_version_ 1866910205856448512
author Shah, Meet
Gusdorf, Jason
Palepu, Anil
Park, Chunjong
O'Sullivan, Jack W.
Ravi, Vishnu
Strother, Tim
Dubov, Pavel
Rysbek, Aliya
Fukuzawa, Toshiyuki
Lunts, Yana
Freyberg, Jan
Chang, Michael B.
Raghu, Aniruddh
Stutz, David
Berlowitz, Devora
Papa, Eliseo
Cemgil, Taylan
Velasquez, JD
Chen, Jack
Chen, Arthur
Fritz, Doug
Taylor, Charlie
Tregubova, Katya
Lim, Jing Rong
Green, Richard
Mahdavi, Sara
Nagda, Mahvish
Lee, Jihyeon
Schiff, Craig
Panait, Liviu
Singh, Sukhdeep
Liévin, Valentin
Barrett, David G. T.
Gladman, Hannah
Cupani, Anna
Pietra, Francesca
Okereke, Uchechi
Tong, Katherine
Meyer, Clemens
Rolland, Erwan
Sanwalka, Mili
Howell, Michael D.
Gu, Shixiang Shane
Xu, Bibo
Ashley, Euan A.
Eslami, S. M. Ali
Wayne, Gregory
Kohli, Pushmeet
Natarajan, Vivek
Rodman, Adam
Karthikesalingam, Alan
Tanno, Ryutaro
author_facet Shah, Meet
Gusdorf, Jason
Palepu, Anil
Park, Chunjong
O'Sullivan, Jack W.
Ravi, Vishnu
Strother, Tim
Dubov, Pavel
Rysbek, Aliya
Fukuzawa, Toshiyuki
Lunts, Yana
Freyberg, Jan
Chang, Michael B.
Raghu, Aniruddh
Stutz, David
Berlowitz, Devora
Papa, Eliseo
Cemgil, Taylan
Velasquez, JD
Chen, Jack
Chen, Arthur
Fritz, Doug
Taylor, Charlie
Tregubova, Katya
Lim, Jing Rong
Green, Richard
Mahdavi, Sara
Nagda, Mahvish
Lee, Jihyeon
Schiff, Craig
Panait, Liviu
Singh, Sukhdeep
Liévin, Valentin
Barrett, David G. T.
Gladman, Hannah
Cupani, Anna
Pietra, Francesca
Okereke, Uchechi
Tong, Katherine
Meyer, Clemens
Rolland, Erwan
Sanwalka, Mili
Howell, Michael D.
Gu, Shixiang Shane
Xu, Bibo
Ashley, Euan A.
Eslami, S. M. Ali
Wayne, Gregory
Kohli, Pushmeet
Natarajan, Vivek
Rodman, Adam
Karthikesalingam, Alan
Tanno, Ryutaro
contents The practice of medicine relies not only upon skillful dialogue but also on the nuanced exchange and interpretation of rich auditory and visual cues between doctors and patients. Building on the low-latency voice and video processing capabilities of Gemini, we introduce AI co-clinician, a first-of-its-kind conversational AI system utilizing continuous streams of audio-visual data from live patient conversations to inform real-time clinical decisions. Its dual-agent architecture balances deep clinical reasoning with the low latency required for natural dialogue. To assess this system, we implemented a video-based interface emulating telemedicine consultations. We crafted 20 standardized outpatient scenarios requiring proactive real-time auditory and visual reasoning and designed "TelePACES" evaluation criteria alongside case-specific rubrics. In a randomized, interface-blinded, crossover simulation study (n = 120 encounters) with 10 internal medicine residents as patient actors, we compared AI co-clinician with primary care physicians (PCPs), GPT-Realtime, and a baseline agent. AI co-clinician approached PCPs in key TelePACES dimensions, including management plans and differential diagnosis, while significantly outperforming GPT-Realtime across all general criteria. While our agent demonstrated parity with PCPs in case-specific triage measures, physicians maintained superior overall performance in case-specific assessments. Although AI co-clinician marks a significant advance in real-time telemedical AI, gaps remain in physical examination and disease-specific reasoning. Our work shows that text-only approaches fail to capture the true challenges of medical consultation and suggests that high-stakes real-time diagnostic AI is most safely advanced in collaborative, triadic models where AI can be a supportive co-clinician for doctors and patients.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09272
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Conversational Medical AI with Eyes, Ears and a Voice
Shah, Meet
Gusdorf, Jason
Palepu, Anil
Park, Chunjong
O'Sullivan, Jack W.
Ravi, Vishnu
Strother, Tim
Dubov, Pavel
Rysbek, Aliya
Fukuzawa, Toshiyuki
Lunts, Yana
Freyberg, Jan
Chang, Michael B.
Raghu, Aniruddh
Stutz, David
Berlowitz, Devora
Papa, Eliseo
Cemgil, Taylan
Velasquez, JD
Chen, Jack
Chen, Arthur
Fritz, Doug
Taylor, Charlie
Tregubova, Katya
Lim, Jing Rong
Green, Richard
Mahdavi, Sara
Nagda, Mahvish
Lee, Jihyeon
Schiff, Craig
Panait, Liviu
Singh, Sukhdeep
Liévin, Valentin
Barrett, David G. T.
Gladman, Hannah
Cupani, Anna
Pietra, Francesca
Okereke, Uchechi
Tong, Katherine
Meyer, Clemens
Rolland, Erwan
Sanwalka, Mili
Howell, Michael D.
Gu, Shixiang Shane
Xu, Bibo
Ashley, Euan A.
Eslami, S. M. Ali
Wayne, Gregory
Kohli, Pushmeet
Natarajan, Vivek
Rodman, Adam
Karthikesalingam, Alan
Tanno, Ryutaro
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
The practice of medicine relies not only upon skillful dialogue but also on the nuanced exchange and interpretation of rich auditory and visual cues between doctors and patients. Building on the low-latency voice and video processing capabilities of Gemini, we introduce AI co-clinician, a first-of-its-kind conversational AI system utilizing continuous streams of audio-visual data from live patient conversations to inform real-time clinical decisions. Its dual-agent architecture balances deep clinical reasoning with the low latency required for natural dialogue. To assess this system, we implemented a video-based interface emulating telemedicine consultations. We crafted 20 standardized outpatient scenarios requiring proactive real-time auditory and visual reasoning and designed "TelePACES" evaluation criteria alongside case-specific rubrics. In a randomized, interface-blinded, crossover simulation study (n = 120 encounters) with 10 internal medicine residents as patient actors, we compared AI co-clinician with primary care physicians (PCPs), GPT-Realtime, and a baseline agent. AI co-clinician approached PCPs in key TelePACES dimensions, including management plans and differential diagnosis, while significantly outperforming GPT-Realtime across all general criteria. While our agent demonstrated parity with PCPs in case-specific triage measures, physicians maintained superior overall performance in case-specific assessments. Although AI co-clinician marks a significant advance in real-time telemedical AI, gaps remain in physical examination and disease-specific reasoning. Our work shows that text-only approaches fail to capture the true challenges of medical consultation and suggests that high-stakes real-time diagnostic AI is most safely advanced in collaborative, triadic models where AI can be a supportive co-clinician for doctors and patients.
title Towards Conversational Medical AI with Eyes, Ears and a Voice
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.09272