Fine-tuning Large Language Models in Behavioral Psychology for Scalable Physical Activity Coaching
Mantena, S. D.; Johnson, A.; Oppezzo, M.; Schuetz, N.; Tolas, A.; Doijad, R.; Mattsson, C. M.; Lawrie, A.; Ramirez-Posada, M.; Linos, E.; King, A. C.; Rodriguez, F.; Kim, D. S.; Ashley, E.
Show abstract
Personalized, smartphone-based coaching improves physical activity but relies on static, human-crafted messages. We introduce My Heart Counts (MHC)-Coach, a large language model fine-tuned on the Transtheoretical Model of Change. MHC-Coach generates messages tailored to an individuals psychology (their "stage of change"), providing personalized support to foster long-term physical activity behavior change. To evaluate MHC-Coachs efficacy, 632 participants compared human-expert and MHC-Coach text-based interventions encouraging physical activity. Among messages matched to an individuals stage of change, 68.0% (N=430) preferred MHC-Coach-generated messages (P < 0.001). Blinded behavioral science experts (N=2) rated MHC-Coach messages higher than human-expert messages for perceived effectiveness (4.4 vs. 2.8) and Transtheoretical Model alignment (4.1 vs. 3.5) on a 5-point Likert scale. This work demonstrates how language models can operationalize behavioral science frameworks for personalized health coaching, promoting long-term physical activity and potentially reducing cardiovascular disease risk at scale.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Can co-designed educational interventions help consumers think critically about asking ChatGPT health questions? Results from a randomised-controlled trial 93%
- Evaluation of two easy-to-implement digital breathing interventions in the context of daily stress levels in a series of N-of-1 trials: results from the Anti-Stress Intervention Among Physicians (ASIP) Study 92%
- Response to Polygenic Risk: Results of the MyGeneRank Mobile Application-Based Coronary Artery Disease Study 91%
Similar papers in this journal
- Conversational, Longitudinal, Ecological Assessment (CLEA): Exploring a new AI-driven method for qualitative data collection in a behavioural health context 93%
- Feasibility and preliminary efficacy of an online mindful walking intervention among COVID-19 long haulers: A mixed method study including daily diary surveys 91%
- Feasibility characteristics of wrist-worn fitness trackers in health status monitoring for post-COVID patients in remote and rural areas 90%
Similar papers in this journal
- Scientific hypothesis generation process in clinical research: a secondary data analytic tool versus experience study protocol 91%
- Wearables and smartphones for modifiable risk factors in metabolic health: a scoping review protocol 89%
- A protocol for a pilot randomized controlled trial of guided self-help Behavioral Activation intervention for geriatric depression 89%
Similar papers in this journal
- A digital self-care intervention for Ugandan patients with heart failure and their clinicians: User-centred design and usability study 91%
- An online mental health informed physical activity intervention for emergency service workers and their families: A stepped-wedge trial 89%
- How suitable are clinical vignettes for the evaluation of symptom checker apps? A test theoretical perspective 89%
Similar papers in this journal
- An mHealth app using machine learning to increase physical activity in diabetes and depression: clinical trial protocol for the DIAMANTE Study 94%
- Telehealth versus Self-Directed Lifestyle Intervention to Promote Healthy Blood Pressure: A Protocol for a Randomized Controlled Trial 92%
- Anatomy of a Failure: Can a Cognitive-Bias Modification Intervention Improve Physical Activity in Patients Following a Cardiac Rehabilitation Programme? 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.