{"id":"W4396500878","doi":"10.1164/ajrccm-conference.2024.209.1_meetingabstracts.a5089","title":"Using Latent Class Analysis to Predict Outcomes and Inform Disease Classification in Fibrotic Interstitial Lung Disease","year":2024,"lang":"en","type":"article","venue":"","topic":"Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of Saskatchewan; Université de Montréal; University of Toronto; McMaster University; University of British Columbia","funders":"","keywords":"Disease; Interstitial lung disease; Computer science; Class (philosophy); Artificial intelligence; Latent class model; Medicine; Lung; Natural language processing; Pathology; Machine learning; Internal medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.008299428,0.0006052422,0.0007662186,0.002340807,0.0006734969,0.00262433,0.0005543045,0.0009732613,0.001519882],"category_scores_gemma":[0.02155275,0.0002110587,0.001012891,0.000884898,0.0006771116,0.001425538,0.001306633,0.001990324,0.0003885472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005501636,"about_ca_system_score_gemma":0.0008130035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002033714,"about_ca_topic_score_gemma":0.003014521,"domain_scores_codex":[0.9964449,0.002402931,0.0002332622,0.0003607585,0.0003322474,0.000225927],"domain_scores_gemma":[0.9797446,0.01596083,0.002100148,0.0009906256,0.0007334144,0.0004702887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001448828,0.0008243717,0.875984,0.00008688885,0.0005251093,0.0001023395,0.0003901423,0.01317994,0.0009729728,0.002636001,0.002404152,0.1014452],"study_design_scores_gemma":[0.0002393316,0.0007042972,0.3558863,0.0002198766,0.000552219,0.0002823706,0.001141705,0.5882848,0.002076759,0.04832659,0.002144249,0.0001415974],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9255379,0.001005036,0.06780594,0.001649393,0.0001728306,0.00008957658,0.001460145,0.0002043226,0.002074901],"genre_scores_gemma":[0.991559,0.0001134443,0.007164815,0.00006599363,0.00007119666,0.00004355282,0.0006907698,0.00001750789,0.0002737996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008299428,"threshold_uncertainty_score":0.04389209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0295974489011168,"score_gpt":0.3231897698178489,"score_spread":0.2935923209167321,"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."}}