{"id":"W4376477583","doi":"10.2139/ssrn.4414662","title":"Integrating Unsupervised and Supervised Learning Techniques to Predict Traumatic Brain Injury: A Population-Based Study","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Traumatic brain injury; Unsupervised learning; Supervised learning; Population; Psychology; Artificial intelligence; Machine learning; Computer science; Medicine; Psychiatry; Artificial neural network","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":[0.003315764,0.0007101074,0.0007299759,0.001237683,0.0009789477,0.001126757,0.0007703482,0.001374257,0.001639442],"category_scores_gemma":[0.009065946,0.000603699,0.001358665,0.001131042,0.0008953618,0.001432073,0.0008177669,0.001538271,0.0006785622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003981592,"about_ca_system_score_gemma":0.0004558025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006691837,"about_ca_topic_score_gemma":0.006851931,"domain_scores_codex":[0.9983333,0.0007354426,0.0001209253,0.0004325143,0.0002441084,0.0001337952],"domain_scores_gemma":[0.9960982,0.001581621,0.0005799711,0.0005696969,0.0008740253,0.0002964625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006783958,0.001718831,0.9897472,0.00001672324,0.0004297484,0.0001332623,0.0007639832,0.0001699816,0.0003525626,0.0000334538,0.0003057131,0.005650283],"study_design_scores_gemma":[0.00008294162,0.00255883,0.9918819,0.00001270522,0.0003670512,0.0005251434,0.001766765,0.002197957,0.0001318198,0.0001339381,0.0003116168,0.000029316],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9994456,0.00004052588,0.0002735999,0.00002054878,0.000005340131,0.00001119545,0.0000816688,0.000003388139,0.0001181277],"genre_scores_gemma":[0.9989838,0.00007578819,0.0002471622,0.0000304976,0.00001808395,0.00002180029,0.0003068207,0.000007414967,0.0003085735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006691837,"threshold_uncertainty_score":0.01753563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1260401635491595,"score_gpt":0.4638827457262444,"score_spread":0.3378425821770848,"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."}}