{"id":"W2910814369","doi":"10.1371/journal.pone.0208737","title":"Computational prediction of diagnosis and feature selection on mesothelioma patient health records","year":2019,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Occupational and environmental lung diseases","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"University of California, Irvine; University of Toronto; University of Melbourne","keywords":"Feature selection; Mesothelioma; Feature (linguistics); Computer science; Health records; Computational biology; Medicine; Bioinformatics; Artificial intelligence; Data mining; Biology; Pathology; Health care","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0000258753,0.00005166832,0.0001176708,0.00005310778,0.00002627492,0.000002282024,0.000008843006,0.00002619791,0.0001552979],"category_scores_gemma":[0.00001005102,0.00004494376,0.00001979549,0.0000625836,0.00001505298,0.00003207234,0.000005590374,0.00004938489,0.00002153772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005851524,"about_ca_system_score_gemma":0.00002116388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001693396,"about_ca_topic_score_gemma":0.000001350379,"domain_scores_codex":[0.999449,0.00001700203,0.00009696204,0.000113226,0.0002662701,0.00005750768],"domain_scores_gemma":[0.9997813,0.00003663957,0.00005565337,0.00004472971,0.00002243492,0.00005930458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003005423,0.002018488,0.9916331,0.0002379168,0.00009465983,2.789181e-7,0.00006950394,0.0001203741,0.0009610542,0.00006213821,0.001049301,0.003452659],"study_design_scores_gemma":[0.0005152408,0.002379172,0.9920649,0.0003344026,0.00005015158,0.000001970415,0.00001781312,0.001758787,0.002601276,0.0001233067,0.0001200278,0.0000329754],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977597,0.0001972992,0.000006683123,0.001231422,0.00002217624,0.0003486032,0.0001222485,0.00001859723,0.0002932915],"genre_scores_gemma":[0.9978253,0.0001688338,0.001049287,0.0004899037,0.00003964315,0.00002372197,0.0001867775,0.000006999913,0.0002095939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003419684,"threshold_uncertainty_score":0.1832753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02016829143078109,"score_gpt":0.231500363062056,"score_spread":0.2113320716312749,"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."}}