{"id":"W2809365483","doi":"10.1186/s12961-018-0334-9","title":"Validity and usability testing of a health systems guidance appraisal tool, the AGREE-HS","year":2018,"lang":"en","type":"article","venue":"Health Research Policy and Systems","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Juravinski Cancer Centre","funders":"Canadian Institutes of Health Research","keywords":"Usability; Quality (philosophy); Context (archaeology); Reliability (semiconductor); Face validity; Computer science; Applied psychology; Test (biology); Health informatics; Content validity; Consistency (knowledge bases); Health services research; Psychology; Knowledge management; Medicine; Psychometrics; Public health; Human–computer interaction; Nursing; Clinical psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"category_scores_codex":[0.2176951,0.0009450291,0.00131925,0.004832459,0.001934265,0.003465712,0.001834033,0.001494268,0.002194429],"category_scores_gemma":[0.3573633,0.0008818868,0.003605639,0.003991144,0.002539352,0.003307794,0.004425982,0.002190575,0.0006386386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004631713,"about_ca_system_score_gemma":0.01097894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002649879,"about_ca_topic_score_gemma":0.005740343,"domain_scores_codex":[0.7696822,0.1552622,0.03315546,0.004948644,0.03369699,0.003254414],"domain_scores_gemma":[0.5572794,0.3025889,0.02162419,0.02533925,0.09051009,0.002658254],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002859499,0.004782852,0.1315034,0.01520428,0.001017734,0.0005161801,0.09273553,0.003421418,0.006424109,0.006560745,0.02374497,0.7112293],"study_design_scores_gemma":[0.007257771,0.03399129,0.6163196,0.02412449,0.002563428,0.001914294,0.1003265,0.04949535,0.02311162,0.01533567,0.1239573,0.001602782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7922266,0.001508598,0.0858437,0.004523076,0.000970365,0.0874598,0.002144361,0.0009271835,0.02439628],"genre_scores_gemma":[0.6363583,0.0008032975,0.2628507,0.001149505,0.0001434924,0.09600738,0.001206687,0.0001505937,0.001329997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7823049,"threshold_uncertainty_score":0.9647213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9170243300131491,"score_gpt":0.7509985645732905,"score_spread":0.1660257654398586,"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."}}