1
|
Chen TT, Cheng TY, Liu IJ, Ho SC, Lee KY, Huang HT, Feng PH, Chen KY, Luo CS, Tseng CH, Chen YH, Majumdar A, Tsai CY, Wu SM. Leveraging Subjective Parameters and Biomarkers in Machine Learning Models: The Feasibility of lnc-IL7R for Managing Emphysema Progression. Diagnostics (Basel) 2025; 15:1165. [PMID: 40361983 PMCID: PMC12071574 DOI: 10.3390/diagnostics15091165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2025] [Revised: 04/24/2025] [Accepted: 05/01/2025] [Indexed: 05/15/2025] Open
Abstract
Background/Objectives: Chronic obstructive pulmonary disease (COPD) remains a leading cause of death worldwide, with emphysema progression providing valuable insights into disease development. Clinical assessment approaches, including pulmonary function tests and high-resolution computed tomography, are limited by accessibility constraints and radiation exposure. This study, therefore, proposed an alternative approach by integrating the novel biomarker long non-coding interleukin-7 receptor α-subunit gene (lnc-Il7R), along with other easily accessible clinical and biochemical metrics, into machine learning (ML) models. Methods: This cohort study collected baseline characteristics, COPD Assessment Test (CAT) scores, and biochemical details from the enrolled participants. Associations with emphysema severity, defined by a low attenuation area percentage (LAA%) threshold of 15%, were evaluated using simple and multivariate-adjusted models. The dataset was then split into training and validation (80%) and test (20%) subsets. Five ML models were employed, with the best-performing model being further analyzed for feature importance. Results: The majority of participants were elderly males. Compared to the LAA% <15% group, the LAA% ≥15% group demonstrated a significantly higher body mass index (BMI), poor pulmonary function, and lower expression levels of lnc-Il7R (all p < 0.01). Fold changes in lnc-IL7R were strongly and negatively associated with LAA% (p < 0.01). The random forest (RF) model achieved the highest accuracy and area under the receiver operating characteristic curve (AUROC) across datasets. A feature importance analysis identified lnc-IL7R fold changes as the strongest predictor for emphysema classification (LAA% ≥15%), followed by CAT scores and BMI. Conclusions: Machine learning models incorporated accessible clinical and biochemical markers, particularly the novel biomarker lnc-IL7R, achieving classification accuracy and AUROC exceeding 75% in emphysema assessments. These findings offer promising opportunities for improving emphysema classification and COPD management.
Collapse
Affiliation(s)
- Tzu-Tao Chen
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
- Graduate Institute of Clinical Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Tzu-Yu Cheng
- Division of Cardiovascular Surgery, Department of Surgery, Wan Fang Hospital, Taipei Medical University, Taipei 11696, Taiwan
- Division of Cardiology, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- Cardiovascular Research Center, Wan Fang Hospital, Taipei Medical University, Taipei 11696, Taiwan
| | - I-Jung Liu
- Research Center of Sleep Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Shu-Chuan Ho
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
- School of Respiratory Therapy, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Kang-Yun Lee
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
- Graduate Institute of Clinical Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Huei-Tyng Huang
- Centre for Immunobiology, Blizard Institute, Queen Mary University of London, London WC1E 6BT, UK
| | - Po-Hao Feng
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Kuan-Yuan Chen
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
- Graduate Institute of Clinical Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Ching-Shan Luo
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
- International PhD Program for Cell Therapy and Regeneration Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Chien-Hua Tseng
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Yueh-His Chen
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
| | - Arnab Majumdar
- Department of Civil and Environmental Engineering, Imperial College London, London SW7 2AZ, UK
| | - Cheng-Yu Tsai
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
- Department of Civil and Environmental Engineering, Imperial College London, London SW7 2AZ, UK
- School of Biomedical Engineering, College of Biomedical Engineering, Taipei Medical University, 250 Wuxing Street, Taipei 11031, Taiwan
| | - Sheng-Ming Wu
- Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 23561, Taiwan
- Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
- TMU Research Center for Thoracic Medicine, Taipei Medical University, Taipei 11031, Taiwan
| |
Collapse
|
3
|
Dournes G, Walkup LL, Benlala I, Willmering MM, Macey J, Bui S, Laurent F, Woods JC. The Clinical Use of Lung MRI in Cystic Fibrosis: What, Now, How? Chest 2020; 159:2205-2217. [PMID: 33345950 PMCID: PMC8579315 DOI: 10.1016/j.chest.2020.12.008] [Citation(s) in RCA: 22] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2020] [Revised: 11/24/2020] [Accepted: 12/03/2020] [Indexed: 12/19/2022] Open
Abstract
To assess airway and lung parenchymal damage noninvasively in cystic fibrosis (CF), chest MRI has been historically out of the scope of routine clinical imaging because of technical difficulties such as low proton density and respiratory and cardiac motion. However, technological breakthroughs have emerged that dramatically improve lung MRI quality (including signal-to-noise ratio, resolution, speed, and contrast). At the same time, novel treatments have changed the landscape of CF clinical care. In this contemporary context, there is now consensus that lung MRI can be used clinically to assess CF in a radiation-free manner and to enable quantification of lung disease severity. MRI can now achieve three-dimensional, high-resolution morphologic imaging, and beyond this morphologic information, MRI may offer the ability to sensitively differentiate active inflammation vs scarring tissue. MRI could also characterize various forms of inflammation for early guidance of treatment. Moreover, functional information from MRI can be used to assess regional, small-airway disease with sensitivity to detect small changes even in patients with mild CF. Finally, automated quantification methods have emerged to support conventional visual analyses for more objective and reproducible assessment of disease severity. This article aims to review the most recent developments of lung MRI, with a focus on practical application and clinical value in CF, and the perspectives on how these modern techniques may converge and impact patient care soon.
