Epidemiology,Faculty Results

Blue machine learning pattern.

Biostatisticians use machine learning approach to improve risk prediction for recurrent health events

"Random forest" algorithm outperforms traditional methods for predicting patient flare-ups, even with incomplete medical histories

A new machine learning approach developed by University of Michigan School of Public Health researchers better predicts when patients might experience recurring health events like disease flare-ups or hospitalizations, even when patient follow-up data is incomplete.

Advertisement for the live recording of the Population Healthy podcast with Matthew Boulton and Natasha Bagdasarian on Friday, April 10 at 11am in the Cornely Community Room at the University of Michigan School of Public Health.

Polio vaccine milestone: Live podcast marks 70th anniversary of historic announcement at U-M

U-M epidemiologist Matthew Boulton and Michigan's chief medical executive Natasha Bagdasarian discuss vaccines, then and now

In today's challenging era for vaccines, the University of Michigan School of Public Health will host a live podcast taping April 11 in recognition of the announcement made 70 years ago at U-M, when the polio vaccine was declared safe and effective to a worldwide audience.

A person walks a cart down a grocery aisle.

Restriction vs. incentives: The complex reality of SNAP food policies

U-M expert: SNAP food restrictions don't improve health outcomes, while incentive programs show promise

Several states are considering restricting SNAP benefit purchases for soda and certain products like chips and candy. Michigan Public Health professor and researcher Kate Bauer explains why such restrictions fail to improve health outcomes while increasing stigma, and offers evidence-based alternatives that preserve dignity for recipients.