{"id":"W3167873286","doi":"10.2196/19905","title":"Patient Representation From Structured Electronic Medical Records Based on Embedding Technique: Development and Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Medical diagnosis; Representation (politics); Embedding; Feature learning; Feature (linguistics); Cosine similarity; Cluster analysis; Pattern recognition (psychology); Machine learning; Data mining; Medicine; Pathology","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":[0.000818067,0.000162197,0.0002224056,0.0001252763,0.0001646521,0.0001264622,0.0003928127,0.0002066612,0.0003573114],"category_scores_gemma":[0.001130833,0.0001403569,0.00002767099,0.000412653,0.00003046161,0.0002676666,0.0003094075,0.0007782312,0.00001652515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001791131,"about_ca_system_score_gemma":0.001168384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002922698,"about_ca_topic_score_gemma":0.00004633225,"domain_scores_codex":[0.9961703,0.0003215481,0.0008024485,0.0002589437,0.002135545,0.0003112262],"domain_scores_gemma":[0.9984138,0.0003988677,0.0002364445,0.0004873273,0.0001356013,0.000327968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002969059,0.0003494245,0.02173971,0.0001567191,0.00004326776,0.000113563,0.02843103,0.0004216151,0.00001033053,0.0008202686,0.0007525671,0.9471318],"study_design_scores_gemma":[0.00105508,0.0004858507,0.01329469,0.0003208367,0.000007281467,0.00003918566,0.001846338,0.9758078,0.002782885,0.0006225413,0.003437083,0.0003004467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6795484,0.00001537064,0.3178218,0.001237324,0.0002415932,0.000627552,0.000001432365,0.0001928583,0.0003136511],"genre_scores_gemma":[0.9168599,0.000006777042,0.08109219,0.001674853,0.00005864981,0.0001927697,0.00009396224,0.00001011652,0.00001078686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9753861,"threshold_uncertainty_score":0.5723589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0155739882696843,"score_gpt":0.340829851255232,"score_spread":0.3252558629855477,"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."}}