{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005439221,0.001044013,0.00150981,0.002441928,0.0006476704,0.001099984,0.001318296,0.0009536134,0.0005304117],"category_scores_gemma":[0.009057883,0.0004672663,0.001511383,0.001777518,0.0004686795,0.001236849,0.0008940541,0.001860734,0.00017066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006100467,"about_ca_system_score_gemma":0.001439216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004372868,"about_ca_topic_score_gemma":0.003803289,"domain_scores_codex":[0.9981788,0.0006764912,0.0002257416,0.0004501229,0.0002847272,0.0001841062],"domain_scores_gemma":[0.9914932,0.00635851,0.000738688,0.0002885339,0.0009295106,0.0001915379],"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":[0.0003363884,0.0006756445,0.1301217,0.0003340738,0.0006151118,0.0009467829,0.0003956105,0.6048133,0.002364157,0.002977695,0.003210499,0.253209],"study_design_scores_gemma":[0.00001004497,0.00005614837,0.004111062,0.00002117881,0.00004617692,0.00005569968,0.00005269111,0.9926467,0.0003359886,0.002414177,0.0002361319,0.00001395989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1858957,0.0008332659,0.8105802,0.001015762,0.00009375618,0.0002169543,0.0004841457,0.0003852014,0.0004950992],"genre_scores_gemma":[0.8553964,0.0005372023,0.1417065,0.0001934715,0.0002362841,0.0003044354,0.00116874,0.00002646495,0.0004305452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005439221,"threshold_uncertainty_score":0.02876568,"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."}}