_version_ 1866911669199831040
author Breda, Joseph
Yousif, Fadi
Hawkins, Beszel
Cotoi, Marinela
Liu, Miao
Luo, Ray
Chen, Po-Hsuan Cameron
Schaekermann, Mike
Schmidgall, Samuel
Liu, Xin
Narayanswamy, Girish
Solomon, Samuel
Xu, Maxwell A.
Fan, Xiaoran
Shangguan, Longfei
Wang, Anran
Daryani, Bhavna
Herkenham, Buddy
Tan, Cara
Malhotra, Mark
Patel, Shwetak
Hernandez, John B.
Duong, Quang
Liu, Yun
Wasson, Zach
Antos, Dimitrios
Lou, Bob
Thompson, Matthew
Richina, Jonathan
Pathak, Anupam
Young-Lin, Nichole
Sunshine, Jake
McDuff, Daniel
author_facet Breda, Joseph
Yousif, Fadi
Hawkins, Beszel
Cotoi, Marinela
Liu, Miao
Luo, Ray
Chen, Po-Hsuan Cameron
Schaekermann, Mike
Schmidgall, Samuel
Liu, Xin
Narayanswamy, Girish
Solomon, Samuel
Xu, Maxwell A.
Fan, Xiaoran
Shangguan, Longfei
Wang, Anran
Daryani, Bhavna
Herkenham, Buddy
Tan, Cara
Malhotra, Mark
Patel, Shwetak
Hernandez, John B.
Duong, Quang
Liu, Yun
Wasson, Zach
Antos, Dimitrios
Lou, Bob
Thompson, Matthew
Richina, Jonathan
Pathak, Anupam
Young-Lin, Nichole
Sunshine, Jake
McDuff, Daniel
contents Language models excel at diagnostic assessments on curated 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 = 2.56, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04012
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SymptomAI: Toward a Conversational AI Agent for Everyday Symptom Assessment
Breda, Joseph
Yousif, Fadi
Hawkins, Beszel
Cotoi, Marinela
Liu, Miao
Luo, Ray
Chen, Po-Hsuan Cameron
Schaekermann, Mike
Schmidgall, Samuel
Liu, Xin
Narayanswamy, Girish
Solomon, Samuel
Xu, Maxwell A.
Fan, Xiaoran
Shangguan, Longfei
Wang, Anran
Daryani, Bhavna
Herkenham, Buddy
Tan, Cara
Malhotra, Mark
Patel, Shwetak
Hernandez, John B.
Duong, Quang
Liu, Yun
Wasson, Zach
Antos, Dimitrios
Lou, Bob
Thompson, Matthew
Richina, Jonathan
Pathak, Anupam
Young-Lin, Nichole
Sunshine, Jake
McDuff, Daniel
Artificial Intelligence
Language models excel at diagnostic assessments on curated 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 = 2.56, 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.
title SymptomAI: Toward a Conversational AI Agent for Everyday Symptom Assessment
topic Artificial Intelligence
url https://arxiv.org/abs/2605.04012