{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0296044,0.000988111,0.0009654362,0.000824558,0.001707472,0.001631157,0.001125019,0.001191411,0.005640143],"category_scores_gemma":[0.08248364,0.001110355,0.001312434,0.0004319709,0.002422923,0.001565283,0.002255638,0.001705194,0.001270253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205896,"about_ca_system_score_gemma":0.00161508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001209635,"about_ca_topic_score_gemma":0.001356113,"domain_scores_codex":[0.9742849,0.01530476,0.001930856,0.003393474,0.004230328,0.0008556565],"domain_scores_gemma":[0.8563238,0.1023997,0.01328641,0.01532778,0.009214872,0.003447264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.09649483,0.4284329,0.2871805,0.00147618,0.00102006,0.0003376758,0.02567371,0.002503974,0.02616324,0.002048543,0.001474808,0.1271937],"study_design_scores_gemma":[0.01524092,0.4568655,0.4867155,0.0003464512,0.001092777,0.0003091039,0.003916896,0.01428156,0.01381029,0.00190193,0.005253316,0.0002657106],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993666,0.00004127948,0.001403607,0.00004253941,0.0000528443,0.003056909,0.00009221581,0.00001825075,0.001626376],"genre_scores_gemma":[0.9772542,0.00009644547,0.007175345,0.0002136562,0.0001426356,0.01258262,0.0002567524,0.00002962981,0.002248782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0296044,"threshold_uncertainty_score":0.1565648,"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."}}