Applying machine learning approaches for predicting obesity risk using US health administrative claims database.

Introduction: Body mass index (BMI) is inadequately recorded in US administrative claims databases. We aimed to validate the sensitivity and positive predictive value (PPV) of BMI-related diagnosis codes using an electronic medical records (EMR) claims-linked database. Additionally, we applied machine learning (ML) to identify features in US claims databases to predict obesity status.

Five-year morbidity and mortality rates in a U.S. population with obesity with and without prediabetes.

Aims: This research examines the prevalence of morbidity and mortality among people with obesity with or without prediabetes.

Methods: This observational study uses Optum® Market Clarity deidentified data from 2007 to 2020. Individuals with obesity without prediabetes (obesity only) were matched 1:1 to adults with prediabetes plus obesity based upon age, sex, race, ethnicity, and region.

The Association Between Obesity and the 5-Year Prevalence of Morbidity and Mortality Among Adults with Type 2 Diabetes.

Introduction: This retrospective claims database study examined the prevalence of mortality and morbidity among adults with type 2 diabetes (T2D) and obesity.

Methods: The study used deidentified data from 2007 to 2021 from the Optum® Market Clarity Dataset. A cohort of adults with T2D and obesity were identified, and age- and sex-adjusted prevalence rates were calculated for mortality, a composite cardiovascular outcome (CCO), a composite microvascular outcome (CMO), and other complications.

Healthcare outcomes for patients with type 2 diabetes with and without comorbid obesity.

Aims: Examine the burden of comorbid obesity associated with type 2 diabetes (T2D).

Methods: The IBM® MarketScan® Explorys Claims Electronic Medical Records Data were used to identify adults with T2D, two recorded body mass index (BMI) values, and continuous insurance coverage from 1 year prior through 1 year post index date. Patients with index BMI ≥18 kg/m and <30 kg/m (normal/overweight) were matched to patients with index BMI ≥ 30 kg/m (obese) using propensity score matching (PSM).