{"id":"W7117534985","doi":"10.1016/j.jad.2025.121095","title":"Doctors can agree: Enhancing interrater reliability of mental health diagnosis among junior psychiatrists using electronic clinician assisting technology","year":2025,"lang":"en","type":"article","venue":"Journal of Affective Disorders","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Science and Technology Department of Zhejiang Province; Wenzhou Municipal Science and Technology Bureau","keywords":"Inter-rater reliability; Concordance; Medical diagnosis; Mental health; Mood; Seniority; Bipolar disorder; Reliability (semiconductor); Medical record","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07140636,0.0004570714,0.0005926383,0.002094672,0.001654965,0.002251215,0.001126635,0.001309909,0.002052216],"category_scores_gemma":[0.2792228,0.0009417645,0.0008304822,0.001006178,0.0009296634,0.002485129,0.005171069,0.001304359,0.00117919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009231885,"about_ca_system_score_gemma":0.002547511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003491637,"about_ca_topic_score_gemma":0.01198682,"domain_scores_codex":[0.9403039,0.04398392,0.005848269,0.002784426,0.006018884,0.001060672],"domain_scores_gemma":[0.6304093,0.2658019,0.02113456,0.01751781,0.06215368,0.002982704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.003601446,0.001206912,0.6478748,0.001594964,0.0007369577,0.0005330031,0.04391815,0.001454813,0.009744546,0.001782476,0.01681669,0.2707353],"study_design_scores_gemma":[0.001443853,0.002416445,0.8680403,0.001610888,0.0009627021,0.001349549,0.04106699,0.03432939,0.01751441,0.007791755,0.02292854,0.0005451515],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9473677,0.0004972531,0.03512081,0.002207561,0.000681254,0.002849333,0.001096141,0.0004829862,0.00969696],"genre_scores_gemma":[0.9118627,0.0003422534,0.08161439,0.00120867,0.0003194746,0.002599398,0.0005474192,0.0001169053,0.001388804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07140636,"threshold_uncertainty_score":0.3776374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01129726547208896,"score_gpt":0.3887869599951206,"score_spread":0.3774896945230316,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}