{"id":"W4417313836","doi":"10.2196/78401","title":"Evaluating the Efficacy of AI-Based Interactive Assessments Using Large Language Models for Depression Screening: Development and Usability Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Mental Health via Writing","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Usability; Depression (economics); Technology acceptance model; Language model; Self-efficacy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01730708,0.001234156,0.0008458977,0.001173033,0.0002854826,0.001481528,0.001369084,0.0008848496,0.001374587],"category_scores_gemma":[0.05118516,0.0005332119,0.00117047,0.0004671216,0.0004602234,0.001591247,0.001561364,0.0006247376,0.0005254894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005877701,"about_ca_system_score_gemma":0.0006395177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00119855,"about_ca_topic_score_gemma":0.001545695,"domain_scores_codex":[0.9901733,0.007041795,0.0008709349,0.000927345,0.0007991634,0.000187456],"domain_scores_gemma":[0.9406824,0.05061379,0.001284236,0.002706309,0.004033569,0.0006796418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01756632,0.01773214,0.1391802,0.004964241,0.002114092,0.001412015,0.01883353,0.01741262,0.0671759,0.0008002501,0.006261824,0.7065468],"study_design_scores_gemma":[0.008834031,0.0644238,0.3339718,0.001385709,0.004295445,0.003517093,0.008531361,0.487876,0.06507997,0.002634251,0.0184759,0.0009745754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9741843,0.0002450547,0.02146191,0.00008358656,0.00003269038,0.001572205,0.0002803057,0.001222463,0.0009175943],"genre_scores_gemma":[0.8958972,0.0002911695,0.09883948,0.000148614,0.00003463487,0.002944333,0.0007379572,0.0001931352,0.0009135831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01730708,"threshold_uncertainty_score":0.09152967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3266456512179997,"score_gpt":0.6483594344163229,"score_spread":0.3217137831983232,"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."}}