{"id":"W4309650827","doi":"10.1093/jamia/ocac216","title":"Machine learning approaches for electronic health records phenotyping: a methodical review","year":2022,"lang":"en","type":"review","venue":"Journal of the American Medical Informatics Association","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Machine learning; Artificial intelligence; Computer science; Scalability; Data science; Deep learning; Data mining; Database","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02526925,0.0003552973,0.002888783,0.0002693813,0.0004971203,0.0001087965,0.003094696,0.0001628718,0.00004631869],"category_scores_gemma":[0.02148773,0.0002284254,0.001259537,0.001545624,0.00005977733,0.0002542838,0.0006423632,0.005333899,0.000004372048],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003636984,"about_ca_system_score_gemma":0.005979717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006178739,"about_ca_topic_score_gemma":0.000007641566,"domain_scores_codex":[0.9886,0.004550198,0.00326854,0.0001843053,0.002674796,0.0007221877],"domain_scores_gemma":[0.9751021,0.004168396,0.01966452,0.000512779,0.000191027,0.0003612011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002760013,0.00003027843,0.00002138487,0.01412121,0.0001984286,5.54991e-7,0.0002957505,0.00005529197,2.76307e-10,0.0009352842,0.003908521,0.9804305],"study_design_scores_gemma":[0.0001452951,0.0004494586,0.000002904065,0.008902648,0.0002238585,0.0001598683,0.00003830449,0.07259718,4.421183e-9,0.0002451675,0.91705,0.0001853206],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.229298e-7,0.8169352,0.1713151,0.01026686,0.0005985649,0.0007438472,0.000007260988,0.00003748739,0.00009542514],"genre_scores_gemma":[0.000001409647,0.9722407,0.02162249,0.005569411,0.0003175126,0.00007248564,0.00003030783,0.0000342655,0.0001113874],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9802452,"threshold_uncertainty_score":0.9996554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08341922040659462,"score_gpt":0.3967048151865077,"score_spread":0.3132855947799131,"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."}}