{"id":"W4226225581","doi":"10.22215/etd/2022-14958","title":"Exploring the Relationship Between Scoring Accuracy and Predictive Validity in Risk Assessment Using the Service Planning Instrument (SPIn)","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Predictive validity; Reliability (semiconductor); Consistency (knowledge bases); Indigenous; Risk assessment; Predictive power; Statistics; Sample (material); Psychology; Computer science; Clinical psychology; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1280022,0.0005198462,0.0005372469,0.002431999,0.0009815617,0.002563764,0.001162894,0.0008148348,0.0007281281],"category_scores_gemma":[0.3664214,0.0006329248,0.001204663,0.002323982,0.00224924,0.003217791,0.002528629,0.002068916,0.0001884038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001523084,"about_ca_system_score_gemma":0.002124097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01458125,"about_ca_topic_score_gemma":0.01841429,"domain_scores_codex":[0.9140278,0.05139345,0.006940272,0.004617727,0.02123548,0.001785337],"domain_scores_gemma":[0.4536766,0.4645875,0.03624745,0.01707637,0.0271413,0.001270789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001593229,0.00006177829,0.9783891,0.00004108866,0.0003255725,0.0000196509,0.002885591,0.0006409285,0.0001342115,0.0005616072,0.0001670327,0.01661405],"study_design_scores_gemma":[0.00003109688,0.0007714396,0.9734384,0.0002397328,0.0003294233,0.0002358599,0.003047175,0.01756675,0.00129836,0.001997281,0.0009792936,0.00006529225],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809291,0.0003860796,0.01371524,0.000374204,0.00005946492,0.0001678177,0.00009983242,0.00002962049,0.004238611],"genre_scores_gemma":[0.9929246,0.0001137345,0.00643988,0.00005484961,0.00003072008,0.00009459527,0.0001005146,0.00001264903,0.0002284847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1280022,"threshold_uncertainty_score":0.6769487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8902706173550375,"score_gpt":0.6935027716384699,"score_spread":0.1967678457165677,"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."}}