A machine-learned model for predicting weight loss success using weight change features early in treatment

Farzad Shahabi; Samuel L Battalio; Angela Fidler Pfammatter; Donald Hedeker; Bonnie Spring; Nabil Alshurafa

doi:10.1038/s41746-024-01299-y

A machine-learned model for predicting weight loss success using weight change features early in treatment

NPJ Digit Med. 2024 Nov 29;7(1):344. doi: 10.1038/s41746-024-01299-y.

Authors

Farzad Shahabi^{1

2}, Samuel L Battalio³, Angela Fidler Pfammatter⁴, Donald Hedeker⁵, Bonnie Spring³, Nabil Alshurafa^{3

6}

Affiliations

¹ Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA. farzad.shahabi@northwestern.edu.
² Department of Computer Science, McCormick School of Engineering, Northwestern University, Evanston, IL, USA. farzad.shahabi@northwestern.edu.
³ Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.
⁴ College of Education, Health, and Human Sciences, University of Tennessee, Knoxville, TN, USA.
⁵ Department of Public Health Sciences, The University of Chicago, Chicago, IL, USA.
⁶ Department of Computer Science, McCormick School of Engineering, Northwestern University, Evanston, IL, USA.

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.

Abstract

Grants and funding