SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment

2026-05-05

AI Summary

This study addresses the unclear effectiveness of large language models (LLMs) in everyday symptom assessment, noting that most prior research focuses on complex cases that poorly reflect real-world usage. To bridge this gap, the authors propose SymptomAI—a multi-agent LLM-based conversational system deployed via a Fitbit application to conduct end-to-end consultations with 13,917 general users. Using a tailored symptom interview protocol, SymptomAI collects clinical information and performs differential diagnosis. The study demonstrates, for the first time in a large-scale real-world population, that this structured approach significantly outperforms user-guided dialogue and achieves diagnostic accuracy substantially higher than that of individual clinicians (OR = 2.47, p < 0.001). Additionally, it reveals strong associations between acute infections such as influenza and physiological signals from wearable devices (OR > 7), providing empirical support for AI-driven routine health assessment.

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.

Problem

• conversational AI
• symptom assessment
• differential diagnosis
• real-world symptom reporting
• everyday health

Innovation

• Conversational AI
• Differential Diagnosis
• Symptom Interview
• Wearable Data Integration
• Randomized Clinical Evaluation