MétaCan
Menu
Back to cohort
Record W7117534985 · doi:10.1016/j.jad.2025.121095

Doctors can agree: Enhancing interrater reliability of mental health diagnosis among junior psychiatrists using electronic clinician assisting technology

2025· article· en· W7117534985 on OpenAlexaff
Yang S. Liu, Lei Qian, Jian Xiang, Deborah Baofeng Wang, Jing Jiang, Ruijin Ni, Haibo Mao, Chongyu Cheng, Jianfeng Hong, Qinying Jiang, Hongshen Yang, Haiyun Xu, Jiahong Liu, Xugong Cai, Xin-min Li, Bo Cao, Andrew J. Greenshaw, Yi Xu

Bibliographic record

VenueJournal of Affective Disorders · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsUniversity of Alberta
FundersScience and Technology Department of Zhejiang ProvinceWenzhou Municipal Science and Technology Bureau
KeywordsInter-rater reliabilityConcordanceMedical diagnosisMental healthMoodSeniorityBipolar disorderReliability (semiconductor)Medical record

Abstract

fetched live from OpenAlex

Interrater reliability in mental health diagnoses presents significant challenges, hindering consistent patient care. This study investigated the dual impact of clinicians' seniority and the use of an Electronic Medical Records (EMR) integrated Clinical Decision Support System (CDSS) on the diagnostic concordance of Major Depressive Disorder (MDD), Bipolar Disorder (BD), and Schizophrenia (SCZ). Seventy-two psychiatrists were randomly assigned to an EMR-assisted or a non-assisted control group, stratified by seniority. Participants diagnosed three cases based on video-recorded structured clinical interviews, and interrater reliability was assessed using Gwet's AC1. Results showed that seniority was a critical factor, with mid-level psychiatrists demonstrating higher reliability than their low-seniority counterparts. The CDSS intervention also significantly improved concordance. This effect was driven by dramatic improvements for mood disorders. The system's impact was negligible for SCZ, which showed high baseline agreement, and among high-seniority psychiatrists, who achieved perfect concordance regardless of CDSS use. This study underscores the potential of EMR-integrated CDSS to enhance psychiatric diagnostic consistency, likely by standardizing the evaluation process for less-experienced clinicians facing complex differential diagnosis of mood disorders. These findings highlight the need to evaluate such systems in diverse clinical settings and across a broader spectrum of psychiatric conditions. • Study seniority & EMR tools' impact on MDD, BD, SCZ interrater reliability. • 72 psychiatrists assessed video interviews, split into EMR/non-EMR groups. • Mid seniority group had better diagnostic concordance than Low seniority group. • The EMR-assisted group had better diagnostic concordance for mood disorders. • EMR assistance is less helpful for SCZ diagnoses & experienced clinicians.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.071
metaresearch head score (Gemma)0.279
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Non-randomized trial · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.071
Threshold uncertainty score0.378

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0710.279
Meta-epidemiology (narrow)0.0000.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0020.001
Scholarly communication0.0020.002
Open science0.0010.005
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.011
GPT teacher head0.389
Teacher spread0.377 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNon-randomized trial
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractno

Explore more

Same venueJournal of Affective DisordersSame topicDigital Mental Health InterventionsFrench-language works237,207