{"id":"W4220667573","doi":"10.1007/s40745-022-00381-0","title":"A Machine Learning Model for Predicting Individual Substance Abuse with Associated Risk-Factors","year":2022,"lang":"en","type":"article","venue":"Annals of Data Science","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Machine learning; Decision tree; Naive Bayes classifier; Artificial intelligence; Random forest; Support vector machine; Substance abuse; Logistic regression; Computer science; CHAID; Vulnerability (computing); Psychology; Psychiatry; Computer security","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001644839,0.0001350882,0.0002680934,0.0001663099,0.0006529954,0.00002447232,0.0007178938,0.00001992249,0.00002367252],"category_scores_gemma":[0.0004441602,0.0001013432,0.00004339933,0.0008814044,0.0002188029,0.0008732052,0.0001186759,0.0002353964,4.845931e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003919214,"about_ca_system_score_gemma":0.0002171724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005526189,"about_ca_topic_score_gemma":0.0001828222,"domain_scores_codex":[0.997984,0.00003686968,0.0002275225,0.0004621715,0.0009005113,0.000388929],"domain_scores_gemma":[0.9985742,0.0002534307,0.0003399078,0.0005522593,0.0001735357,0.0001066394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002279589,0.0001732268,0.9864714,0.000007481902,0.000103664,0.000005253092,0.008340093,0.003724932,0.0001707764,0.00003177913,0.0001904196,0.0005530897],"study_design_scores_gemma":[0.004444492,0.001509655,0.2377251,0.0001240801,0.000401959,0.00001055517,0.005057726,0.746854,0.003045791,0.0001170863,0.000356313,0.0003532826],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975207,0.0003581478,0.0006303535,0.0001361065,0.00003772641,0.0003346085,0.0008556555,0.00006624376,0.0000604989],"genre_scores_gemma":[0.9960877,0.0002471039,0.002499567,0.0001371791,0.00001167384,0.00002157571,0.0007770513,0.00001636748,0.0002017588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7487463,"threshold_uncertainty_score":0.5022379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1783476059303608,"score_gpt":0.3609677976113045,"score_spread":0.1826201916809438,"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."}}