1
|
Maldonado-Franco A, Giraldo-Cadavid LF, Tuta-Quintero E, Cagy M, Bastidas Goyes AR, Botero-Rosas DA. Curve-Modelling and Machine Learning for a Better COPD Diagnosis. Int J Chron Obstruct Pulmon Dis 2024; 19:1333-1343. [PMID: 38895045 PMCID: PMC11182754 DOI: 10.2147/copd.s456390] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2024] [Accepted: 05/20/2024] [Indexed: 06/21/2024] Open
Abstract
Background Development of new tools in artificial intelligence has an outstanding performance in the recognition of multidimensional patterns, which is why they have proven to be useful in the diagnosis of Chronic Obstructive Pulmonary Disease (COPD). Methods This was an observational analytical single-centre study in patients with spirometry performed in outpatient medical care. The segment that goes from the peak expiratory flow to the forced vital capacity was modelled with quadratic polynomials, the coefficients obtained were used to train and test neural networks in the task of classifying patients with COPD. Results A total of 695 patient records were included in the analysis. The COPD group was significantly older than the No COPD group. The pre-bronchodilator (Pre BD) and post-bronchodilator (Post BD) spirometric curves were modelled with a quadratic polynomial, and the coefficients obtained were used to feed three neural networks (Pre BD, Post BD and all coefficients). The best neural network was the one that used the post-bronchodilator coefficients, which has an input layer of 3 neurons and three hidden layers with sigmoid activation function and two neurons in the output layer with softmax activation function. This system had an accuracy of 92.9% accuracy, a sensitivity of 88.2% and a specificity of 94.3% when assessed using expert judgment as the reference test. It also showed better performance than the current gold standard, especially in specificity and negative predictive value. Conclusion Artificial Neural Networks fed with coefficients obtained from quadratic and cubic polynomials have interesting potential of emulating the clinical diagnostic process and can become an important aid in primary care to help diagnose COPD in an early stage.
Collapse
Affiliation(s)
| | - Luis F Giraldo-Cadavid
- School of Medicine, Universidad de La Sabana, Chía, Colombia
- Interventional Pulmonology Service, Fundación Neumológica Colombiana, Bogotá, DC, Colombia
| | | | - Mauricio Cagy
- Biomedical Engineering Program, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brasil
| | | | | |
Collapse
|
2
|
Maldonado-Franco A, Giraldo-Cadavid LF, Tuta-Quintero E, Bastidas Goyes AR, Botero-Rosas DA. The Challenges of Spirometric Diagnosis of COPD. Can Respir J 2023; 2023:6991493. [PMID: 37808623 PMCID: PMC10558269 DOI: 10.1155/2023/6991493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Revised: 03/09/2023] [Accepted: 03/28/2023] [Indexed: 10/10/2023] Open
Abstract
Chronic obstructive pulmonary disease (COPD) is one of the top causes of morbidity and mortality worldwide. Although for many years its accurate diagnosis has been a focus of intense research, it is still challenging. Due to its simplicity, portability, and low cost, spirometry has been established as the main tool to detect this condition, but its flawed performance makes it an imperfect COPD diagnosis gold standard. This review aims to provide an up-to-date literature overview of recent studies regarding COPD diagnosis; we seek to identify their limitations and establish perspectives for spirometric diagnosis of COPD in the XXI century by combining deep clinical knowledge of the disease with advanced computer analysis techniques.
Collapse
Affiliation(s)
| | - Luis F. Giraldo-Cadavid
- Departments of Epidemiology and Internal Medicine, School of Medicine, Universidad de La Sabana, Chía, Colombia
- Director of Interventional Pulmonology Service, Fundación Neumológica Colombiana, Bogotá, Colombia
| | - Eduardo Tuta-Quintero
- Candidate for Master's Degree in Epidemiology, Universidad de La Sabana, Chía, Colombia
| | | | | |
Collapse
|
3
|
Kurian V, Ghadipasha N, Gee M, Chalant A, Hamill T, Okossi A, Chen L, Yu B, Ogunnaike BA, Beris AN. Systems Engineering Approach to Modeling and Analysis of Chronic Obstructive Pulmonary Disease. ACS OMEGA 2023; 8:20524-20535. [PMID: 37332794 PMCID: PMC10268641 DOI: 10.1021/acsomega.3c00854] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Accepted: 05/15/2023] [Indexed: 06/20/2023]
Abstract
Chronic obstructive pulmonary disease (COPD) is a progressive lung disease characterized by airflow limitation. This study develops a systems engineering framework for representing important mechanistic details of COPD in a model of the cardiorespiratory system. In this model, we present the cardiorespiratory system as an integrated biological control system responsible for regulating breathing. Four engineering control system components are considered: sensor, controller, actuator, and the process itself. Knowledge of human anatomy and physiology is used to develop appropriate mechanistic mathematical models for each component. Following a systematic analysis of the computational model, we identify three physiological parameters associated with reproducing clinical manifestations of COPD: changes in the forced expiratory volume, lung volumes, and pulmonary hypertension. We quantify the changes in these parameters (airway resistance, lung elastance, and pulmonary resistance) as the ones that result in a systemic response that is diagnostic of COPD. A multivariate analysis of the simulation results reveals that the changes in airway resistance have a broad impact on the human cardiorespiratory system and that the pulmonary circuit is stressed beyond normal under hypoxic environments in most COPD patients.
