Using insurance claims to predict and improve hospitalizations and biologics use in members with inflammatory bowel diseases

Abstract

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

Artificial Intelligence for Inflammatory Bowel Diseases (IBD); Accurately Predicting Adverse Outcomes Using Machine Learning

“…For instance, Waljee et al applied their model to a set of Veteran’s Heath Administration data, which limited their sample to a 93% male and old (mean age 59 years) population [ 10 ]; furthermore, public insurance is only used by a minority of US population [ 24 ]. Other prior works that have used ML approaches on private insurance data have been limited by the geographic spread of their sample [ 13 ]. To our knowledge, this is the first study to utilize this ML-based prediction approach on a nationally representative IBD population.…”

“…We constructed 108 variables related to IBD-related care using the claims in the first year of each dataset. These variables were defined based on definitions previously described by Vaughn et al [ 13 ].The variables include the number of IBD-related claims, hospitalizations, emergency department (ED) visits, office visits, procedures, laboratory and imaging tests, medication use, relapse rate, and comorbidities (for a complete list, see Supplementary Table 1) [ 13 ]. Since the OptumLabs Data Warehouse is a curated database of claims, missing data are not an issue when constructing these variables.…”

“…There is consensus in the literature that these are negative outcomes for IBD that should be avoided [ 5 , 6 ]. IBD-related hospitalizations were defined as the presence of any claim for an IBD-related inpatient hospital stay [ 13 ]. Initiation of biologics was defined as a pharmacy or medical claim for adalimumab, certolizumab pegol, infliximab or natalizumab in the second year, with no claim for that medicine in the first year.…”

“…However, studies using the most straightforward data resource, which are administrative databases due to the standardized format and accessibility, to build data-driven predictive models for patients with IBD were limited in their generalizability. The data came from public health insurance records, while the majority (67.2%) of US citizens use private insurance, and their samples have limited geographic spread [ 13 , 24 ]. Additionally, these studies have not attempted to predict other costly negative outcomes such as IBD-related surgeries [ 10 , 13 ].…”

“…The data came from public health insurance records, while the majority (67.2%) of US citizens use private insurance, and their samples have limited geographic spread [ 13 , 24 ]. Additionally, these studies have not attempted to predict other costly negative outcomes such as IBD-related surgeries [ 10 , 13 ]. To our knowledge, no other study has attempted to apply this ML approach to a larger set of private insurance claims data or use novel deep learning methods such as neural networks.…”