Collapse
Affiliation(s)
- Gaël Dournes
- University of Bordeaux, Centre de Recherche Cardio-Thoracique de Bordeaux, U1045, CIC 1401, Bordeaux, France; INSERM, Centre de Recherche Cardio-Thoracique de Bordeaux, U1045, CIC 1401, Bordeaux, France; CHU de Bordeaux, Service d'Imagerie Thoracique et Cardiovasculaire, Service des Maladies Respiratoires, Service d'Exploration Fonctionnelle Respiratoire, CIC 1401, Pessac, France; Center for Pulmonary Imaging Research, Division of Pulmonary Medicine and Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH.
| | - Laura L Walkup
- Center for Pulmonary Imaging Research, Division of Pulmonary Medicine and Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH; Department of Pediatrics, College of Medicine, University of Cincinnati, Cincinnati, OH
| | - Ilyes Benlala
- University of Bordeaux, Centre de Recherche Cardio-Thoracique de Bordeaux, U1045, CIC 1401, Bordeaux, France; INSERM, Centre de Recherche Cardio-Thoracique de Bordeaux, U1045, CIC 1401, Bordeaux, France; CHU de Bordeaux, Service d'Imagerie Thoracique et Cardiovasculaire, Service des Maladies Respiratoires, Service d'Exploration Fonctionnelle Respiratoire, CIC 1401, Pessac, France
| | - Matthew M Willmering
- Center for Pulmonary Imaging Research, Division of Pulmonary Medicine and Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH
| | - Julie Macey
- CHU de Bordeaux, Service d'Imagerie Thoracique et Cardiovasculaire, Service des Maladies Respiratoires, Service d'Exploration Fonctionnelle Respiratoire, CIC 1401, Pessac, France
| | - Stephanie Bui
- CHU Bordeaux, Hôpital Pellegrin-Enfants, Pediatric Cystic Fibrosis Reference Center (CRCM), Centre d'Investigation Clinique (CIC 1401), Bordeaux, France
| | - François Laurent
- University of Bordeaux, Centre de Recherche Cardio-Thoracique de Bordeaux, U1045, CIC 1401, Bordeaux, France; INSERM, Centre de Recherche Cardio-Thoracique de Bordeaux, U1045, CIC 1401, Bordeaux, France; CHU de Bordeaux, Service d'Imagerie Thoracique et Cardiovasculaire, Service des Maladies Respiratoires, Service d'Exploration Fonctionnelle Respiratoire, CIC 1401, Pessac, France
| | - Jason C Woods
- Center for Pulmonary Imaging Research, Division of Pulmonary Medicine and Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH; Department of Pediatrics, College of Medicine, University of Cincinnati, Cincinnati, OH
| |
Collapse
|
6
|
Vult von Steyern K, Björkman-Burtscher IM, Geijer M. Radiography, tomosynthesis, CT and MRI in the evaluation of pulmonary cystic fibrosis: an untangling review of the multitude of scoring systems. Insights Imaging 2013; 4:787-98. [PMID: 24065629 PMCID: PMC3846934 DOI: 10.1007/s13244-013-0288-y] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2013] [Revised: 07/04/2013] [Accepted: 09/02/2013] [Indexed: 02/03/2023] Open
Abstract
Objective The first radiographic scoring system for pulmonary cystic fibrosis was presented in 1958. Since then a multitude of scoring systems for radiography and computed tomography (CT) have been presented, recently also for tomosynthesis and magnetic resonance imaging (MRI). The aim of the current review was to analyse and compare the plethora of scoring systems for cystic fibrosis, especially regarding which scoring components are considered most important. Methods Four scoring systems for chest radiography, one for tomosynthesis, eight for CT and one for MRI were compared regarding components evaluated and their terminology; the areas scored; scoring levels; the weighting of each component in percentage of the total score; and the calculations for the final score. Results In most radiological scoring systems the lungs are evaluated for increased volume, bronchial wall thickening, bronchiectasis, mucus plugging, atelectasis and consolidation. In addition, for instance abscesses, bullae, septal thickening, mosaic perfusion, ground glass opacities and air trapping are evaluated in some CT scoring systems. Pleural affection and perfusion defects are scored on MRI. Conclusions Bronchiectasis alone, or in combination with mucus plugging, is given the highest weighting in most scoring systems and is thus commonly considered to be the most significant finding when evaluating cystic fibrosis lung disease. Teaching points
Scoring of examinations is used for comparison of outcome in studies. Scoring of examinations can also be used for monitoring disease progression. Cystic fibrosis can be scored on radiography, tomosynthesis, CT or MRI. The typical imaging findings of cystic fibrosis depend on the imaging modality used. Bronchiectasis is commonly considered the most significant finding when scoring cystic fibrosis.
Collapse
Affiliation(s)
- Kristina Vult von Steyern
- Center for Medical Imaging and Physiology, Skåne University Hospital, Lund, Lund University, 221 85, Lund, Sweden,
| | | | | |
Collapse
|