Claims

Psycho Analyst, a GPT-4-based model enhanced with DSM-5 and PHQ-8 guidelines, achieved F1 and Macro-F1 scores of 0.929 and 0.949 on the DAIC-WOZ dataset

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q2 i? Psycho Analyst demonstrates high accuracy in detecting mental disorders, evidenced by F1 and Macro-F1 scores of 0.929 and 0.949, validated on the DAIC-WOZ dataset. → Jinwen Tang 2026

Evidence

Jinwen Tang 2026

Jinwen Tang. (2026). NEW AI-DRIVEN TOOLS FOR ENHANCING CAMPUS WELL-BEING: A PREVENTION AND INTERVENTION APPROACH. Doctoral dissertation, University of Missouri-Columbia. https://arxiv.org/abs/2605.10804 doi:10.48550/arxiv.2605.10804

q2 · i? · design · r2

Evaluation of the Psycho Analyst custom GPT model on the DAIC-WOZ dataset, as summarized in the dissertation's contributions chapter. The model achieved "F1 and Macro-F1 scores of 0.929 and 0.949"; these are accuracy metrics, not standardized effect sizes.

"Enhanced with DSM-5 and PHQ-8, it demonstrates high accuracy in detecting mental disorders, evidenced by F1 and Macro-F1 scores of 0.929 and 0.949. Validated with the DAIC-WOZ dataset, it shows potential for improving mental health diagnostics"

Discussion

Page metadata
Field Value
type claim
id psycho-analyst-f1-daic-woz
title Psycho Analyst, a GPT-4-based model enhanced with DSM-5 and PHQ-8 guidelines, achieved F1 and Macro-F1 scores of 0.929 and 0.949 on the DAIC-WOZ dataset
description Psycho Analyst, a GPT-4-based model enhanced with DSM-5 and PHQ-8 guidelines, achieved F1 and Macro-F1 scores of 0.929 and 0.949 on the DAIC-WOZ dataset
status review
evidence_strength moderate
newest_evidence 2026
recheck_by 2029
generated by process:wiki-ingest on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — jinwen-tang-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.