{"id":"W4376879040","doi":"10.1016/j.jbi.2023.104395","title":"A community-of-practice-based evaluation methodology for knowledge intensive computational methods and its application to multimorbidity decision support","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital; Dalhousie University; University of Ottawa","funders":"","keywords":"Computer science; Operationalization; Decision support system; Domain (mathematical analysis); Feature (linguistics); Computational model; Benchmark (surveying); USable; Artificial intelligence; Computational thinking; Data science; Machine learning; Management science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1580735,0.00163995,0.002420804,0.009881319,0.002709056,0.005450936,0.002552252,0.002609508,0.00504456],"category_scores_gemma":[0.343608,0.0005930219,0.002235435,0.007545162,0.001874202,0.003779327,0.006999485,0.001996728,0.0004954837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003406228,"about_ca_system_score_gemma":0.01203895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007565346,"about_ca_topic_score_gemma":0.01004384,"domain_scores_codex":[0.8419852,0.125493,0.008688178,0.004612892,0.01784777,0.001373062],"domain_scores_gemma":[0.701086,0.2211049,0.01322354,0.01145735,0.04905412,0.004074116],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005628676,0.004887052,0.1074483,0.005578842,0.004793591,0.000286287,0.005696825,0.08867938,0.003082772,0.07010324,0.0122401,0.6915749],"study_design_scores_gemma":[0.002052116,0.004492887,0.0243045,0.001567398,0.001863802,0.0004140972,0.003139134,0.8818327,0.00378393,0.06440661,0.01186324,0.0002795608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1584133,0.0009219641,0.8123735,0.002435805,0.0002587564,0.01187703,0.001887002,0.0008913148,0.01094137],"genre_scores_gemma":[0.4501727,0.0001202944,0.5421532,0.0002131825,0.00004664559,0.005863742,0.0009039618,0.00007821582,0.0004479855],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8419265,"threshold_uncertainty_score":0.8359825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.284602727147468,"score_gpt":0.5670888552916508,"score_spread":0.2824861281441827,"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."}}