{"id":"W2099537015","doi":"10.1016/j.ijnurstu.2011.07.002","title":"Testing the reliability and efficiency of the pilot Mixed Methods Appraisal Tool (MMAT) for systematic mixed studies review","year":2011,"lang":"en","type":"article","venue":"International Journal of Nursing Studies","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":1354,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Checklist; Reliability (semiconductor); Inter-rater reliability; Cohen's kappa; Quality (philosophy); Research design; Systematic review; Medical physics; Psychology; Medicine; Statistics; MEDLINE; Mathematics; Rating scale; Chemistry","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":[0.4663014,0.001318246,0.003070037,0.006340318,0.002240119,0.003805387,0.002139453,0.002707206,0.002673712],"category_scores_gemma":[0.7258431,0.002455183,0.008116985,0.005371646,0.002956349,0.005185524,0.006226244,0.001848567,0.0005779358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003737612,"about_ca_system_score_gemma":0.01001029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001374994,"about_ca_topic_score_gemma":0.002572149,"domain_scores_codex":[0.4542324,0.400939,0.09535836,0.00871352,0.03849954,0.00225719],"domain_scores_gemma":[0.1221605,0.7344551,0.02305883,0.03174615,0.08756004,0.001019323],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01605573,0.002792863,0.1517309,0.05013652,0.0181765,0.0006184763,0.07424877,0.007997937,0.01221404,0.01015678,0.006312418,0.649559],"study_design_scores_gemma":[0.02775274,0.07882882,0.4385803,0.040014,0.07361156,0.00308331,0.03857337,0.1312271,0.06561691,0.02988478,0.07061248,0.002214635],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6195942,0.006971108,0.2716478,0.002655282,0.001422044,0.08573927,0.001569538,0.001059106,0.00934159],"genre_scores_gemma":[0.6212997,0.000893004,0.3249421,0.0003513603,0.0001284747,0.05131959,0.0003989408,0.0001359197,0.0005308968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5336986,"threshold_uncertainty_score":0.6581454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4938030885747823,"score_gpt":0.5981297874005457,"score_spread":0.1043266988257633,"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."}}