{"id":"W4309077608","doi":"10.1038/s41598-022-23101-3","title":"Ontology-based feature engineering in machine learning workflows for heterogeneous epilepsy patient records","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"International League Against Epilepsy; Office of Extramural Research, National Institutes of Health; National Center for Advancing Translational Sciences; National Institutes of Health; Else Kröner-Fresenius-Stiftung","keywords":"Workflow; Computer science; Ontology; Feature (linguistics); Epilepsy; Feature engineering; Artificial intelligence; Data science; Machine learning; Deep learning; Database; Neuroscience; Biology","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":[0.01132629,0.0008116757,0.0009599175,0.003459105,0.001148788,0.002980246,0.00160386,0.0008846578,0.0007863082],"category_scores_gemma":[0.02845775,0.000502478,0.002393348,0.002709874,0.0007491362,0.003536437,0.002333778,0.001539573,0.0003485788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003165856,"about_ca_system_score_gemma":0.004856926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01743985,"about_ca_topic_score_gemma":0.01523607,"domain_scores_codex":[0.9942006,0.002358923,0.0009450715,0.001098936,0.001080835,0.0003155961],"domain_scores_gemma":[0.9849136,0.009328656,0.001452585,0.002028959,0.001928134,0.000347993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004529885,0.0007127777,0.02622805,0.0004224367,0.0002918315,0.0008807465,0.00143143,0.3778602,0.006955292,0.01841384,0.004400517,0.5619498],"study_design_scores_gemma":[0.00003037727,0.00006725309,0.001803247,0.00004204094,0.00004642417,0.0001338133,0.0002003291,0.9729706,0.004341581,0.01765573,0.002673462,0.00003507624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0527994,0.0001996237,0.9374506,0.0007348844,0.00004994526,0.0004570998,0.0009245925,0.006854715,0.0005290643],"genre_scores_gemma":[0.3391531,0.0001377542,0.6573675,0.000118997,0.00002400033,0.0003475905,0.002297697,0.0002120056,0.0003413571],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01743985,"threshold_uncertainty_score":0.05989981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01172345276269541,"score_gpt":0.2429472517418376,"score_spread":0.2312237989791422,"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."}}