{"id":"W4205346926","doi":"10.1136/bmjopen-2021-053820","title":"Problems with evidence assessment in COVID-19 health policy impact evaluation: a systematic review of study design and evidence strength","year":2022,"lang":"en","type":"review","venue":"BMJ Open","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse; National Institute of Mental Health; National Heart, Lung, and Blood Institute; Knut och Alice Wallenbergs Stiftelse; National Institutes of Health; Laura and John Arnold Foundation","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Impact assessment; Health impact assessment; Health policy; Set (abstract data type); Inclusion (mineral); Research design; Systematic review; MEDLINE; Public health; Actuarial science; Disease; Nursing; Statistics; Computer science; Psychology; Political science; Pathology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.687623,0.004179681,0.01864543,0.03048776,0.004879255,0.02159837,0.01124683,0.01122035,0.005945599],"category_scores_gemma":[0.8767912,0.008018568,0.01566136,0.03097816,0.01358403,0.02392183,0.01225469,0.008031208,0.001462708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02905486,"about_ca_system_score_gemma":0.07290556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01154245,"about_ca_topic_score_gemma":0.02250948,"domain_scores_codex":[0.1509295,0.4595954,0.3056606,0.01696754,0.06448695,0.00236004],"domain_scores_gemma":[0.0475295,0.8261469,0.06019605,0.01697097,0.04769496,0.001461726],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0006503739,0.00005235976,0.003797723,0.8900244,0.01682164,0.0002393973,0.00384162,0.0004824649,0.0002896776,0.006375814,0.007356908,0.07006765],"study_design_scores_gemma":[0.0007884637,0.0002088099,0.002526901,0.942392,0.01832948,0.0002970583,0.001370267,0.0007242426,0.0004721252,0.01089347,0.02180415,0.0001930177],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004786426,0.8911731,0.0336941,0.03653074,0.005952206,0.02220174,0.002246839,0.0002554657,0.003159365],"genre_scores_gemma":[0.2004909,0.4375944,0.1799448,0.03690663,0.004332734,0.1366784,0.002310138,0.0005547398,0.001187158],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.312377,"threshold_uncertainty_score":0.3852165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9416824309756451,"score_gpt":0.8249776248102781,"score_spread":0.1167048061653669,"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."}}