Machine Learning Predictive Outcomes Modeling in Inflammatory Bowel Diseases.

There is a rising interest in use of big data approaches to personalize treatment of inflammatory bowel diseases (IBDs) and to predict and prevent outcomes such as disease flares and therapeutic nonresponse. Machine learning (ML) provides an avenue to identify and quantify features across vast quantities of data to produce novel insights in disease management. In this review, we cover current approaches in ML-driven predictive outcomes modeling for IBD and relate how advances in other fields of medicine may be applied to improve future IBD predictive models. Numerous studies have incorporated clinical, laboratory, or omics data to predict significant outcomes in IBD, including hospitalizations, outpatient corticosteroid use, biologic response, and refractory disease after colectomy, among others, with considerable health care dollars saved as a result. Encouraging results in other fields of medicine support efforts to use ML image analysis-including analysis of histopathology, endoscopy, and radiology-to further advance outcome predictions in IBD. Though obstacles to clinical implementation include technical barriers, bias within data sets, and incongruence between limited data sets preventing model validation in larger cohorts, ML-predictive analytics have the potential to transform the clinical management of IBD. Future directions include the development of models that synthesize all aforementioned approaches to produce more robust predictive metrics.

The Role of Health Disparities and Socioeconomic Status in Emergent Gastrointestinal Procedures.

Objectives: There is limited data describing the role of health disparity factors and socioeconomic status (SES) on emergent versus nonemergent gastrointestinal (GI) procedures within pediatrics. We aimed to characterize risk factors and determine the role of SES on emergent versus nonemergent GI care. We hypothesized that patients with lower SES incur higher risk of having emergent procedures performed. Methods: Retrospective chart review was performed between 2012 and 2016, with 2556 patient records reviewed. Demographic data and SES categories were determined. The majority of emergent procedures were performed on an inpatient basis. Health disparity factors analyzed included age, gender, insurance type, race, language, and SES using census tracts. Logistic regression analyses and paired t-tests were utilized. Results: Two hundred eighty-six (11.2%) patients had emergent GI procedures performed. Logistic regression (odds ratio [OR], confidence interval (95% CI)] showed patients from 6-11 to 12-17 years of age were less likely to seek emergent care than the youngest group [0.47, 0.33-0.66 and 0.61, 0.45-0.84]. Patients with Medicaid insurance [1.68, 1.27-2.26], African American or "other" race [2.07, 1.48-2.90 and 2.43, 1.77-3.36, respectively], as well as "other" language [2.1, 1.14-3.99] more often sought emergent care. Using geocoded data, we found that as SES increases by 1, emergent risk for procedures decreased by 2.9% (OR 0.97, p=0.045). Conclusions: Children with lower SES, at extremes of age (<5, >18 years), non-English or Spanish speaking and with Medicaid insurance are at higher risk of undergoing emergent GI procedures. This study gives us an opportunity to plan targeted interventions to improve access and quality of care.