{"id":"W4313154943","doi":"10.2196/38590","title":"Dealing With Missing, Imbalanced, and Sparse Features During the Development of a Prediction Model for Sudden Death Using Emergency Medicine Data: Machine Learning Approach","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"General Hospital of People’s Liberation Army; National Natural Science Foundation of China","keywords":"Missing data; Random forest; Interpolation (computer graphics); Artificial intelligence; Data pre-processing; Receiver operating characteristic; Computer science; Data mining; Logistic regression; Preprocessor; Machine learning; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001693235,0.0001699615,0.0002605971,0.0001185333,0.0009653794,0.00002436439,0.0009963915,0.0000620845,0.00002025754],"category_scores_gemma":[0.000199062,0.0001111014,0.00002085915,0.0002637364,0.00007422765,0.0003383815,0.001035882,0.0007256956,9.472887e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006960201,"about_ca_system_score_gemma":0.0002909644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004766354,"about_ca_topic_score_gemma":0.00001686126,"domain_scores_codex":[0.9974983,0.00008585212,0.0008167222,0.0002176145,0.001079471,0.0003020074],"domain_scores_gemma":[0.9986609,0.0001024915,0.0004956977,0.0004855887,0.00008831063,0.0001669686],"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":[0.0003407104,0.0002617708,0.08657512,0.007594146,0.0003191382,0.000008260181,0.328352,0.5090938,0.0001386699,0.008291871,0.0007436677,0.05828083],"study_design_scores_gemma":[0.0005833835,0.00009048863,0.001706954,0.000112783,0.00001453269,0.0001099013,0.001332537,0.995151,0.000005766752,0.00007724032,0.0006987893,0.0001165932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1618483,0.0003150822,0.8363891,0.0004325501,0.0001204492,0.0005569807,0.00001935156,0.00009836137,0.0002198802],"genre_scores_gemma":[0.6488348,0.00003857327,0.3505792,0.0001010444,0.00009020867,0.00009849425,0.0001359673,0.0000197093,0.0001019593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4869865,"threshold_uncertainty_score":0.7425016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06055190061720239,"score_gpt":0.3362449957190598,"score_spread":0.2756930951018574,"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."}}