Author information

1 UCLA Semel Institute for Neuroscience and Human Behavior, Los Angeles, CA, USA.

2 UCLA Center for Inflammatory Bowel Diseases, Vatche and Tamar Manoukian Division of Digestive Disease, David Geffen School of Medicine, Los Angeles, CA, USA; Gehr Family Center for Health Systems Science, Division of Geriatric, Hospital, Palliative and General Internal Medicine, Department of Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA; Leonard D. Schaeffer Center for Health Policy and Economics, University of Southern California, Los Angeles, University of Southern California, Los Angeles, CA, USA.

3 UCLA David Geffen School of Medicine, Los Angeles, CA, USA; UCLA Department of Biomathematics, Los Angeles, CA, USA; Eisenhower Medical Center, Department of Internal Medicine, Rancho Mirage, CA, USA.

4 UCLA Department of Mathematics, Los Angeles, CA, USA.

5 UCLA Center for Inflammatory Bowel Diseases, Vatche and Tamar Manoukian Division of Digestive Disease, David Geffen School of Medicine, Los Angeles, CA, USA. Electronic address: DHommes@mednet.ucla.edu.

6 UCLA Semel Institute for Neuroscience and Human Behavior, Los Angeles, CA, USA; UCLA Departments of Psychiatry, Neurology, Radiology, Psychology, Biomedical Physics and Bioengineering, and California Nanosystems Institute, Los Angeles, CA, USA.

Abstract

OBJECTIVE: Inflammatory Bowel Disease (IBD) is an inflammatory disorder of the gastrointestinal tract that can necessitate hospitalization and the use of expensive biologics. Models predicting these interventions may improve patient quality of life and reduce expenditures.

MATERIALS AND METHODS: We used insurance claims from 2011-2013 to predict IBD-related hospitalizations and the initiation of biologics. We derived and optimized our model from a 2011 training set of 7771 members, predicting their outcomes the following year. The best-performing model was then applied to a 2012 validation set of 7450 members to predict their outcomes in 2013.

RESULTS: Our models predicted both IBD-related hospitalizations and the initiation of biologics, with average positive predictive values of 17% and 11%, respectively - each a 200% improvement over chance. Further, when we used topic modeling to identify four member subpopulations, the positive predictive value of predicting hospitalization increased to 20%.

DISCUSSION: We show that our hospitalization model, in concert with a mildly-effective interventional treatment plan for members identified as high-risk, may both improve patient outcomes and reduce insurance expenditures.

CONCLUSION: The success of our approach provides a roadmap for how claims data can complement traditional medical decision making with personalized, data-driven predictive medicine.