Collapse
Affiliation(s)
- Varghese Kurian
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
| | - Navid Ghadipasha
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
| | - Michelle Gee
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
- Daniel
Baugh Institute of Functional Genomics/Computational Biology, Department
of Pathology and Genomic Medicine, Thomas
Jefferson University, Philadelphia, Pennsylvania 19107, United States
| | - Anais Chalant
- American
Air Liquide Inc., Innovation Campus Delaware, Newark, Delaware 19702, United States
| | - Teresa Hamill
- American
Air Liquide Inc., Innovation Campus Delaware, Newark, Delaware 19702, United States
| | - Alphonse Okossi
- American
Air Liquide Inc., Innovation Campus Delaware, Newark, Delaware 19702, United States
| | - Lucy Chen
- American
Air Liquide Inc., Innovation Campus Delaware, Newark, Delaware 19702, United States
| | - Bin Yu
- American
Air Liquide Inc., Innovation Campus Delaware, Newark, Delaware 19702, United States
| | - Babatunde A. Ogunnaike
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
| | - Antony N. Beris
- Department
of Chemical and Biomolecular Engineering, University of Delaware, Newark, Delaware 19716, United States
| |
Collapse
|
4
|
Verstraete K, Das N, Gyselinck I, Topalovic M, Troosters T, Crapo JD, Silverman EK, Make BJ, Regan EA, Jensen R, De Vos M, Janssens W. Principal component analysis of flow-volume curves in COPDGene to link spirometry with phenotypes of COPD. Respir Res 2023; 24:20. [PMID: 36658542 PMCID: PMC9854102 DOI: 10.1186/s12931-023-02318-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2022] [Accepted: 01/06/2023] [Indexed: 01/20/2023] Open
Abstract
BACKGROUND Parameters from maximal expiratory flow-volume curves (MEFVC) have been linked to CT-based parameters of COPD. However, the association between MEFVC shape and phenotypes like emphysema, small airways disease (SAD) and bronchial wall thickening (BWT) has not been investigated. RESEARCH QUESTION We analyzed if the shape of MEFVC can be linked to CT-determined emphysema, SAD and BWT in a large cohort of COPDGene participants. STUDY DESIGN AND METHODS In the COPDGene cohort, we used principal component analysis (PCA) to extract patterns from MEFVC shape and performed multiple linear regression to assess the association of these patterns with CT parameters over the COPD spectrum, in mild and moderate-severe COPD. RESULTS Over the entire spectrum, in mild and moderate-severe COPD, principal components of MEFVC were important predictors for the continuous CT parameters. Their contribution to the prediction of emphysema diminished when classical pulmonary function test parameters were added. For SAD, the components remained very strong predictors. The adjusted R2 was higher in moderate-severe COPD, while in mild COPD, the adjusted R2 for all CT outcomes was low; 0.28 for emphysema, 0.21 for SAD and 0.19 for BWT. INTERPRETATION The shape of the maximal expiratory flow-volume curve as analyzed with PCA is not an appropriate screening tool for early disease phenotypes identified by CT scan. However, it contributes to assessing emphysema and SAD in moderate-severe COPD.
