Finding a predictive model for post-hospitalization adverse events
Using a logistic regression model, the following factors were predictive of adverse events during a 6 week post-hospitalization period: whether or not the primary care provider knew of the patient’s initial hospitalization, patient alcohol use, patient prescription drug use, distance to the hospital from the patient’s residence, driving time to the hospital from the patient’s residence, patient education level, and indicators for patient urbanicity classification. The model has a 70.9% accuracy rate in the test dataset for predicting patient’s with post-hospitalization adverse events and may serve as a starting point in the discussion on how to reduce hospital readmission rates.
Learning Areas:Administration, management, leadership
Provision of health care to the public
Name risk factors for post-discharge adverse events
Qualified on the content I am responsible for because: 20 years of progressive public health research experience. Supervised this student's (Katrina McAffee) work in preparing the submission to APHA.
Any relevant financial relationships? No
I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.