{"id":"W2982702361","doi":"10.2196/13863","title":"Accuracy of a Chatbot (Ada) in the Diagnosis of Mental Disorders: Comparative Case Study With Lay and Expert Users","year":2019,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Kappa; Mental health; Medical diagnosis; Inter-rater reliability; Diagnostic Classification of Mental Health and Developmental Disorders of Infancy and Early Childhood; Psychology; Psychiatry; Medicine; Clinical psychology; Prevalence of mental disorders; Developmental psychology; Rating scale; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.0008577944,0.0001040207,0.0002399979,0.0002499697,0.00008118477,0.00002410351,0.0002200771,0.00003115595,0.0001654294],"category_scores_gemma":[0.00001467442,0.00006566235,0.00003724335,0.0005039982,0.000324042,0.0004312039,0.0001324343,0.0002777662,0.000036127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005902307,"about_ca_system_score_gemma":0.00002709991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002441964,"about_ca_topic_score_gemma":0.002179334,"domain_scores_codex":[0.997946,0.0007301955,0.0003644212,0.0001761782,0.0004875617,0.0002955965],"domain_scores_gemma":[0.9983457,0.001088498,0.0001400485,0.0002827892,0.0000909736,0.00005200551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0009175863,0.008960444,0.2145977,0.0001874165,0.0001442366,0.00005593929,0.7602612,8.505642e-7,0.00001011888,0.001679147,0.00167969,0.01150565],"study_design_scores_gemma":[0.002633907,0.01355504,0.1370648,0.0002540897,0.000002856755,0.00007735855,0.8455676,0.00003017708,0.0002492839,0.00011604,0.0003597136,0.00008908752],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894446,0.0001797011,0.000001657476,0.0003721082,0.00005604641,0.003120865,0.00006352467,0.000004625537,0.006756846],"genre_scores_gemma":[0.9983702,0.00001191126,0.000009589522,0.00001989461,0.000004266135,0.001492186,0.000005217109,0.000007985651,0.00007877855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0853064,"threshold_uncertainty_score":0.3691535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1705206091532488,"score_gpt":0.5455406751274376,"score_spread":0.3750200659741889,"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."}}