{"id":"W3017202087","doi":"10.1038/s41598-020-63515-5","title":"Data-driven segmentation of audiometric phenotypes across a large clinical cohort","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Deafness and Other Communication Disorders; National Institutes of Health; McGill University","keywords":"Cohort; Phenotype; Segmentation; Medicine; Computer science; Audiology; Biology; Genetics; Internal medicine; Artificial intelligence; Gene","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003265554,0.00008659618,0.0002221334,0.00009570484,0.0002746498,0.0001444922,0.0002910125,0.00005788642,0.00007161629],"category_scores_gemma":[0.006545308,0.00007243864,0.00007606254,0.001678451,0.0003449851,0.000376425,0.0003430612,0.0001186449,0.00005542565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001860585,"about_ca_system_score_gemma":0.0001272205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000100059,"about_ca_topic_score_gemma":0.000002877386,"domain_scores_codex":[0.9969653,0.0001602146,0.0008272963,0.001065293,0.0006889366,0.0002928915],"domain_scores_gemma":[0.9981977,0.0002432055,0.0004119164,0.0008739774,0.000117913,0.0001553354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001864278,0.0002869283,0.3503096,0.00009704561,0.00001225725,0.00009790382,0.001524128,0.0001647075,0.627781,0.00007922081,0.005855753,0.01377281],"study_design_scores_gemma":[0.0008571348,0.0003669836,0.7850536,0.00007605701,0.00006946681,0.00008598169,0.0006183731,0.02698028,0.1500319,0.001234392,0.03413888,0.0004869848],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937211,0.00002541631,0.001846658,0.0002989524,0.003327207,0.0003719052,0.00006366031,0.00006306104,0.0002820491],"genre_scores_gemma":[0.9983073,0.000006518731,0.00116269,0.0001450079,0.00008948772,0.000006431746,0.00005980003,0.000009906424,0.0002128152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.477749,"threshold_uncertainty_score":0.7835818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1296542348788646,"score_gpt":0.4054579831297491,"score_spread":0.2758037482508846,"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."}}