{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1699126,0.0006326727,0.005829286,0.0008690415,0.000963998,0.0001146185,0.002221172,0.0001215351,0.001623516],"category_scores_gemma":[0.05207091,0.0003829237,0.000144094,0.004201718,0.0001003197,0.001077269,0.001617111,0.001346146,0.00002859722],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.01055089,"about_ca_system_score_gemma":0.2225737,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02346545,"about_ca_topic_score_gemma":0.003073019,"domain_scores_codex":[0.8790593,0.1055012,0.008514889,0.001491712,0.004084853,0.001348032],"domain_scores_gemma":[0.9534623,0.0324291,0.01025991,0.002313233,0.0005053182,0.001030124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002336093,0.00009866325,0.0004000652,0.9778139,0.00007989605,0.000006484805,0.006213127,0.00002589797,3.919424e-9,0.0000400834,0.001882879,0.01341563],"study_design_scores_gemma":[0.0009976759,0.00188268,0.0001787898,0.9720286,0.0006523277,0.00004200921,0.003155352,0.00008888502,1.030586e-9,0.00002493403,0.02058308,0.0003656503],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001472134,0.724117,0.00030075,0.00852018,0.00006228729,0.2668561,0.00006748189,0.00002098444,0.00005371749],"genre_scores_gemma":[0.00003587806,0.8286703,0.001134594,0.009453883,0.00004899115,0.1604921,0.00002122874,0.00005041834,0.00009256352],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2120228,"threshold_uncertainty_score":0.9998623,"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."}}