Machine learning using longitudinal prescription and medical claims for the detection of non-alcoholic steatohepatitis (NASH).

OBJECTIVES: To develop and evaluate machine learning models to detect patients with suspected undiagnosed non-alcoholic steatohepatitis (NASH) for diagnostic screening and clinical management. METHODS: In this retrospective observational non-interventional study using administrative medical claims data from 1 463 089 patients, gradient-boosted decision trees were trained to detect patients with likely NASH from an at-risk patient population with a history of obesity, type 2 diabetes mellitus, metabolic disorder or non-alcoholic fatty liver (NAFL). Models were trained to detect likely NASH in all at-risk patients or in the subset without a prior NAFL diagnosis (at-risk non-NAFL patients). Models were trained and validated using retrospective medical claims data and assessed using area under precision recall curves and receiver operating characteristic curves (AUPRCs and AUROCs). RESULTS: The 6-month incidences of NASH in claims data were 1 per 1437 at-risk patients and 1 per 2127 at-risk non-NAFL patients . The model trained to detect NASH in all at-risk patients had an AUPRC of 0.0107 (95% CI 0.0104 to 0.0110) and an AUROC of 0.84. At 10% recall, model precision was 4.3%, which is 60× above NASH incidence. The model trained to detect NASH in the non-NAFL cohort had an AUPRC of 0.0030 (95% CI 0.0029 to 0.0031) and an AUROC of 0.78. At 10% recall, model precision was 1%, which is 20× above NASH incidence. CONCLUSION: The low incidence of NASH in medical claims data corroborates the pattern of NASH underdiagnosis in clinical practice. Claims-based machine learning could facilitate the detection of patients with probable NASH for diagnostic testing and disease management.

An epidemiological study of major surgical procedures in an urban population of East delhi.

Surgery has become an integral part of global health care, with an estimated 234 million operations performed yearly. The World Bank in 2002 reported that an estimated 164 million disability-adjusted life years, representing 11% of the entire disease burden, were attributable to surgically treatable conditions. To study the prevalence of various surgical operations undergone by individuals in their life time, in an urbanized community of Delhi. Cross-sectional study, conducted from October 2008 to April 2009 in Vivek Vihar-an urban affluent colony in Delhi. A total of 3,043 individuals residing in 622 households were interviewed as part of the study. Total number of households with some member having ever undergone surgery was 306 (49.2%). 12.3% of our study population (375 out of 3,043) had undergone one or the other form of major surgical operation in their life time. Caesarean section was found to be the most common surgical procedure performed. 61.7% surgeries were elective in nature and 81.9% were performed in a private hospital. The lifetime prevalence of surgical procedures was 1.77% among children, 12.6% among adult males and 15.8% among adult females (p < 0.001). It was observed that the expense of surgeries conducted in private hospitals was more compared to government. Our findings suggest that surgery occurs at a substantial rate, at least among the urban affluent, with most of the patients choosing to refer to a private hospital for their surgery.