Abstract
Stepped-care obesity treatments aim to improve efficiency by early identification of non-responders and adjusting interventions but lack validated models. We trained a random forest classifier to improve the predictive utility of a clinical decision rule (>0.5 lb weight loss/week) that identifies non-responders in the first 2 weeks of a stepped-care weight loss trial (SMART). From 2009 to 2021, 1058 individuals with obesity participated in three studies: SMART, Opt-IN, and ENGAGED. The model was trained on 80% of the SMART data (224 participants), and its in-distribution generalizability was tested on the remaining 20% (remaining 57 participants). The out-of-distribution generalizability was tested on the ENGAGED and Opt-IN studies (472 participants). The model predicted weight loss at month 6 with an 84.5% AUROC and an 86.3% AUPRC. SHAP identified predictive features: weight loss at week 2, ranges/means and ranges of weight loss, slope, and age. The SMART-trained model showed generalizable performance with no substantial difference across studies.
| Original language | English (US) |
|---|---|
| Article number | 344 |
| Journal | npj Digital Medicine |
| Volume | 7 |
| Issue number | 1 |
| DOIs | |
| State | Published - Dec 2024 |
Funding
This work has been funded by the US National Institute of Diabetes and Digestive and Kidney Diseases R01DK125414 and NIH - National Heart, Lung, and Blood Institute F31HL162555. The funders had no role in the analysis, interpretation of data, or preparation of the manuscript. The authors would like to thank Dr. Juned Siddique, Elyse Daly, Harvey Gene McFadden, Charles Olvera, Chris Romano, Rowan McCloskey, and Boyang Wei for their support during this project.
ASJC Scopus subject areas
- Medicine (miscellaneous)
- Health Informatics
- Computer Science Applications
- Health Information Management
