{"id":"W4403394070","doi":"10.2196/63466","title":"Identifying Patient-Reported Care Experiences in Free-Text Survey Comments: Topic Modeling Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services; Canadian Patient Safety Institute; University of Calgary","funders":"","keywords":"Preprint; Health care; Context (archaeology); Text messaging; Identification (biology); Computer science; Patient experience; Topic model; MEDLINE; Data science; Medicine; Psychology; Natural language processing; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01405926,0.0005490595,0.0004234794,0.003148564,0.0006287007,0.001791164,0.0007215803,0.0007695272,0.001401979],"category_scores_gemma":[0.05755879,0.0003239077,0.001049109,0.002486426,0.00059467,0.002086853,0.001240687,0.0008966847,0.0005753417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314959,"about_ca_system_score_gemma":0.001010917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003526495,"about_ca_topic_score_gemma":0.004075095,"domain_scores_codex":[0.9924959,0.004721396,0.0006521988,0.001033189,0.0007466213,0.0003508003],"domain_scores_gemma":[0.9000517,0.08340994,0.007241469,0.002499483,0.005942706,0.0008546164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008417857,0.00102316,0.8287363,0.0006616684,0.000243188,0.0003291407,0.08443134,0.003279582,0.003176111,0.0009051283,0.003091299,0.07328128],"study_design_scores_gemma":[0.00008838471,0.0009267272,0.7672739,0.0004287647,0.0002879554,0.0008124413,0.07059945,0.145344,0.00409352,0.001910595,0.008070011,0.0001642461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837224,0.0000861132,0.01322428,0.0001809846,0.00001617644,0.0005213512,0.001372218,0.0000712847,0.0008053143],"genre_scores_gemma":[0.9884557,0.00008560082,0.008406816,0.00007149563,0.00003499808,0.0006610175,0.001868951,0.00002488908,0.0003905668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01405926,"threshold_uncertainty_score":0.07435334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1815882162657952,"score_gpt":0.494137599829847,"score_spread":0.3125493835640518,"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."}}