{"id":"W4205455313","doi":"10.2196/23965","title":"Consistency and Sensitivity Evaluation of the Saudi Arabia Mental Health Surveillance System (MHSS): Hypothesis Generation and Testing","year":2022,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Mental Health Treatment and Access","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Mental health; Consistency (knowledge bases); Anxiety; Quality (philosophy); Scale (ratio); Public health; Clinical psychology; Statistics; Applied psychology; Psychiatry; Medicine; Geography; Mathematics","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4580304,0.00143517,0.002066038,0.005309503,0.001920254,0.00372365,0.002917713,0.002494559,0.00246408],"category_scores_gemma":[0.6013914,0.0009157874,0.007969392,0.004468959,0.006587234,0.003740387,0.004382411,0.002080864,0.0003047673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003178947,"about_ca_system_score_gemma":0.004043621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002439744,"about_ca_topic_score_gemma":0.001180615,"domain_scores_codex":[0.454331,0.453238,0.03764478,0.01858079,0.0341129,0.00209252],"domain_scores_gemma":[0.1549858,0.7460142,0.03938124,0.03150684,0.02692359,0.001188313],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005197777,0.0008444685,0.8856512,0.002890941,0.0119986,0.0002865347,0.005258874,0.01763156,0.00129348,0.01048914,0.00142394,0.05703358],"study_design_scores_gemma":[0.002271262,0.02495408,0.6753762,0.002850152,0.01156914,0.00120786,0.008298685,0.2143025,0.01078149,0.03348192,0.01427189,0.000634688],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7739314,0.002750699,0.1940566,0.001408514,0.0007892089,0.01652518,0.001677331,0.0002579884,0.008603141],"genre_scores_gemma":[0.9282781,0.0001926343,0.06491655,0.0002726392,0.0001350295,0.005321755,0.000636873,0.00003240192,0.0002140522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5419697,"threshold_uncertainty_score":0.668345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.244946854893142,"score_gpt":0.4704047877529122,"score_spread":0.2254579328597703,"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."}}