| title | SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment |
|---|---|
| authors | Joseph Breda, Fadi Yousif, Beszel Hawkins, Marinela Cotoi, Miao Liu, Ray Luo, Po-Hsuan Cameron Chen, Mike Schaekermann, Samuel Schmidgall, Xin Liu, Girish Narayanswamy, Samuel Solomon, Maxwell A. Xu, Xiaoran Fan, Longfei Shangguan, Anran Wang, Bhavna Daryani, Buddy Herkenham, Cara Tan, Mark Malhotra, Shwetak Patel, John B. Hernandez, Quang Duong, Yun Liu, Zach Wasson, Dimitrios Antos, Bob Lou, Matthew Thompson, Jonathan Richina, Anupam Pathak, Nichole Young-Lin, Jake Sunshine, Daniel McDuff |
| date | 2026-05-05 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.04012 |
| upvotes | 9 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Language models excel at diagnostic assessments on currated medical case-studies and vignettes, performing on par with, or better than, clinical professionals. However, existing studies focus on complex scenarios with rich context making it difficult to draw conclusions about how these systems perform for patients reporting symptoms in everyday life. We deployed SymptomAI, a set of conversational AI agents for end-to-end patient interviewing and differential diagnosis (DDx), via the Fitbit app in a study that randomized participants (N=13,917) to interact with five AI agents. This corpus captures diverse communication and a realistic distribution of illnesses from a real world population. A subset of 1,228 participants reported a clinician-provided diagnosis, and 517 of these were further evaluated by a panel of clinicians during over 250 hours of annotation. SymptomAI DDx were significantly more accurate (OR = 2.47, p < 0.001) than those from independent clinicians given the same dialogue in a blinded randomized comparison. Moreover, agentic strategies which conduct a dedicated symptom interview that elicit additional symptom information before providing a diagnosis, perform substantially better than baseline, user-guided conversations (p < 0.001). An auxiliary analysis on 1,509 conversations from a general US population panel validated that these results generalize beyond wearable device users. We used SymptomAI diagnoses as labels for all 13,917 participants to analyze over 500,000 days of wearable metrics across nearly 400 unique conditions. We identified strong associations between acute infections and physiological shifts (e.g., OR > 7 for influenza). While limited by self-reported ground truth, these results demonstrate the benefits of a dedicated and complete symptom interview compared to a user-guided symptom discussion, which is the default of most consumer LLMs. |
cite
@misc{breda2026symptomai,
title={SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment},
author={Joseph Breda and Fadi Yousif and Beszel Hawkins and Marinela Cotoi and Miao Liu and Ray Luo and Po-Hsuan Cameron Chen and Mike Schaekermann and Samuel Schmidgall and Xin Liu and Girish Narayanswamy and Samuel Solomon and Maxwell A. Xu and Xiaoran Fan and Longfei Shangguan and Anran Wang and Bhavna Daryani and Buddy Herkenham and Cara Tan and Mark Malhotra and Shwetak Patel and John B. Hernandez and Quang Duong and Yun Liu and Zach Wasson and Dimitrios Antos and Bob Lou and Matthew Thompson and Jonathan Richina and Anupam Pathak and Nichole Young-Lin and Jake Sunshine and Daniel McDuff},
year={2026},
eprint={2605.04012},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.04012}
}