{"id":"W4405751905","doi":"10.1016/j.jval.2024.10.2064","title":"HTA239 Streamlining Systematic Review Feasibility Assessments With Large Language Models: A Novel AI-Driven Workflow","year":2024,"lang":"en","type":"article","venue":"Value in Health","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"EVERSANA (Canada)","funders":"","keywords":"Workflow; Computer science; Software engineering; Systems engineering; Data science; Engineering; Database","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":[],"category_scores_codex":[0.161696,0.002513178,0.004068694,0.01299982,0.002004866,0.01201562,0.00489022,0.00287015,0.03324438],"category_scores_gemma":[0.5082268,0.002553169,0.008990333,0.009014928,0.001391769,0.006723117,0.008185115,0.003714306,0.006065549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003928395,"about_ca_system_score_gemma":0.03971595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01103574,"about_ca_topic_score_gemma":0.03164561,"domain_scores_codex":[0.8927729,0.07405519,0.01861045,0.007167975,0.006736926,0.0006566171],"domain_scores_gemma":[0.4352469,0.4816928,0.02053146,0.03482643,0.02365792,0.00404449],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00738832,0.0005943848,0.009296466,0.07493359,0.01632808,0.0006781313,0.005903431,0.01925219,0.005077591,0.03244838,0.1271124,0.700987],"study_design_scores_gemma":[0.01655474,0.001640811,0.008255322,0.02373328,0.02931621,0.0008576027,0.002206638,0.3066753,0.01133203,0.3120314,0.2862864,0.001110275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01667105,0.01133251,0.7678547,0.02511179,0.002076394,0.03773545,0.0746085,0.05080781,0.01380181],"genre_scores_gemma":[0.03511425,0.0007492196,0.9398445,0.001294411,0.0002229923,0.01242186,0.008282112,0.0009932469,0.001077456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.838304,"threshold_uncertainty_score":0.8551405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2667751677074912,"score_gpt":0.4961394386560821,"score_spread":0.2293642709485909,"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."}}