{"id":"W4205159797","doi":"10.2196/30474","title":"Using Health Concept Surveying to Elicit Usable Evidence: Case Studies of a Novel Evaluation Methodology","year":2022,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Innovative Human-Technology Interaction","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"U.S. National Library of Medicine; National Institute of Diabetes and Digestive and Kidney Diseases; National Institutes of Health; National Science Foundation","keywords":"USable; Applied psychology; Computer science; Vignette; Research design; Incentive; Psychology; Knowledge management; Medical education; Data science; Medicine; Social psychology; World Wide Web","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":[0.004796325,0.0001873022,0.0004386378,0.000763947,0.0009700263,0.00003765296,0.0006190593,0.00005596501,0.0001084622],"category_scores_gemma":[0.0009425476,0.0001922212,0.00006456958,0.001304009,0.000129818,0.0005756664,0.0008355578,0.0003915931,0.000002205806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201856,"about_ca_system_score_gemma":0.0002300494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000797765,"about_ca_topic_score_gemma":0.00015765,"domain_scores_codex":[0.9965295,0.001353553,0.0006189222,0.0005376634,0.0006000437,0.0003603331],"domain_scores_gemma":[0.9972853,0.0007869226,0.0006166057,0.0005454328,0.0007183231,0.0000474111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001023443,0.001231401,0.0242191,0.0003358022,0.0008477977,0.000225229,0.3322167,0.0421508,0.4348281,0.1338515,0.004962188,0.02502896],"study_design_scores_gemma":[0.01025441,0.01902826,0.101822,0.001772923,0.000350509,0.007860644,0.2672803,0.2449625,0.3172157,0.02018277,0.003086469,0.006183548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8848777,0.0001645855,0.1130654,0.0002936788,0.0006737002,0.0007932826,0.00001039355,0.0001027909,0.00001846318],"genre_scores_gemma":[0.9769154,6.972037e-7,0.02253051,0.0003130076,0.00002839048,0.0001462846,0.000005423443,0.00001312971,0.0000471231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2028117,"threshold_uncertainty_score":0.7838553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7480182231193021,"score_gpt":0.5826756446459754,"score_spread":0.1653425784733267,"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."}}