1
|
Zhao D, Mou X, Li Y, Yao Y, Du L, Li Z, Wang P, Li X, Chen X, Li X, Li Y, Fang Z, Xia J. The application of impulse oscillometry system based on machine learning algorithm in the diagnosis of chronic obstructive pulmonary disease. Physiol Meas 2024; 45:055022. [PMID: 38599216 DOI: 10.1088/1361-6579/ad3d24] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Accepted: 04/10/2024] [Indexed: 04/12/2024]
Abstract
Objective. Diagnosing chronic obstructive pulmonary disease (COPD) using impulse oscillometry (IOS) is challenging due to the high level of clinical expertise it demands from doctors, which limits the clinical application of IOS in screening. The primary aim of this study is to develop a COPD diagnostic model based on machine learning algorithms using IOS test results.Approach. Feature selection was conducted to identify the optimal subset of features from the original feature set, which significantly enhanced the classifier's performance. Additionally, secondary features area of reactance (AX) were derived from the original features based on clinical theory, further enhancing the performance of the classifier. The performance of the model was analyzed and validated using various classifiers and hyperparameter settings to identify the optimal classifier. We collected 528 clinical data examples from the China-Japan Friendship Hospital for training and validating the model.Main results. The proposed model achieved reasonably accurate diagnostic results in the clinical data (accuracy = 0.920, specificity = 0.941, precision = 0.875, recall = 0.875).Significance. The results of this study demonstrate that the proposed classifier model, feature selection method, and derived secondary feature AX provide significant auxiliary support in reducing the requirement for clinical experience in COPD diagnosis using IOS.
Collapse
Affiliation(s)
- Dongfang Zhao
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Xiuying Mou
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Yueqi Li
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Yicheng Yao
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Lidong Du
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Zhenfeng Li
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Peng Wang
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Xiaoran Li
- Beijing Friendship Hospital, Capital Medical University, Beijing, People's Republic of China
| | - Xianxiang Chen
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
| | - Xiaopan Li
- National Center for Respiratory Medicine, State Key Laboratory of Respiratory Health and Multimorbidity, National Clinical Research Center for Respiratory Diseases, Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing, People's Republic of China
| | - Yong Li
- National Center for Respiratory Medicine, State Key Laboratory of Respiratory Health and Multimorbidity, National Clinical Research Center for Respiratory Diseases, Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing, People's Republic of China
| | - Zhen Fang
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100094, People's Republic of China
- Research Unit of Personalized Management of Chronic Respiratory Disease, Chinese Academy of Medical Sciences, People's Republic of China
| | - Jingen Xia
- National Center for Respiratory Medicine, State Key Laboratory of Respiratory Health and Multimorbidity, National Clinical Research Center for Respiratory Diseases, Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing, People's Republic of China
| |
Collapse
|
2
|
Yang L, Gao Z, Cao X, Sun S, Wang C, Wang H, Dai J, Liu Y, Qin Y, Dai M, Guo W, Zhang B, Zhao K, Zhao Z. Electrical impedance tomography as a bedside assessment tool for COPD treatment during hospitalization. Front Physiol 2024; 15:1352391. [PMID: 38562620 PMCID: PMC10982416 DOI: 10.3389/fphys.2024.1352391] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 03/06/2024] [Indexed: 04/04/2024] Open
Abstract
For patients with chronic obstructive pulmonary disease (COPD), the assessment of the treatment efficacy during hospitalization is of importance to the optimization of clinical treatments. Conventional spirometry might not be sensitive enough to capture the regional lung function development. The study aimed to evaluate the feasibility of using electrical impedance tomography (EIT) as an objective bedside evaluation tool for the treatment of acute exacerbation of COPD (AECOPD). Consecutive patients who required hospitalization due to AECOPD were included prospectively. EIT measurements were conducted at the time of admission and before the discharge simultaneously when a forced vital capacity maneuver was conducted. EIT-based heterogeneity measures of regional lung function were calculated based on the impedance changes over time. Surveys for attending doctors and patients were designed to evaluate the ease of use, feasibility, and overall satisfaction level to understand the acceptability of EIT measurements. Patient-reported outcome assessments were conducted. User's acceptance of EIT technology was investigated with a five-dimension survey. A total of 32 patients were included, and 8 patients were excluded due to the FVC maneuver not meeting the ATS criteria. Spirometry-based lung function was improved during hospitalization but not significantly different (FEV1 %pred.: 35.8% ± 6.7% vs. 45.3% ± 8.8% at admission vs. discharge; p = 0.11. FVC %pred.: 67.8% ± 0.4% vs. 82.6% ± 5.0%; p = 0.15. FEV1/FVC: 0.41 ± 0.09 vs. 0.42 ± 0.07, p = 0.71). The symptoms of COPD were significantly improved, but the correlations between the improvement of symptoms and spirometry FEV1 and FEV1/FVC were low (R = 0.1 and -0.01, respectively). The differences in blood gasses and blood tests were insignificant. All but one EIT-based regional lung function parameter were significantly improved after hospitalization. The results highly correlated with the patient-reported outcome assessment (R > 0.6, p < 0.001). The overall acceptability score of EIT measurement for both attending physicians and patients was high (4.1 ± 0.8 for physicians, 4.5 ± 0.5 for patients out of 5). These results demonstrated that it was feasible and acceptable to use EIT as an objective bedside evaluation tool for COPD treatment efficacy.
