{"id":"W3124915543","doi":"10.1101/2021.01.21.21250243","title":"Problems with Evidence Assessment in COVID-19 Health Policy Impact Evaluation: A systematic review of study design and evidence strength","year":2021,"lang":"en","type":"review","venue":"medRxiv","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse; Knut och Alice Wallenbergs Stiftelse; National Institutes of Health; Laura and John Arnold Foundation","keywords":"Impact assessment; Coronavirus disease 2019 (COVID-19); Health impact assessment; Impact factor; Systematic review; Actuarial science; Sample (material); Medicine; Set (abstract data type); MEDLINE; Psychology; Computer science; Political science; Business; Public health; Nursing; Disease","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":[0.6592028,0.003776421,0.01703675,0.02996075,0.004311356,0.01880643,0.009575634,0.009460688,0.005613825],"category_scores_gemma":[0.8655229,0.007033742,0.01482733,0.0293277,0.01230935,0.02135875,0.01114586,0.007237559,0.001216257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02707768,"about_ca_system_score_gemma":0.07600185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01174073,"about_ca_topic_score_gemma":0.02245082,"domain_scores_codex":[0.1808481,0.4567625,0.2837062,0.01640068,0.05998936,0.00229317],"domain_scores_gemma":[0.05405364,0.8254498,0.05860294,0.01722274,0.04326281,0.001408017],"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":[0.000555722,0.00005163049,0.004126346,0.8827905,0.01731319,0.0002357163,0.003567557,0.000487521,0.0002336579,0.0063645,0.005983613,0.07829013],"study_design_scores_gemma":[0.0005841581,0.0001826246,0.002144162,0.9481086,0.0176022,0.0002519943,0.001214665,0.0005948207,0.0003903041,0.008804921,0.01996375,0.0001578308],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004269486,0.9084941,0.02929357,0.02758449,0.00457623,0.02077961,0.001984027,0.000211657,0.002806896],"genre_scores_gemma":[0.1911561,0.4850093,0.1676162,0.03083207,0.003257139,0.1186742,0.002080571,0.0004453741,0.0009289887],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3407972,"threshold_uncertainty_score":0.4202637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8374160443260061,"score_gpt":0.7610109532821004,"score_spread":0.07640509104390569,"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."}}