{"id":"W4400918589","doi":"10.2196/54653","title":"Accelerating Evidence Synthesis in Observational Studies: Development of a Living Natural Language Processing–Assisted Intelligent Systematic Literature Review System","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Systematic review; Observational study; Machine learning; Data extraction; Artificial intelligence; Natural language processing; MEDLINE; Medicine","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"],"consensus_categories":[],"category_scores_codex":[0.00167772,0.0001776746,0.0004769196,0.00009408432,0.00005080175,0.00005434581,0.0003091227,0.0002010105,0.000008634229],"category_scores_gemma":[0.008878232,0.0001169709,0.00008072017,0.0004357737,0.00009656057,0.00002252597,0.0001895297,0.000271311,0.000005722694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008428538,"about_ca_system_score_gemma":0.0004463398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.055316e-7,"about_ca_topic_score_gemma":0.00001116714,"domain_scores_codex":[0.9976482,0.0001165453,0.001273079,0.0001526053,0.0006033461,0.0002062304],"domain_scores_gemma":[0.9986384,0.0007032214,0.0002305963,0.0001836913,0.000159114,0.00008497893],"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":[0.000009209001,0.00005533907,0.0001426681,0.8480246,0.0001827816,0.00004486241,0.02014605,0.000001478949,0.0005876416,0.00004750411,0.00126275,0.1294951],"study_design_scores_gemma":[0.00003880666,0.00004135269,0.0002278276,0.9735275,0.00004765361,0.0001173212,0.01279001,0.01181688,0.0008226106,4.510989e-7,0.0003807922,0.0001887866],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1431756,0.8528495,0.002195196,0.0003387774,0.0003518321,0.0008347075,0.000005946403,0.0001082535,0.0001402556],"genre_scores_gemma":[0.9778051,0.008237924,0.01289482,0.0004138268,0.0000979545,0.0004197996,0.00002439224,0.00001356588,0.00009261831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8446115,"threshold_uncertainty_score":0.9994704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08055717155902066,"score_gpt":0.3848893639462279,"score_spread":0.3043321923872072,"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."}}