Towards Democratization of Subspeciality Medical Expertise

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: O'Sullivan, Jack W., Palepu, Anil, Saab, Khaled, Weng, Wei-Hung, Cheng, Yong, Chu, Emily, Desai, Yaanik, Elezaby, Aly, Kim, Daniel Seung, Lan, Roy, Tang, Wilson, Tapaskar, Natalie, Parikh, Victoria, Jain, Sneha S., Kulkarni, Kavita, Mansfield, Philip, Webster, Dale, Gottweis, Juraj, Barral, Joelle, Schaekermann, Mike, Tanno, Ryutaro, Mahdavi, S. Sara, Natarajan, Vivek, Karthikesalingam, Alan, Ashley, Euan, Tu, Tao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912060008300544
author O'Sullivan, Jack W.
Palepu, Anil
Saab, Khaled
Weng, Wei-Hung
Cheng, Yong
Chu, Emily
Desai, Yaanik
Elezaby, Aly
Kim, Daniel Seung
Lan, Roy
Tang, Wilson
Tapaskar, Natalie
Parikh, Victoria
Jain, Sneha S.
Kulkarni, Kavita
Mansfield, Philip
Webster, Dale
Gottweis, Juraj
Barral, Joelle
Schaekermann, Mike
Tanno, Ryutaro
Mahdavi, S. Sara
Natarajan, Vivek
Karthikesalingam, Alan
Ashley, Euan
Tu, Tao
author_facet O'Sullivan, Jack W.
Palepu, Anil
Saab, Khaled
Weng, Wei-Hung
Cheng, Yong
Chu, Emily
Desai, Yaanik
Elezaby, Aly
Kim, Daniel Seung
Lan, Roy
Tang, Wilson
Tapaskar, Natalie
Parikh, Victoria
Jain, Sneha S.
Kulkarni, Kavita
Mansfield, Philip
Webster, Dale
Gottweis, Juraj
Barral, Joelle
Schaekermann, Mike
Tanno, Ryutaro
Mahdavi, S. Sara
Natarajan, Vivek
Karthikesalingam, Alan
Ashley, Euan
Tu, Tao
contents The scarcity of subspecialist medical expertise, particularly in rare, complex and life-threatening diseases, poses a significant challenge for healthcare delivery. This issue is particularly acute in cardiology where timely, accurate management determines outcomes. We explored the potential of AMIE (Articulate Medical Intelligence Explorer), a large language model (LLM)-based experimental AI system optimized for diagnostic dialogue, to potentially augment and support clinical decision-making in this challenging context. We curated a real-world dataset of 204 complex cases from a subspecialist cardiology practice, including results for electrocardiograms, echocardiograms, cardiac MRI, genetic tests, and cardiopulmonary stress tests. We developed a ten-domain evaluation rubric used by subspecialists to evaluate the quality of diagnosis and clinical management plans produced by general cardiologists or AMIE, the latter enhanced with web-search and self-critique capabilities. AMIE was rated superior to general cardiologists for 5 of the 10 domains (with preference ranging from 9% to 20%), and equivalent for the rest. Access to AMIE's response improved cardiologists' overall response quality in 63.7% of cases while lowering quality in just 3.4%. Cardiologists' responses with access to AMIE were superior to cardiologist responses without access to AMIE for all 10 domains. Qualitative examinations suggest AMIE and general cardiologist could complement each other, with AMIE thorough and sensitive, while general cardiologist concise and specific. Overall, our results suggest that specialized medical LLMs have the potential to augment general cardiologists' capabilities by bridging gaps in subspecialty expertise, though further research and validation are essential for wide clinical utility.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03741
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Democratization of Subspeciality Medical Expertise
O'Sullivan, Jack W.
Palepu, Anil
Saab, Khaled
Weng, Wei-Hung
Cheng, Yong
Chu, Emily
Desai, Yaanik
Elezaby, Aly
Kim, Daniel Seung
Lan, Roy
Tang, Wilson
Tapaskar, Natalie
Parikh, Victoria
Jain, Sneha S.
Kulkarni, Kavita
Mansfield, Philip
Webster, Dale
Gottweis, Juraj
Barral, Joelle
Schaekermann, Mike
Tanno, Ryutaro
Mahdavi, S. Sara
Natarajan, Vivek
Karthikesalingam, Alan
Ashley, Euan
Tu, Tao
Human-Computer Interaction
Artificial Intelligence
The scarcity of subspecialist medical expertise, particularly in rare, complex and life-threatening diseases, poses a significant challenge for healthcare delivery. This issue is particularly acute in cardiology where timely, accurate management determines outcomes. We explored the potential of AMIE (Articulate Medical Intelligence Explorer), a large language model (LLM)-based experimental AI system optimized for diagnostic dialogue, to potentially augment and support clinical decision-making in this challenging context. We curated a real-world dataset of 204 complex cases from a subspecialist cardiology practice, including results for electrocardiograms, echocardiograms, cardiac MRI, genetic tests, and cardiopulmonary stress tests. We developed a ten-domain evaluation rubric used by subspecialists to evaluate the quality of diagnosis and clinical management plans produced by general cardiologists or AMIE, the latter enhanced with web-search and self-critique capabilities. AMIE was rated superior to general cardiologists for 5 of the 10 domains (with preference ranging from 9% to 20%), and equivalent for the rest. Access to AMIE's response improved cardiologists' overall response quality in 63.7% of cases while lowering quality in just 3.4%. Cardiologists' responses with access to AMIE were superior to cardiologist responses without access to AMIE for all 10 domains. Qualitative examinations suggest AMIE and general cardiologist could complement each other, with AMIE thorough and sensitive, while general cardiologist concise and specific. Overall, our results suggest that specialized medical LLMs have the potential to augment general cardiologists' capabilities by bridging gaps in subspecialty expertise, though further research and validation are essential for wide clinical utility.
title Towards Democratization of Subspeciality Medical Expertise
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2410.03741