Deep learning prediction of hospital readmissions for asthma and COPD
Authors:
Open Access
- 13 December 2023
- journal article
- research article
- Published by Springer Nature in Respiratory Research
- Vol. 24 (1) , 1-11
Abstract
Question: Severe asthma and COPD exacerbations requiring hospitalization are linked to increased disease morbidity and healthcare costs. We sought to identify Electronic Health Record (EHR) features of severe asthma and COPD exacerbations and evaluate the performance of four machine learning (ML) and one deep learning (DL) model in predicting readmissions using EHR data. Study design and methods: Observational study between September 30, 2012, and December 31, 2017, of patients hospitalized with asthma and COPD exacerbations. Results: This study included 5,794 patients, 1,893 with asthma and 3,901 with COPD. Patients with asthma were predominantly female (n = 1288 [68%]), 35% were Black (n = 669), and 25% (n = 479) were Hispanic. Black (44 vs. 33%, p = 0.01) and Hispanic patients (30 vs. 24%, p = 0.02) were more likely to be readmitted for asthma. Similarly, patients with COPD readmissions included a large percentage of Blacks (18 vs. 10%, p < 0.01) and Hispanics (8 vs. 5%, p < 0.01). To identify patients at high risk of readmission index hospitalization data of a subset of 2,682 patients, 777 with asthma and 1,905 with COPD, was analyzed with four ML models, and one DL model. We found that multilayer perceptron, the DL method, had the best sensitivity and specificity compared to the four ML methods implemented in the same dataset. Interpretation: Multilayer perceptron, a deep learning method, had the best performance in predicting asthma and COPD readmissions, demonstrating that EHR and deep learning integration can improve high-risk patient detection.Keywords
Funding Information
- National Heart, Lung, and Blood Institute (2T32HL007778-26, 21-004125, R01 HL153604)
- National Institute of Diabetes and Digestive and Kidney Diseases (P30 DK079310)
- National Institutes of Health (R01 HS027626)
This publication has 29 references indexed in Scilit:
- The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced DatasetsPLOS ONE, 2015
- Total and State-Specific Medical and Absenteeism Costs of COPD Among Adults Aged 18 Years in the United States for 2010 and Projections Through 2020Chest, 2015
- Prognostic value of cluster analysis of severe asthma phenotypesJournal of Allergy and Clinical Immunology, 2014
- Unsupervised phenotyping of Severe Asthma Research Program participants using expanded lung dataJournal of Allergy and Clinical Immunology, 2014
- Cluster analysis in the COPDGene study identifies subtypes of smokers with distinct patterns of airway disease and emphysemaThorax, 2014
- A Randomized Study of Endobronchial Valves for Advanced EmphysemaNew England Journal of Medicine, 2010
- Identification of Asthma Phenotypes Using Cluster Analysis in the Severe Asthma Research ProgramAmerican Journal of Respiratory and Critical Care Medicine, 2010
- Mepolizumab and Exacerbations of Refractory Eosinophilic AsthmaNew England Journal of Medicine, 2009
- Endotyping asthma: new insights into key pathogenic mechanisms in a complex, heterogeneous diseaseThe Lancet, 2008
- The R Project in Statistical ComputingMSOR Connections, 2001