Transforming Wearable Data into Personal Health Insights using Large Language Model Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912575030034432 |
|---|---|
| author | Merrill, Mike A. Paruchuri, Akshay Rezaei, Naghmeh Kovacs, Geza Perez, Javier Liu, Yun Schenck, Erik Hammerquist, Nova Sunshine, Jake Tailor, Shyam Ayush, Kumar Su, Hao-Wei He, Qian McLean, Cory Y. Malhotra, Mark Patel, Shwetak Zhan, Jiening Althoff, Tim McDuff, Daniel Liu, Xin |
| author_facet | Merrill, Mike A. Paruchuri, Akshay Rezaei, Naghmeh Kovacs, Geza Perez, Javier Liu, Yun Schenck, Erik Hammerquist, Nova Sunshine, Jake Tailor, Shyam Ayush, Kumar Su, Hao-Wei He, Qian McLean, Cory Y. Malhotra, Mark Patel, Shwetak Zhan, Jiening Althoff, Tim McDuff, Daniel Liu, Xin |
| contents | Deriving personalized insights from popular wearable trackers requires complex numerical reasoning that challenges standard LLMs, necessitating tool-based approaches like code generation. Large language model (LLM) agents present a promising yet largely untapped solution for this analysis at scale. We introduce the Personal Health Insights Agent (PHIA), a system leveraging multistep reasoning with code generation and information retrieval to analyze and interpret behavioral health data. To test its capabilities, we create and share two benchmark datasets with over 4000 health insights questions. A 650-hour human expert evaluation shows that PHIA significantly outperforms a strong code generation baseline, achieving 84% accuracy on objective, numerical questions and, for open-ended ones, earning 83% favorable ratings while being twice as likely to achieve the highest quality rating. This work can advance behavioral health by empowering individuals to understand their data, enabling a new era of accessible, personalized, and data-driven wellness for the wider population. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06464 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transforming Wearable Data into Personal Health Insights using Large Language Model Agents Merrill, Mike A. Paruchuri, Akshay Rezaei, Naghmeh Kovacs, Geza Perez, Javier Liu, Yun Schenck, Erik Hammerquist, Nova Sunshine, Jake Tailor, Shyam Ayush, Kumar Su, Hao-Wei He, Qian McLean, Cory Y. Malhotra, Mark Patel, Shwetak Zhan, Jiening Althoff, Tim McDuff, Daniel Liu, Xin Artificial Intelligence Computation and Language Deriving personalized insights from popular wearable trackers requires complex numerical reasoning that challenges standard LLMs, necessitating tool-based approaches like code generation. Large language model (LLM) agents present a promising yet largely untapped solution for this analysis at scale. We introduce the Personal Health Insights Agent (PHIA), a system leveraging multistep reasoning with code generation and information retrieval to analyze and interpret behavioral health data. To test its capabilities, we create and share two benchmark datasets with over 4000 health insights questions. A 650-hour human expert evaluation shows that PHIA significantly outperforms a strong code generation baseline, achieving 84% accuracy on objective, numerical questions and, for open-ended ones, earning 83% favorable ratings while being twice as likely to achieve the highest quality rating. This work can advance behavioral health by empowering individuals to understand their data, enabling a new era of accessible, personalized, and data-driven wellness for the wider population. |
| title | Transforming Wearable Data into Personal Health Insights using Large Language Model Agents |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2406.06464 |