Collapse
Affiliation(s)
- Kenneth Verstraete
- grid.5596.f0000 0001 0668 7884Laboratory of Respiratory Diseases and Thoracic Surgery (BREATHE), Department of Chronic Diseases and Metabolism, KU Leuven, Herestraat 49, O&N 1Bis, Box 706, 3000 Leuven, Belgium ,grid.5596.f0000 0001 0668 7884STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium
| | - Nilakash Das
- grid.5596.f0000 0001 0668 7884Laboratory of Respiratory Diseases and Thoracic Surgery (BREATHE), Department of Chronic Diseases and Metabolism, KU Leuven, Herestraat 49, O&N 1Bis, Box 706, 3000 Leuven, Belgium
| | - Iwein Gyselinck
- grid.5596.f0000 0001 0668 7884Laboratory of Respiratory Diseases and Thoracic Surgery (BREATHE), Department of Chronic Diseases and Metabolism, KU Leuven, Herestraat 49, O&N 1Bis, Box 706, 3000 Leuven, Belgium
| | | | - Thierry Troosters
- grid.5596.f0000 0001 0668 7884Department of Rehabilitation Sciences, KU Leuven, Leuven, Belgium
| | - James D. Crapo
- grid.240341.00000 0004 0396 0728National Jewish Medical and Research Center, Denver, CO USA
| | - Edwin K. Silverman
- grid.38142.3c000000041936754XChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA USA
| | - Barry J. Make
- grid.240341.00000 0004 0396 0728National Jewish Medical and Research Center, Denver, CO USA
| | - Elizabeth A. Regan
- grid.240341.00000 0004 0396 0728National Jewish Medical and Research Center, Denver, CO USA
| | - Robert Jensen
- grid.223827.e0000 0001 2193 0096University of Utah, Salt Lake City, Utah USA
| | - Maarten De Vos
- grid.5596.f0000 0001 0668 7884STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium ,grid.5596.f0000 0001 0668 7884Department of Development and Regeneration, KU Leuven, Leuven, Belgium
| | - Wim Janssens
- grid.5596.f0000 0001 0668 7884Laboratory of Respiratory Diseases and Thoracic Surgery (BREATHE), Department of Chronic Diseases and Metabolism, KU Leuven, Herestraat 49, O&N 1Bis, Box 706, 3000 Leuven, Belgium
| |
Collapse
|
5
|
Kakavas S, Kotsiou OS, Perlikos F, Mermiri M, Mavrovounis G, Gourgoulianis K, Pantazopoulos I. Pulmonary function testing in COPD: looking beyond the curtain of FEV1. NPJ Prim Care Respir Med 2021; 31:23. [PMID: 33963190 PMCID: PMC8105397 DOI: 10.1038/s41533-021-00236-w] [Citation(s) in RCA: 31] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2020] [Accepted: 03/15/2021] [Indexed: 02/03/2023] Open
Abstract
Chronic obstructive pulmonary disease (COPD) management remains challenging due to the high heterogeneity of clinical symptoms and the complex pathophysiological basis of the disease. Airflow limitation, diagnosed by spirometry, remains the cornerstone of the diagnosis. However, the calculation of the forced expiratory volume in the first second (FEV1) alone, has limitations in uncovering the underlying complexity of the disease. Incorporating additional pulmonary function tests (PFTs) in the everyday clinical evaluation of COPD patients, like resting volume, capacity and airway resistance measurements, diffusion capacity measurements, forced oscillation technique, field and cardiopulmonary exercise testing and muscle strength evaluation, may prove essential in tailoring medical management to meet the needs of such a heterogeneous patient population. We aimed to provide a comprehensive overview of the available PFTs, which can be incorporated into the primary care physician's practice to enhance the efficiency of COPD management.
Collapse
Affiliation(s)
- Sotirios Kakavas
- Critical Care Department, Sismanogleio General Hospital, Athens, Greece
| | - Ourania S Kotsiou
- Department of Respiratory Medicine, University of Thessaly, School of Medicine, University General Hospital of Larisa, Thessaly, Greece
| | - Fotis Perlikos
- Department of Respiratory Medicine, Evangelismos General Hospital, Athens, Greece
| | - Maria Mermiri
- Department of Emergency Medicine, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larisa, Greece.
| | - Georgios Mavrovounis
- Department of Emergency Medicine, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larisa, Greece
| | - Konstantinos Gourgoulianis
- Department of Respiratory Medicine, University of Thessaly, School of Medicine, University General Hospital of Larisa, Thessaly, Greece
| | - Ioannis Pantazopoulos
- Department of Emergency Medicine, Faculty of Medicine, School of Health Sciences, University of Thessaly, Larisa, Greece
| |
Collapse
|