{"id":"W2912141246","doi":"10.1109/access.2019.2894421","title":"Towards a Knowledge-Based Recommender System for Linking Electronic Patient Records With Continuing Medical Education Information at the Point of Care","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Association des pharmaciens du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Context (archaeology); Matching (statistics); Set (abstract data type); Recall; Medical record; Precision and recall; Point of care; Information retrieval; Recommender system; Point (geometry); Artificial intelligence; Medicine; Nursing; Psychology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005907564,0.0001216369,0.0001862336,0.000110969,0.0001141199,0.0001263646,0.0008695945,0.00008526952,0.00001516253],"category_scores_gemma":[0.0001034082,0.00008181867,0.00005488197,0.0002884138,0.00001771983,0.0005970665,0.0001381989,0.000240039,0.000009509517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005203884,"about_ca_system_score_gemma":0.001202156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003455282,"about_ca_topic_score_gemma":0.0005073412,"domain_scores_codex":[0.9985805,0.0001724978,0.0003869545,0.000208192,0.0003798489,0.0002720174],"domain_scores_gemma":[0.9982222,0.0002371157,0.0003947449,0.0004880964,0.0005918895,0.00006600314],"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":[0.0001518721,0.00005482326,0.03126894,0.003331719,0.00002825546,3.095136e-7,0.01787096,0.002436789,0.000008439885,0.004411734,0.0007409421,0.9396952],"study_design_scores_gemma":[0.003890658,0.003166341,0.0108436,0.007387899,0.00006378119,0.00007099118,0.005020011,0.9094861,0.01150552,0.0004093319,0.04719646,0.0009593375],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7200915,0.0004753263,0.2695657,0.003235756,0.002452815,0.001809595,0.000005228508,0.0001638514,0.002200203],"genre_scores_gemma":[0.9978088,0.000003535851,0.001446159,0.0004277894,0.00007066476,0.0001890165,0.00002737894,0.00001059971,0.00001602337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9387359,"threshold_uncertainty_score":0.3336469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009433303879319,"score_gpt":0.3028955956082646,"score_spread":0.2934622917289456,"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."}}