{"id":"W2957140256","doi":"10.2196/13128","title":"How We Evaluate Postgraduate Medical E-Learning: Systematic Review","year":2019,"lang":"en","type":"review","venue":"JMIR Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Usability; Medical education; Instructional design; Psychology; MEDLINE; Active learning (machine learning); Systematic review; Medicine; Computer science; Artificial intelligence; Mathematics education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.005701452,0.001006689,0.005875009,0.0008644111,0.0001702873,0.0001212648,0.001131525,0.002022332,0.00437988],"category_scores_gemma":[0.07491826,0.0006987457,0.001072129,0.002505287,0.0003310066,0.0002104844,0.0002011204,0.004503818,0.002922845],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156797,"about_ca_system_score_gemma":0.02948901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000757703,"about_ca_topic_score_gemma":9.056554e-7,"domain_scores_codex":[0.9867075,0.00156991,0.002950105,0.001190902,0.006800155,0.000781437],"domain_scores_gemma":[0.9931433,0.0006266217,0.002007212,0.00189106,0.00131109,0.001020688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002304301,0.0004333513,7.811442e-7,0.4973023,0.0001736226,0.00001095278,0.00005470804,1.817903e-9,1.079513e-8,0.0002320604,0.101151,0.4006389],"study_design_scores_gemma":[0.0002276936,0.00009823089,8.907509e-7,0.48893,0.004069952,0.000964331,0.00009766978,0.00004915875,3.480443e-8,0.00001881602,0.5052332,0.0003100257],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00000179919,0.8977695,0.00005197296,0.08634492,0.003831032,0.0103378,0.000003525552,0.0002377689,0.001421655],"genre_scores_gemma":[0.000004329125,0.9505733,0.0002460696,0.01444449,0.002042933,0.006200306,0.002585098,0.0002028927,0.02370054],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4040822,"threshold_uncertainty_score":0.9995463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05664265392371726,"score_gpt":0.4570186284625186,"score_spread":0.4003759745388014,"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."}}