{"id":"W3036927141","doi":"10.3233/shti200121","title":"Automatic Extraction of Risk Factors for Dialysis Patients from Clinical Notes Using Natural Language Processing Techniques","year":2020,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dialysis; Dementia; Diabetes mellitus; Medicine; Electronic health record; Intensive care medicine; Health records; Natural language processing; Computer science; Artificial intelligence; Medical emergency; Psychiatry; Internal medicine; Disease; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001679081,0.001135897,0.0006289182,0.004014287,0.0004875033,0.001572816,0.000714481,0.0006528731,0.002163376],"category_scores_gemma":[0.01134346,0.0004217037,0.0009093852,0.001625852,0.0002580659,0.001102468,0.0008631661,0.0009261624,0.001355958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005777307,"about_ca_system_score_gemma":0.002169089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003921901,"about_ca_topic_score_gemma":0.004902955,"domain_scores_codex":[0.9987032,0.0003015049,0.0004183861,0.0002897189,0.0002367586,0.00005035635],"domain_scores_gemma":[0.9884844,0.008030184,0.001330411,0.0005105016,0.001487327,0.0001572114],"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":[0.0008548542,0.0004856426,0.03838784,0.003043497,0.0002591939,0.004503482,0.002087298,0.005651327,0.06179072,0.002727987,0.03183809,0.84837],"study_design_scores_gemma":[0.0009433537,0.001210223,0.1936377,0.002462759,0.001926665,0.01375065,0.006043245,0.3619559,0.1847384,0.03098433,0.2014765,0.000870413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2468604,0.004599027,0.6373376,0.004320969,0.0006506467,0.003438957,0.06787819,0.02862362,0.006290529],"genre_scores_gemma":[0.2672174,0.001361315,0.6962711,0.0004417667,0.0002482954,0.0006838306,0.03191954,0.0002812721,0.001575439],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004014287,"threshold_uncertainty_score":0.0088799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.24868230903548,"score_gpt":0.5618093797721642,"score_spread":0.3131270707366842,"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."}}