{"id":"W4403540278","doi":"10.2196/62963","title":"Describing the Framework for AI Tool Assessment in Mental Health and Applying It to a Generative AI Obsessive-Compulsive Disorder Platform: Tutorial","year":2024,"lang":"en","type":"review","venue":"JMIR Formative Research","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mental health; Psychological intervention; Transparency (behavior); Credibility; Agency (philosophy); Scrutiny; Accountability; Psychology; Computer science; Psychiatry; Computer security; Sociology; Political 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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002774738,0.0006017837,0.001421186,0.0009335146,0.0009360109,0.000717762,0.0006804367,0.0003699157,0.00009562375],"category_scores_gemma":[0.0002270781,0.0004083742,0.0004415755,0.001432125,0.0002653267,0.0005883354,0.0009276322,0.003558392,0.0003178939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002579738,"about_ca_system_score_gemma":0.001462762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001673715,"about_ca_topic_score_gemma":0.0001805567,"domain_scores_codex":[0.9939446,0.001157413,0.00161552,0.0008846411,0.00089138,0.001506373],"domain_scores_gemma":[0.9967947,0.001659055,0.0003467627,0.0005216648,0.0002244634,0.0004533293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001135848,0.00041898,0.000003648315,0.009007281,0.000272411,0.000008341989,0.02878895,6.159985e-7,2.304097e-8,0.1093713,0.04452431,0.8074906],"study_design_scores_gemma":[0.0007002968,0.00223994,0.000009495237,0.03781321,0.00003614448,0.00003502341,0.01417034,0.0001247429,2.536862e-7,0.01033888,0.934108,0.000423733],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001494312,0.9408415,0.00765617,0.01211024,0.005558716,0.02988335,0.002494453,0.00007626194,0.00122988],"genre_scores_gemma":[0.004796349,0.798281,0.005407066,0.005736031,0.002613354,0.1770097,0.002461126,0.0005474478,0.003147996],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8895836,"threshold_uncertainty_score":0.9998368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3058027182502824,"score_gpt":0.590659697631615,"score_spread":0.2848569793813325,"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."}}