{"id":"W3121070036","doi":"10.1007/978-3-030-73050-5_42","title":"Predicting Individual Substance Abuse Vulnerability Using Machine Learning Techniques","year":2021,"lang":"en","type":"preprint","venue":"Advances in intelligent systems and computing","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Vulnerability (computing); Logistic regression; Machine learning; Substance abuse; Artificial intelligence; Classifier (UML); Substance abuse prevention; Binary classification; Predictive power; Computer science; Alcohol abuse; Psychology; Psychiatry; Computer security; Support vector machine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001019231,0.0005596167,0.001236602,0.0002780726,0.0002348266,0.0001786219,0.0001959428,0.0003281076,0.00001076166],"category_scores_gemma":[0.0001226847,0.0005107723,0.0001852459,0.0003204667,0.0001146315,0.0002366851,0.000206924,0.001476686,8.30843e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003816259,"about_ca_system_score_gemma":0.00008736635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004188853,"about_ca_topic_score_gemma":0.000545397,"domain_scores_codex":[0.9965367,0.0002794583,0.001156517,0.001001565,0.0004946136,0.0005311621],"domain_scores_gemma":[0.9981367,0.000456369,0.0006082513,0.0004765105,0.0001885169,0.0001336248],"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":[0.0000549266,0.0001106702,0.9642034,0.001066737,0.0001440143,0.0001743515,0.00976842,0.01236166,0.0001005313,0.00004504764,4.152719e-7,0.01196986],"study_design_scores_gemma":[0.004442345,0.0007840518,0.04902108,0.08212621,0.001539308,0.001417501,0.06183118,0.76342,0.02758717,0.0005108991,0.003192619,0.004127611],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8757943,0.1118572,0.009982122,0.00001100341,0.00100394,0.0009292057,0.00000476188,0.0002621655,0.0001552995],"genre_scores_gemma":[0.9769083,0.01279892,0.009591513,0.00003712682,0.0003963087,0.00004031597,0.0001096687,0.00006230158,0.00005556793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9151823,"threshold_uncertainty_score":0.9997344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04301806237029548,"score_gpt":0.3321914736632374,"score_spread":0.2891734112929419,"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."}}