{"id":"W4288321632","doi":"10.48550/arxiv.1907.03706","title":"Developing an Evidence-Based Framework for Grading and Assessment of\\n Predictive Tools for Clinical Decision Support","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); GRASP; Critical appraisal; Evidence-based practice; Evidence-based medicine; Computer science; Medicine; Engineering; Alternative medicine; Pathology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3668486,0.005401241,0.007993434,0.06888217,0.006617565,0.02268778,0.01392812,0.007812085,0.005872917],"category_scores_gemma":[0.4782241,0.002977264,0.01502439,0.02606176,0.009931944,0.01481482,0.01890771,0.0111491,0.002316711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03189411,"about_ca_system_score_gemma":0.08592527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02049902,"about_ca_topic_score_gemma":0.02991042,"domain_scores_codex":[0.6557818,0.2003195,0.08702999,0.0088228,0.04420684,0.003839142],"domain_scores_gemma":[0.4519864,0.3606808,0.0442967,0.01602573,0.1203974,0.006612893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005900844,0.000535435,0.01172667,0.09670021,0.004946638,0.0004648667,0.007314273,0.01665807,0.0007922882,0.1833389,0.05677438,0.6201582],"study_design_scores_gemma":[0.001286078,0.001406082,0.01203923,0.2767998,0.008638656,0.0009458642,0.006850495,0.04003461,0.002595122,0.4401769,0.2081205,0.001106666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009596534,0.1014896,0.7223997,0.0716148,0.002974538,0.05049182,0.006270812,0.002133356,0.03302879],"genre_scores_gemma":[0.03511858,0.009756654,0.9384356,0.002166384,0.0003021271,0.01189604,0.001817566,0.00007570861,0.0004313691],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3668486,"threshold_uncertainty_score":0.7807884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7162999676104943,"score_gpt":0.5069695957311376,"score_spread":0.2093303718793567,"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."}}