{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01100104,0.0001022484,0.0003984724,0.0006609202,0.00007941075,0.00001557903,0.0001374991,0.00009425869,0.00003602855],"category_scores_gemma":[0.01934085,0.00008246243,0.0001014765,0.0005573902,0.0001104735,0.0002288144,0.0001069466,0.0002605691,0.00001360828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001290551,"about_ca_system_score_gemma":0.000638574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003353852,"about_ca_topic_score_gemma":8.400304e-7,"domain_scores_codex":[0.9977331,0.0004339665,0.001063626,0.00005618154,0.0005706585,0.0001424837],"domain_scores_gemma":[0.9898542,0.0063727,0.0006936518,0.0001492275,0.002703567,0.0002266956],"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":[0.002261281,0.0007504046,0.00004012744,0.002209401,0.0005265673,0.000007190797,0.01073666,0.006486889,0.001766917,0.001605437,0.03468806,0.938921],"study_design_scores_gemma":[0.005936941,0.001824813,0.003228041,0.0003049044,0.0007807816,0.00008162849,0.01139789,0.9412432,0.0005347645,0.004633287,0.02992484,0.0001089093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07714366,0.00006670783,0.9185483,0.002840678,0.0002776227,0.0008770141,0.0000241182,0.0000186529,0.0002032316],"genre_scores_gemma":[0.231639,0.00003703979,0.7666109,0.001291539,0.00009753258,0.00003784579,0.0002633705,0.00001116925,0.00001165029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9388121,"threshold_uncertainty_score":0.9889197,"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."}}