Collapse
Affiliation(s)
- Lin Yang
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Zhijun Gao
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Xinsheng Cao
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Shuying Sun
- Department of Pulmonary and Critical Care Medicine, 986th Hospital of Air Force, Air Force Medical University, Xi’an, China
| | - Chunchen Wang
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Hang Wang
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Jing Dai
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Yang Liu
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Yilong Qin
- Department of Aerospace Medicine, Air Force Medical University, Xi’an, China
| | - Meng Dai
- Department of Biomedical Engineering, Air Force Medical University, Xi’an, China
| | - Wei Guo
- Department of Pulmonary and Critical Care Medicine, 986th Hospital of Air Force, Air Force Medical University, Xi’an, China
| | - Binghua Zhang
- Department of Pulmonary and Critical Care Medicine, 986th Hospital of Air Force, Air Force Medical University, Xi’an, China
| | - Ke Zhao
- Department of Pulmonary and Critical Care Medicine, 986th Hospital of Air Force, Air Force Medical University, Xi’an, China
| | - Zhanqi Zhao
- School of Biomedical Engineering, Guangzhou Medical University, Guangzhou, China
- Department of Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China
| |
Collapse
|
3
|
Yang L, Gao Z, Wang C, Wang H, Dai J, Liu Y, Qin Y, Dai M, Cao X, Zhao Z. Evaluation of adjacent and opposite current injection patterns for a wearable chest electrical impedance tomography system. Physiol Meas 2024; 45:025004. [PMID: 38266301 DOI: 10.1088/1361-6579/ad2215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Accepted: 01/24/2024] [Indexed: 01/26/2024]
Abstract
Objective.Wearable electrical impedance tomography (EIT) can be used to monitor regional lung ventilation and perfusion at the bedside. Due to its special system architecture, the amplitude of the injected current is usually limited compared to stationary EIT system. This study aims to evaluate the performance of current injection patterns with various low-amplitude currents in healthy volunteers.Approach.A total of 96 test sets of EIT measurement was recorded in 12 healthy subjects by employing adjacent and opposite current injection patterns with four amplitudes of small current (i.e. 1 mA, 500 uA, 250 uA and 125 uA). The performance of the two injection patterns with various currents was evaluated in terms of signal-to-noise ratio (SNR) of thorax impedance, EIT image metrics and EIT-based clinical parameters.Main results.Compared with adjacent injection, opposite injection had higher SNR (p< 0.01), less inverse artifacts (p< 0.01), and less boundary artifacts (p< 0.01) with the same current amplitude. In addition, opposite injection exhibited more stable EIT-based clinical parameters (p< 0.01) across the current range. For adjacent injection, significant differences were found for three EIT image metrics (p< 0.05) and four EIT-based clinical parameters (p< 0.01) between the group of 125 uA and the other groups.Significance.For better performance of wearable pulmonary EIT, currents greater than 250 uA should be used in opposite injection, 500 uA in adjacent one, to ensure a high level of SNR, a high quality of reconstructed image as well as a high reliability of clinical parameters.
Collapse
Affiliation(s)
- Lin Yang
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Zhijun Gao
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Chunchen Wang
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Hang Wang
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Jing Dai
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Yang Liu
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Yilong Qin
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Meng Dai
- Department of Biomedical Engineering, Air Force Medical University, Xi'an, People's Republic of China
| | - Xinsheng Cao
- Department of Aerospace Medicine, Air Force Medical University, Xi'an, People's Republic of China
| | - Zhanqi Zhao
- School of Biomedical Engineering, Guangzhou Medical University, Guangzhou, People's Republic of China
- Department of Critical Care Medicine, Peking Union Medical College Hospital, Beijing, People's Republic of China
| |
Collapse
|
4
|
Quiroga TN, Bachar N, Voigt W, Danino N, Shafran I, Shtrichman R, Shuster G, Lambrecht N, Eisenmann S. Changes in tidal breathing biomarkers as indicators of treatment response in AECOPD patients in an acute care setting. Adv Med Sci 2023; 68:176-185. [PMID: 37146372 DOI: 10.1016/j.advms.2023.04.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2022] [Revised: 03/01/2023] [Accepted: 04/26/2023] [Indexed: 05/07/2023]
Abstract
PURPOSE Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) is a complication of COPD that typically necessitates intensified treatment and hospitalization. It is linked to higher morbidity, mortality and healthcare spending. Assessment of therapy response for AECOPD is difficult due to the variability of symptoms and limitations in current measures. Hence, there is a need for new biomarkers to aid in the management of AECOPD in acute care settings. MATERIALS AND METHODS Fifteen hospitalized AECOPD patients (GOLD 3-4) were enrolled in this study. Treatment response was assessed daily through clinical evaluations and by monitoring tidal breathing biomarkers (respiratory rate [RR], expiratory time [Tex], inspiratory time [Tin], expiratory pause [Trst], total breath time [Ttot]), using a novel, wearable nanosensor-based device (SenseGuard™). RESULTS Patients who showed significant clinical improvement had substantial changes in ΔTex/Ttot (+14%), ΔTrst/Ttot (-18%), and ΔTin/Tex (+0.09), whereas patients who showed mild or no clinical improvement had smaller changes (+5%, +3%, and -0.03, respectively). Linear regression between change in physician's assessment score and the median change in tidal breathing parameters was significant for Tin/Tex (R2 = 0.449, ∗p = 0.017), Tex/Ttot (R2 = 0.556, ∗p = 0.005) and Trst/Ttot (R2 = 0.446, ∗p = 0.018), while no significant regression was observed for RR, Tin/(Trst + Tex) and Tin/Ttot. CONCLUSIONS Our study demonstrates the potential of the SenseGuard™ to monitor treatment response in AECOPD patients by measuring changes in tidal breathing biomarkers, which were shown to be associated with significant changes in the patients' respiratory condition as evaluated by physicians. However, further large-scale clinical studies are needed to confirm these findings.
