By Mary L. Martialay
In partnership with local health insurer CDPHP, researchers from the Institute for Data Exploration and Applications (IDEA) at Rensselaer are using artificial intelligence to improve patient health by developing a better understanding of high needs patients and identifying aspects of care that lead to better outcomes.
“It’s not enough to just figure out who are the highest needs patients, you really need to know why and what approaches can help them,” said Kristin Bennett, a Rensselaer math professor and associate director of IDEA. “Our approach develops explainable models that help us understand who these high needs patients are, why some people in this group do well, and some do not.”
The project builds on the “cadre” modeling technique developed by Bennett. As opposed to deep learning, in which a computer identifies a pattern but the path to its decision is not clear, cadre models bring another level of understanding into the equation.
“CDPHP is incredibly excited to be partnering with Rensselaer on this innovative project,” said CDPHP President and CEO Dr. John D. Bennett, who earned his bachelor’s degree in biology from Rensselaer in 1974. “As part of its commitment to improving patient care through population health, CDPHP is working closely with researchers at Rensselaer to understand the best approaches to identify at-risk patients, and develop strategies that will improve their health.”
Standard machine learning and deep learning models could predict which patients may require extensive care in the future, but cannot explain why or offer remedies. Cadre models identify subgroups of at risk-patients, offer doctors an explanation for why those patients may be facing health challenges, and also suggest services that will improve their health.
“Instead of bringing our assumptions to the table, the cadre models show us what’s relevant,” Bennett said. “So it discovers the important factors that help us find people who could benefit from different interventions. It’s a powerful technique.”
Bennett is attracting the attention of hospitals and health insurers for her work in “precision health care,” which uses data to improve the overall efficiency of healthcare. For example, in a partnership with a local hospital, she recently analyzed Medicaid patient records to understand why some patients are likely to land back in the emergency room within three days of a visit.
Malik Magon-Ishmail, Rensselaer professor of computer science, and Jason Kuruzovich, Rensselaer associate professor of management, will join Bennett in the research.