{"id":"W4307877758","doi":"10.2196/28082","title":"Validity of Chatbot Use for Mental Health Assessment: Experimental Study","year":2022,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Chatbot; Discriminant validity; Psychology; Convergent validity; Mental health; Alcohol Use Disorders Identification Test; Clinical psychology; Distress; Digital health; Developmental psychology; Applied psychology; Psychometrics; Psychiatry; Medicine; Health care; Poison control; Injury prevention; Artificial intelligence; Computer science","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001753425,0.0002591487,0.0005899941,0.0002501759,0.001197106,0.00003486325,0.0002406562,0.00004775165,0.0004431533],"category_scores_gemma":[0.00001121718,0.0002826276,0.0001402379,0.0002899787,0.00009445916,0.0002160489,0.000238555,0.0003573475,0.000007119754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008032189,"about_ca_system_score_gemma":0.0004685728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001364439,"about_ca_topic_score_gemma":0.000107985,"domain_scores_codex":[0.9958908,0.0008553647,0.001210131,0.0006632904,0.0004793488,0.0009010877],"domain_scores_gemma":[0.9979258,0.0002009581,0.0007282233,0.0004573968,0.00004387337,0.0006437741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.008308837,0.1592745,0.2986948,0.007234816,0.0004397907,0.00003438452,0.09483068,0.00001124514,0.00007068841,0.1438733,0.1843057,0.1029212],"study_design_scores_gemma":[0.01701399,0.1128518,0.7259682,0.000128745,0.00007553981,0.0001575471,0.07443056,0.0002192419,0.00005030015,0.001122203,0.0671574,0.0008243784],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848858,0.0008029518,0.00008462039,0.003523155,0.00250562,0.005542984,0.001945217,0.00009255786,0.0006170858],"genre_scores_gemma":[0.9934719,0.00001664517,0.0005292611,0.001905621,0.00009079673,0.00277535,0.0002619765,0.00005274117,0.0008956973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4272735,"threshold_uncertainty_score":0.9999626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2154820388108473,"score_gpt":0.5353842889419838,"score_spread":0.3199022501311365,"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."}}