{"id":"W4412871963","doi":"10.1101/2025.07.17.25331744","title":"Scalable depression monitoring with smartphone speech: a multimodal benchmark and topic analysis","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Mental Health via Writing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotel Dieu Hospital","funders":"Deutsche Forschungsgemeinschaft","keywords":"Benchmark (surveying); Scalability; Depression (economics); Computer science; Speech recognition; Data science; Geography; Cartography; Operating system; Economics","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":[0.001256555,0.0009526986,0.0004711605,0.0009223875,0.0002542422,0.0008544042,0.0004066523,0.0007572326,0.001186358],"category_scores_gemma":[0.005125042,0.0001464578,0.0006201125,0.00057259,0.0002827163,0.0006399424,0.001092503,0.0005509673,0.00108146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002846452,"about_ca_system_score_gemma":0.0002933619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002427816,"about_ca_topic_score_gemma":0.002231128,"domain_scores_codex":[0.9991378,0.0003911957,0.00006586951,0.0002376939,0.00009849691,0.00006893461],"domain_scores_gemma":[0.9981218,0.001189321,0.0001075565,0.000278109,0.0002093173,0.00009384751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004065857,0.001134985,0.1135051,0.001515422,0.0009528481,0.001937154,0.001683317,0.1124437,0.06545405,0.002001546,0.03680509,0.658501],"study_design_scores_gemma":[0.0002288039,0.001149685,0.1052401,0.0001083954,0.0002668544,0.001027649,0.001133283,0.8516275,0.02196665,0.0064785,0.01065265,0.0001199433],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9118595,0.002463179,0.06492314,0.001239586,0.0003811572,0.0001828536,0.01295525,0.003173153,0.002822264],"genre_scores_gemma":[0.9618092,0.0003842887,0.02349938,0.0001098045,0.0002054179,0.0001430328,0.01252175,0.0001116831,0.00121548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002427816,"threshold_uncertainty_score":0.006645381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03055244407890616,"score_gpt":0.3499349617104092,"score_spread":0.319382517631503,"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."}}