The Last JITAI? The Unreasonable Effectiveness of Large Language Models in Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Prospective Cardiac Rehabilitation Setting

Guardado en:
Detalles Bibliográficos
Publicado en:arXiv.org (Apr 15, 2024), p. n/a
Autor principal: Haag, David
Otros Autores: Kumar, Devender, Gruber, Sebastian, Sareban, Mahdi, Treff, Gunnar, Niebauer, Josef, Bull, Christopher, Smeddinck, Jan David
Publicado:
Cornell University Library, arXiv.org
Materias:
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 2926343486
003 UK-CbPIL
022 |a 2331-8422 
035 |a 2926343486 
045 0 |b d20240415 
100 1 |a Haag, David 
245 1 |a The Last JITAI? The Unreasonable Effectiveness of Large Language Models in Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Prospective Cardiac Rehabilitation Setting 
260 |b Cornell University Library, arXiv.org  |c Apr 15, 2024 
513 |a Working Paper 
520 3 |a We investigated the viability of using Large Language Models (LLMs) for triggering and personalizing content for Just-in-Time Adaptive Interventions (JITAIs) in digital health. JITAIs are being explored as a key mechanism for sustainable behavior change, adapting interventions to an individual's current context and needs. However, traditional rule-based and machine learning models for JITAI implementation face scalability and flexibility limitations, such as lack of personalization, difficulty in managing multi-parametric systems, and issues with data sparsity. To investigate JITAI implementation via LLMs, we tested the contemporary overall performance-leading model 'GPT-4' with examples grounded in the use case of fostering heart-healthy physical activity in outpatient cardiac rehabilitation. Three personas and five sets of context information per persona were used as a basis of triggering and personalizing JITAIs. Subsequently, we generated a total of 450 proposed JITAI decisions and message content, divided equally into JITAIs generated by 10 iterations with GPT-4, a baseline provided by 10 laypersons (LayPs), and a gold standard set by 10 healthcare professionals (HCPs). Ratings from 27 LayPs and 11 HCPs indicated that JITAIs generated by GPT-4 were superior to those by HCPs and LayPs over all assessed scales: i.e., appropriateness, engagement, effectiveness, and professionality. This study indicates that LLMs have significant potential for implementing JITAIs as a building block of personalized or "precision" health, offering scalability, effective personalization based on opportunistically sampled information, and good acceptability. 
653 |a Exercise 
653 |a Just in time 
653 |a Large language models 
653 |a Machine learning 
653 |a Rehabilitation 
653 |a Context 
653 |a Customization 
653 |a Effectiveness 
700 1 |a Kumar, Devender 
700 1 |a Gruber, Sebastian 
700 1 |a Sareban, Mahdi 
700 1 |a Treff, Gunnar 
700 1 |a Niebauer, Josef 
700 1 |a Bull, Christopher 
700 1 |a Smeddinck, Jan David 
773 0 |t arXiv.org  |g (Apr 15, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/2926343486/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2402.08658