دورية أكاديمية
Machine Learning of Plasma Proteomics Classifies Diagnosis of Interstitial Lung Disease.
العنوان: | Machine Learning of Plasma Proteomics Classifies Diagnosis of Interstitial Lung Disease. |
---|---|
المؤلفون: | Huang Y; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Ma SF; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Oldham JM; Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan., Adegunsoye A; Section of Pulmonary and Critical Care Medicine, University of Chicago, Chicago, Illinois., Zhu D; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Murray S; Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan., Kim JS; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Bonham C; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Strickland E; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Linderholm AL; Division of Pulmonary, Critical Care and Sleep Medicine, University of California, Davis, Davis, California., Lee CT; Section of Pulmonary and Critical Care Medicine, University of Chicago, Chicago, Illinois., Paul T; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Mannem H; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia., Maher TM; National Heart and Lung Institute, Imperial College, London, United Kingdom.; Keck Medicine of the University of Southern California, Los Angeles, California; and., Molyneaux PL; National Heart and Lung Institute, Imperial College, London, United Kingdom., Strek ME; Section of Pulmonary and Critical Care Medicine, University of Chicago, Chicago, Illinois., Martinez FJ; Weill Cornell Medical Center, New York, New York., Noth I; Division of Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, Virginia. |
المصدر: | American journal of respiratory and critical care medicine [Am J Respir Crit Care Med] 2024 Aug 15; Vol. 210 (4), pp. 444-454. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: American Thoracic Society Country of Publication: United States NLM ID: 9421642 Publication Model: Print Cited Medium: Internet ISSN: 1535-4970 (Electronic) Linking ISSN: 1073449X NLM ISO Abbreviation: Am J Respir Crit Care Med Subsets: MEDLINE |
أسماء مطبوعة: | Publication: 2000- : New York, NY : American Thoracic Society Original Publication: New York, NY : American Lung Association, c1994- |
مواضيع طبية MeSH: | Machine Learning* , Lung Diseases, Interstitial*/blood , Lung Diseases, Interstitial*/diagnosis , Proteomics*/methods, Humans ; Female ; Male ; Middle Aged ; Aged ; Idiopathic Pulmonary Fibrosis/blood ; Idiopathic Pulmonary Fibrosis/diagnosis ; Diagnosis, Differential ; Connective Tissue Diseases/blood ; Connective Tissue Diseases/diagnosis ; Biomarkers/blood |
مستخلص: | Rationale: Distinguishing connective tissue disease-associated interstitial lung disease (CTD-ILD) from idiopathic pulmonary fibrosis (IPF) can be clinically challenging. Objectives: To identify proteins that separate and classify patients with CTD-ILD and those with IPF. Methods: Four registries with 1,247 patients with IPF and 352 patients with CTD-ILD were included in analyses. Plasma samples were subjected to high-throughput proteomics assays. Protein features were prioritized using recursive feature elimination to construct a proteomic classifier. Multiple machine learning models, including support vector machine, LASSO (least absolute shrinkage and selection operator) regression, random forest, and imbalanced Random Forest, were trained and tested in independent cohorts. The validated models were used to classify each case iteratively in external datasets. Measurements and Main Results: A classifier with 37 proteins (proteomic classifier 37 [PC37]) was enriched in the biological process of bronchiole development and smooth muscle proliferation and immune responses. Four machine learning models used PC37 with sex and age score to generate continuous classification values. Receiver operating characteristic curve analyses of these scores demonstrated consistent areas under the curve of 0.85-0.90 in the test cohort and 0.94-0.96 in the single-sample dataset. Binary classification demonstrated 78.6-80.4% sensitivity and 76-84.4% specificity in the test cohort and 93.5-96.1% sensitivity and 69.5-77.6% specificity in the single-sample classification dataset. Composite analysis of all machine learning models confirmed 78.2% (194 of 248) accuracy in the test cohort and 82.9% (208 of 251) in the single-sample classification dataset. Conclusions: Multiple machine learning models trained with large cohort proteomic datasets consistently distinguished CTD-ILD from IPF. Many of the identified proteins are involved in immune pathways. We further developed a novel approach for single-sample classification, which could facilitate honing the differential diagnosis of ILD in challenging cases and improve clinical decision making. |
التعليقات: | Comment in: Am J Respir Crit Care Med. 2024 Aug 15;210(4):378-380. doi: 10.1164/rccm.202403-0603ED. (PMID: 38593003) |
معلومات مُعتمدة: | R01 HL166290 United States HL NHLBI NIH HHS; R01 HL169166 United States HL NHLBI NIH HHS; K23HL138190 United States HL NHLBI NIH HHS; K23HL150301 United States HL NHLBI NIH HHS; K23HL146942 United States HL NHLBI NIH HHS; T32HL007605 United States HL NHLBI NIH HHS; R01HL130796 United States HL NHLBI NIH HHS; UG3HL145266 United States HL NHLBI NIH HHS |
فهرسة مساهمة: | Keywords: connective tissue disease with ILD; differential diagnosis; idiopathic pulmonary fibrosis; machine learning model; plasma proteomics |
المشرفين على المادة: | 0 (Biomarkers) |
تواريخ الأحداث: | Date Created: 20240229 Date Completed: 20240815 Latest Revision: 20240815 |
رمز التحديث: | 20240815 |
DOI: | 10.1164/rccm.202309-1692OC |
PMID: | 38422478 |
قاعدة البيانات: | MEDLINE |
تدمد: | 1535-4970 |
---|---|
DOI: | 10.1164/rccm.202309-1692OC |