both models were able to successfully predict a patient’s need for social service referrals with “considerable accuracy.”
“While the use of [social determinants of health] did not result in significant performance improvements, our approach represents a novel and important application of risk predictive modeling,” the study authors concluded.
More articles on data analytics & precision medicine:
Froedtert taps PeraHealth for clinical surveillance, predictive analytics
Mayo Clinic collaborates with Veritas Genetics on whole-genome sequencing
Microsoft partners with Adaptive Biotechnologies to ‘decode’ immune systems with AI
