{"id":"W2740827051","doi":"10.2196/humanfactors.6857","title":"Modeling Patient Treatment With Medical Records: An Abstraction Hierarchy to Understand User Competencies and Needs","year":2017,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Conestoga College","funders":"","keywords":"Sociotechnical system; Abstraction; Hierarchy; Scope (computer science); Work (physics); Computer science; Domain (mathematical analysis); Health care; Knowledge management; Psychology; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001323067,0.0001885203,0.0001889084,0.0001800777,0.0009630993,0.0004622946,0.0004971551,0.00008366106,0.00003152019],"category_scores_gemma":[0.00003669871,0.0001361371,0.0000269191,0.00006856518,0.00007046817,0.0006162219,0.0001536543,0.0002168162,0.000004430342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001948095,"about_ca_system_score_gemma":0.00009139911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003807569,"about_ca_topic_score_gemma":0.00341434,"domain_scores_codex":[0.9985616,0.00007260406,0.000202588,0.000375624,0.0005057495,0.0002818355],"domain_scores_gemma":[0.9986183,0.00005717192,0.0001072148,0.0007322542,0.00006902119,0.0004160241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001333064,0.0006334301,0.5879644,0.0001345811,0.000129959,0.0001335732,0.17719,0.007846386,0.0001567335,0.02149446,0.0001512241,0.204032],"study_design_scores_gemma":[0.002257155,0.01414264,0.6200794,0.0005419497,0.00002801441,0.00007060737,0.0135642,0.3400255,0.0002582641,0.001891769,0.005676428,0.001464024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845689,0.00001057817,0.01341694,0.0009475862,0.0001586193,0.0003270086,0.000002662237,0.0001289325,0.0004387833],"genre_scores_gemma":[0.997418,0.000005954735,0.002261035,0.0001092122,0.00005840538,0.00001907558,0.000006616012,0.0000149745,0.0001066937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3321791,"threshold_uncertainty_score":0.7407479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0652248373115682,"score_gpt":0.3413551814976708,"score_spread":0.2761303441861026,"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."}}