
Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 17, 2024
Language: Английский
Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 17, 2024
Language: Английский
Obesity Surgery, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 15, 2025
Language: Английский
Citations
0Diabetes Obesity and Metabolism, Journal Year: 2025, Volume and Issue: unknown
Published: March 11, 2025
Abstract Aims Numerous risk factors for the development of obesity have been identified, yet aetiology is not well understood. Traditional statistical methods analysing observational data are limited by volume and characteristics large datasets. Machine learning (ML) can analyse datasets to extract novel insights on obesity. This study predicted adults at a ≥10% increase in index body mass (BMI) within 12 months using ML electronic medical records (EMR) database. Materials Methods algorithms were used with EMR from Optum's de‐identified Market Clarity Data, US Models included extreme gradient boosting (XGBoost), random forest, simple logistic regression (no feature selection procedure) two penalised models (Elastic Net Least Absolute Shrinkage Selection Operator [LASSO]). Performance metrics area under curve (AUC) receiver operating characteristic (used determine best‐performing model), average precision, Brier score, accuracy, recall, positive predictive value, Youden index, F1 negative value specificity. Results The XGBoost model performed best post‐index, an AUC 0.75. Lower baseline BMI, having any emergency room visit during period, no diabetes mellitus, lipid disorders younger age among top predictors BMI. Conclusion current demonstrates approach applied identify those weight gain over months. Providers may use this stratification prioritise prevention strategies or earlier intervention.
Language: Английский
Citations
0Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 17, 2024
Language: Английский
Citations
0