Skip to main content

Table 1 Comparison of model accuracy

From: Integrative diagnosis of psychiatric conditions using ChatGPT and fMRI data

Model

Accuracy

Clinician Diagnosis

53.8% - 85.7%

Proposed Model (Training)

88.3%

Proposed Model (Validation)

85.2%

Proposed Model (Test)

85.7%

  1. We compared the accuracy of clinician diagnosis with the proposed model across different stages: training, validation, and testing. The proposed model shows higher and more consistent accuracy, highlighting its effectiveness over traditional diagnostic methods
Back to article page

BMC Psychiatry

ISSN: 1471-244X

Contact us