{"id":"W4389512251","doi":"10.1016/j.canep.2023.102511","title":"Evaluating the efficacy of artificial intelligence tools for the automation of systematic reviews in cancer research: A systematic review","year":2023,"lang":"en","type":"review","venue":"Cancer Epidemiology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; McMaster University; Impact; McMaster Children's Hospital","funders":"","keywords":"Medicine; Workload; Cochrane Library; Systematic review; MEDLINE; Automation; Artificial intelligence; Medical physics; Computer science; Meta-analysis; 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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06900086,0.000351877,0.007752726,0.0003292742,0.0001602548,0.00001016166,0.0007333484,0.0003588679,0.00006296878],"category_scores_gemma":[0.2698669,0.000164532,0.0009132872,0.001730577,0.0003824603,0.00005799044,0.00008362722,0.0008412051,0.00008312124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007135401,"about_ca_system_score_gemma":0.001775387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001376209,"about_ca_topic_score_gemma":0.0004217781,"domain_scores_codex":[0.9766365,0.01238397,0.0093216,0.0005763092,0.0004536705,0.0006279802],"domain_scores_gemma":[0.8284312,0.1633527,0.00533549,0.001598131,0.001191552,0.00009085267],"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":[0.00001387925,0.00002485964,0.00000159685,0.7009672,0.0001331319,2.353022e-7,0.0003572042,0.00004189486,4.679935e-7,0.0006480453,0.0004522581,0.2973592],"study_design_scores_gemma":[0.00001172835,0.0002096864,0.000002042995,0.9878236,0.004030335,0.000007993126,0.0004887573,0.003387197,0.000004032765,0.001266761,0.002649589,0.0001182846],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001035194,0.95397,0.0008827877,0.003159648,0.001085095,0.04083672,0.0000338268,0.00001770763,0.0000038829],"genre_scores_gemma":[0.00002396242,0.9503652,0.0002049766,0.0003906013,0.000512603,0.04831125,0.00003996516,0.00004411117,0.0001072837],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2972409,"threshold_uncertainty_score":0.9586595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9542690698920192,"score_gpt":0.7329447462817987,"score_spread":0.2213243236102205,"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."}}