{"id":"W4410883894","doi":"10.2196/56057","title":"Comparative Efficacy of MultiModal AI Methods in Screening for Major Depressive Disorder: Machine Learning Model Development Predictive Pilot Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Major depressive disorder; Artificial intelligence; Psychology; Correlation; Machine learning; Computer science; Clinical psychology; Mathematics; Mood","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002550331,0.0002028572,0.0004677063,0.0009774906,0.0004137667,0.00002915897,0.0002670877,0.00008540259,0.00007657512],"category_scores_gemma":[0.000254999,0.0001812363,0.00006524112,0.0007617262,0.0001700264,0.0002299076,0.0002427442,0.0009933716,0.00001474156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001362978,"about_ca_system_score_gemma":0.0001570436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002257797,"about_ca_topic_score_gemma":0.0002606787,"domain_scores_codex":[0.9959681,0.002084939,0.0006380389,0.000406749,0.0003849873,0.0005171951],"domain_scores_gemma":[0.997151,0.001734824,0.0001717898,0.0001919259,0.0006728636,0.00007758374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01911115,0.02420661,0.04159414,0.0004363189,0.001999489,0.00000721361,0.5266303,0.02148745,0.002221434,0.003287455,0.001531655,0.3574868],"study_design_scores_gemma":[0.02462814,0.006587302,0.4078785,0.0004476726,0.00003521794,0.000001456802,0.04880646,0.504081,0.005262894,0.001361557,0.0005323477,0.000377375],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3788595,0.000192655,0.6114548,0.0001211217,0.00008842061,0.003675479,0.00004173256,0.0000435834,0.005522627],"genre_scores_gemma":[0.9754815,0.000005813115,0.0210027,0.00002859854,0.00001415588,0.002449767,0.00009685593,0.00001787207,0.0009026972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.596622,"threshold_uncertainty_score":0.7390603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1794782452701404,"score_gpt":0.5375731965893382,"score_spread":0.3580949513191979,"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."}}