{"id":"W4225772450","doi":"10.1007/978-981-19-9865-2_10","title":"Machine Learning for Multimodal Electronic Health Records-Based Research: Challenges and Perspectives","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Health records; Modalities; Unstructured data; Electronic health record; Machine learning; Artificial intelligence; Digital library; Data science; Information retrieval; Data mining; Big data; Health care","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.006332593,0.0002178895,0.0003088399,0.001754309,0.001368314,0.0004230444,0.002351265,0.0001253549,0.000001935977],"category_scores_gemma":[0.0004207505,0.0002251198,0.00004137378,0.000457289,0.0008266307,0.002222262,0.001883763,0.00145441,0.00001326449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000392996,"about_ca_system_score_gemma":0.001028439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072531,"about_ca_topic_score_gemma":0.0002115557,"domain_scores_codex":[0.9975721,0.0002238688,0.0005875732,0.0005032449,0.0005557789,0.0005574817],"domain_scores_gemma":[0.9957619,0.001544396,0.0003371369,0.001475298,0.0007207857,0.0001604313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003302557,0.000007170187,0.00002295911,0.00009718545,0.000002744132,8.247101e-8,0.008237649,0.0004602674,8.749233e-8,0.5726699,0.00002769421,0.4184709],"study_design_scores_gemma":[0.0002950365,0.0003546739,0.001143073,0.0002537696,0.000001089284,0.000006658427,0.0002099878,0.8835527,2.864562e-7,0.0167271,0.09725396,0.0002016333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009327564,0.05331763,0.7257612,0.126361,0.0007589623,0.004644929,0.00005064619,0.001207117,0.08780522],"genre_scores_gemma":[0.2034097,0.2848819,0.5023238,0.002082007,0.0002364302,0.0005713316,0.0002829724,0.0001023155,0.006109502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8830925,"threshold_uncertainty_score":0.9999318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2531785037105655,"score_gpt":0.4162408136605928,"score_spread":0.1630623099500273,"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."}}