{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002311378,0.0002198872,0.0002928784,0.0005206487,0.0007645921,0.0002374932,0.000590617,0.00007736277,0.00006942956],"category_scores_gemma":[0.0005480776,0.0002349412,0.0001488331,0.001151458,0.00003676812,0.000138954,0.0004228437,0.0008140521,0.000003083641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003213593,"about_ca_system_score_gemma":0.0002674151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001452973,"about_ca_topic_score_gemma":0.0001806602,"domain_scores_codex":[0.996595,0.0002625791,0.0005871474,0.001258611,0.0006381683,0.000658544],"domain_scores_gemma":[0.9980454,0.0001967115,0.0003904386,0.001109657,0.0001067323,0.0001510513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002222415,0.0000907155,0.08672086,0.00007890398,0.000008081508,0.001148851,0.0009973628,0.877589,0.0002917755,0.0001513216,0.001990794,0.03091008],"study_design_scores_gemma":[0.0002455856,0.0003169206,0.001121866,0.00003309854,0.000003220003,0.0004994919,0.00001627168,0.8137362,0.0003744307,0.0006075591,0.1827651,0.0002803203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8974288,0.001393518,0.06799109,0.003340107,0.02676965,0.001958527,0.00000976692,0.0008791737,0.0002293856],"genre_scores_gemma":[0.9600432,6.698985e-7,0.03836479,0.0001944521,0.00004599866,0.0004344218,0.0000942363,0.00003066136,0.0007915844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1807743,"threshold_uncertainty_score":0.9580625,"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."}}