{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00407797,0.0007067659,0.0004163405,0.001627885,0.0002064823,0.0006267265,0.0007408558,0.0007069727,0.001427246],"category_scores_gemma":[0.01359873,0.0001767657,0.0007172847,0.001073185,0.0004313372,0.001313404,0.001031035,0.0004775554,0.0005559529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004623691,"about_ca_system_score_gemma":0.0006640222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001599065,"about_ca_topic_score_gemma":0.001163345,"domain_scores_codex":[0.997493,0.001395863,0.000214737,0.0003107073,0.0004903168,0.00009543902],"domain_scores_gemma":[0.9924688,0.004179387,0.0004644191,0.001047991,0.001701698,0.0001378658],"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":[0.001787724,0.003571033,0.0718991,0.001680195,0.0005575372,0.0008647866,0.001432692,0.05259214,0.02981631,0.002575733,0.006916492,0.8263062],"study_design_scores_gemma":[0.0004536032,0.005940874,0.1061366,0.0002910688,0.0005213905,0.002487763,0.001314416,0.822241,0.0493226,0.001776542,0.009356608,0.0001574537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9092126,0.000667449,0.08402458,0.0001476696,0.0001123424,0.0011827,0.002307058,0.0009774433,0.00136816],"genre_scores_gemma":[0.8687145,0.0005993671,0.1197417,0.00005176152,0.00004683556,0.0006703947,0.009151682,0.00004072219,0.0009830937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00407797,"threshold_uncertainty_score":0.02156663,"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."}}