{"id":"W4413050082","doi":"10.3233/shti251293","title":"Text Analysis for Depression Detection: Mental Health Digital Transformation","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Mental Health via Writing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Leverage (statistics); Computer science; Convolutional neural network; Social media; Mental health; Architecture; Identification (biology); Depression (economics); Feature extraction; Artificial intelligence; Data science; Footprint; World Wide Web; Machine learning; Psychology; Psychiatry","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":[0.000470106,0.0006680994,0.0003190509,0.002416163,0.0003579178,0.0009262321,0.0004456959,0.0004517027,0.008133225],"category_scores_gemma":[0.003028117,0.0001337084,0.0004384475,0.001546632,0.0001781444,0.001064646,0.0006794585,0.0006089735,0.005327452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004226485,"about_ca_system_score_gemma":0.0004422737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003410869,"about_ca_topic_score_gemma":0.006687864,"domain_scores_codex":[0.9995934,0.00006831811,0.00005272281,0.0001199452,0.0001137989,0.00005179331],"domain_scores_gemma":[0.9990517,0.0003443436,0.0001239226,0.0001350104,0.0002885814,0.00005630308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004151205,0.0002670632,0.02545808,0.0005320284,0.00009619174,0.0003778823,0.0002441847,0.002518088,0.03247411,0.001801824,0.05845886,0.8773566],"study_design_scores_gemma":[0.0001185715,0.0006371852,0.1920732,0.0004767489,0.0002603008,0.001704762,0.001537981,0.4835365,0.1070942,0.01818979,0.1942339,0.0001368838],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4754283,0.00725736,0.3174418,0.009699674,0.002453421,0.002030666,0.1085293,0.02481318,0.05234622],"genre_scores_gemma":[0.7730698,0.002077041,0.1556937,0.001041878,0.001076011,0.0006422664,0.04168193,0.0004324103,0.02428499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008133225,"threshold_uncertainty_score":0.02720839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04265137226424771,"score_gpt":0.4300609848222565,"score_spread":0.3874096125580088,"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."}}