Large language models outperform mental and medical health care professionals in identifying obsessive-compulsive disorder

Jiyeong Kim; Kimberly G Leonte; Michael L Chen; John B Torous; Eleni Linos; Anthony Pinto; Carolyn I Rodriguez

doi:10.1038/s41746-024-01181-x

Large language models outperform mental and medical health care professionals in identifying obsessive-compulsive disorder

NPJ Digit Med. 2024 Jul 19;7(1):193. doi: 10.1038/s41746-024-01181-x.

Authors

Jiyeong Kim^#¹, Kimberly G Leonte^#², Michael L Chen³, John B Torous⁴, Eleni Linos³, Anthony Pinto^{5

6}, Carolyn I Rodriguez^{7

8}

Affiliations

¹ Stanford Center for Digital Health, Department of Medicine, Stanford University, Palo Alto, CA, USA. jykim3@stanford.edu.
² Clearview Horizons, North Andover, MA, USA.
³ Stanford Center for Digital Health, Department of Medicine, Stanford University, Palo Alto, CA, USA.
⁴ Division of Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA, USA.
⁵ Department of Psychiatry, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, NY, USA.
⁶ Northwell, New Hyde Park, NY, USA.
⁷ Department of Psychiatry and Behavioral Sciences, School of Medicine, Stanford University, Palo Alto, CA, USA. cr2163@stanford.edu.
⁸ Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, USA. cr2163@stanford.edu.

^# Contributed equally.

Abstract

Despite the promising capacity of large language model (LLM)-powered chatbots to diagnose diseases, they have not been tested for obsessive-compulsive disorder (OCD). We assessed the diagnostic accuracy of LLMs in OCD using vignettes and found that LLMs outperformed medical and mental health professionals. This highlights the potential benefit of LLMs in assisting in the timely and accurate diagnosis of OCD, which usually entails a long delay in diagnosis and treatment.

Abstract

Grants and funding