Collapse
Affiliation(s)
- Tess Nuñez Quiroga
- Department of Internal Medicine I, Pulmonary Medicine, University Hospital Halle (Saale), Halle, Germany
| | | | - Wieland Voigt
- NanoVation-GS LTD, Haifa, Israel; Medical Innovation and Management, Steinbeis University Berlin, Berlin, Germany
| | | | | | | | | | - Nina Lambrecht
- Department of Internal Medicine I, Pulmonary Medicine, University Hospital Halle (Saale), Halle, Germany
| | - Stephan Eisenmann
- Department of Internal Medicine I, Pulmonary Medicine, University Hospital Halle (Saale), Halle, Germany
| |
Collapse
|
5
|
Scaramuzzo G, Ronzoni L, Campo G, Priani P, Arena C, La Rosa R, Turrini C, Volta CA, Papi A, Spadaro S, Contoli M. Long-term dyspnea, regional ventilation distribution and peripheral lung function in COVID-19 survivors: a 1 year follow up study. BMC Pulm Med 2022; 22:408. [PMCID: PMC9643983 DOI: 10.1186/s12890-022-02214-5] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2022] [Accepted: 11/02/2022] [Indexed: 11/11/2022] Open
Abstract
Abstract
Background
Dyspnea is common after COVID-19 pneumonia and can be characterized by a defective CO2 diffusion (DLCO) despite normal pulmonary function tests (PFT). Nevertheless, DLCO impairment tends to normalize at 1 year, with no dyspnea regression. The altered regional distribution of ventilation and a dysfunction of the peripheral lung may characterize dyspnea at 1 year after COVID-19 pneumonia. We aimed at assessing the pattern of airway resistance and inflammation and the regional ventilation inhomogeneity in COVID-19 pneumonia survivors at 12-months after hospital discharge.
Methods
We followed up at 1-year patients previously admitted to the respiratory units (intensive care or sub-intensive care unit) for COVID-19 acute respiratory failure at 1-year after hospital discharge. PFT (spirometry, DLCO), impulse oscillometry (IOS), measurements of the exhaled nitric oxide (FENO) and Electrical Impedance Tomography (EIT) were used to evaluate lung volumes, CO2 diffusion capacity, peripheral lung inflammation/resistances and the regional inhomogeneity of ventilation distribution. A full medical examination was conducted, and symptoms of new onset (not present before COVID-19) were recorded. Patients were therefore divided into two groups based on the presence/absence of dyspnea (defined as mMRC ≥1) compared to evaluate differences in the respiratory function derived parameters.
Results
Sixty-seven patients were admitted between October and December 2020. Of them, 42/67 (63%) patients were discharged alive and 33 were evaluated during the follow up. Their mean age was 64 ± 11 years and 24/33 (73%) were males. Their maximum respiratory support was in 7/33 (21%) oxygen, in 4/33 (12%) HFNC, in 14/33 (42%) NIV/CPAP and in 8/33 (24%) invasive mechanical ventilation. During the clinical examination, 15/33 (45%) reported dyspnea. When comparing the two groups, no significant differences were found in PFT, in the peripheral airway inflammation (FENO) or mechanical properties (IOS). However, EIT showed a significantly higher regional inhomogeneity in patients with dyspnea both during resting breathing (0.98[0.96–1] vs 1.1[1–1.1], p = 0.012) and during forced expiration (0.96[0.94–1] vs 1 [0.98–1.1], p = 0.045).
Conclusions
New onset dyspnea characterizes 45% of patients 1 year after COVID-19 pneumonia. In these patients, despite pulmonary function test may be normal, EIT shows a higher regional inhomogeneity both during quiet and forced breathing which may contribute to dyspnea.
Clinical trial registration
Clinicaltrials.gov NCT04343053, registration date 13/04/2020.
Collapse
|