{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002995374,0.0007873368,0.001113205,0.001633692,0.0005483548,0.001215486,0.001319719,0.001184702,0.002514477],"category_scores_gemma":[0.009422171,0.0003276365,0.001202323,0.001224327,0.000328967,0.0009648955,0.000631653,0.001968492,0.0009902688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007371844,"about_ca_system_score_gemma":0.001394534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01202877,"about_ca_topic_score_gemma":0.01050706,"domain_scores_codex":[0.999255,0.0003065939,0.00007267633,0.0002008538,0.00009080669,0.00007404298],"domain_scores_gemma":[0.9948384,0.004152909,0.0002463521,0.0002204953,0.0004169638,0.000124824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001117974,0.001567584,0.1753748,0.0001631537,0.00082974,0.0004216863,0.0002033251,0.4928887,0.001025542,0.006467648,0.01352716,0.3064127],"study_design_scores_gemma":[0.0000260755,0.00006480552,0.004220247,0.00001627146,0.00005379227,0.00006768639,0.00001595148,0.9908097,0.000125584,0.004180474,0.0004097735,0.000009716505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4399574,0.002438632,0.5379451,0.005776497,0.0005389114,0.0003033896,0.007901814,0.002024517,0.003113832],"genre_scores_gemma":[0.9315658,0.0005798295,0.05793056,0.0003453609,0.00031841,0.0002968298,0.004760377,0.00004121987,0.004161724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01202877,"threshold_uncertainty_score":0.02391756,"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."}}