{"id":"W4415771544","doi":"10.21203/rs.3.rs-7794878/v1","title":"Large Language Models for Large-Scale, Rigorous Qualitative Analysis in Applied Health Services Research","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Impact","funders":"","keywords":"Qualitative research; Qualitative analysis; Coding (social sciences); Health care; Qualitative comparative analysis; Qualitative property; Work (physics)","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":[0.2115753,0.002054185,0.003841933,0.002891043,0.003579638,0.008765467,0.006970615,0.003924775,0.0219005],"category_scores_gemma":[0.5380386,0.003513715,0.005006533,0.004338745,0.009810507,0.01315016,0.01403923,0.01250836,0.003937165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009053835,"about_ca_system_score_gemma":0.0174581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008151393,"about_ca_topic_score_gemma":0.01391321,"domain_scores_codex":[0.7187921,0.2589246,0.005955734,0.006851557,0.008490843,0.0009851725],"domain_scores_gemma":[0.1788477,0.7809936,0.006226456,0.0265252,0.005948033,0.001459086],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004053792,0.0002445159,0.001925393,0.001588906,0.0005368165,0.0001401478,0.004622257,0.03666499,0.0004954335,0.8756723,0.009500442,0.0682034],"study_design_scores_gemma":[0.000200574,0.0000513808,0.0002565828,0.000365039,0.00009583291,0.00003648987,0.000492657,0.1705016,0.0003088101,0.8206888,0.006957729,0.00004450635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001058543,0.0001704386,0.9939879,0.001825999,0.0001047907,0.0007058777,0.000355962,0.0004211136,0.001369384],"genre_scores_gemma":[0.06189616,0.0002127729,0.9249274,0.0008390546,0.0001453359,0.009726969,0.0007366217,0.0004070827,0.001108547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7884247,"threshold_uncertainty_score":0.972268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5905499480820336,"score_gpt":0.760164354254545,"score_spread":0.1696144061725113,"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."}}