Dataset Information

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease.

ABSTRACT: Heterogeneous clinical manifestations and progression of chronic obstructive pulmonary disease (COPD) affect patient health risk assessment, stratification, and management. Pulmonary function tests are used to diagnose and classify the severity of COPD, but they cannot fully represent the type or range of pathophysiologic abnormalities of the disease. To evaluate whether deep radiomics from chest computed tomography (CT) images can predict mortality in patients with COPD, we designed a convolutional neural network (CNN) model for extracting representative features from CT images and then performed random survival forest to predict survival in COPD patients. We trained CNN-based binary classifier based on six-minute walk distance results (> 440 m or not) and extracted high-throughput image features (i.e., deep radiomics) directly from the last fully connected layer of it. The various sizes of fully connected layers and combinations of deep features were experimented using a discovery cohort with 344 patients from the Korean Obstructive Lung Disease cohort and an external validation cohort with 102 patients from Penang General Hospital in Malaysia. In the integrative analysis of discovery and external validation cohorts, with combining 256 deep features from the coronal slice of the vertebral body and two sagittal slices of the left/right lung, deep radiomics for survival prediction achieved concordance indices of 0.8008 (95% CI, 0.7642-0.8373) and 0.7156 (95% CI, 0.7024-0.7288), respectively. Deep radiomics from CT images could be used to predict mortality in COPD patients.

SUBMITTER: Yun J

PROVIDER: S-EPMC8313653 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundRadiomics and artificial intelligence approaches have been developed to predict chronic obstructive pulmonary disease (COPD), but it is still unclear which approach has the best performance. Therefore, we established five prediction models that employed deep-learning (DL) and radiomics-based machine-learning (ML) approaches to identify COPD on low-dose computed tomography (LDCT) images and compared the relative performance of the different models to find the best model for identifying COPD.MethodsThis retrospective analysis included 1,024 subjects (169 COPD patients and 855 control subjects) who underwent LDCT scans from August 2018 to July 2021. Five prediction models, including models that employed computed tomography (CT)-based radiomics features, chest CT images, quantitative lung density parameters, and demographic and clinical characteristics, were established to identify COPD by DL or ML approaches. Model 1 used CT-based radiomics features by ML method. Model 2 used a combination of CT-based radiomics features, lung density parameters, and demographic and clinical characteristics by ML method. Model 3 used CT images only by DL method. Model 4 used a combination of CT images, lung density parameters, and demographic and clinical characteristics by DL method. Model 5 used a combination of CT images, CT-based radiomics features, lung density parameters, and demographic and clinical characteristics by DL method. The accuracy, sensitivity, specificity, highest negative predictive values (NPVs), positive predictive values, and areas under the receiver operating characteristic (AUC) curve of the five prediction models were compared to examine their performance. The DeLong test was used to compare the AUCs of the different models.ResultsIn total, 107 radiomics features were extracted from each subject's CT images, 17 lung density parameters were acquired by quantitative measurement, and 18 selected demographic and clinical characteristics were recorded in this study. Model 2 had the highest AUC [0.73, 95% confidence interval (CI): 0.64-0.82], while model 3 had the lowest AUC (0.65, 95% CI: 0.55-0.75) in the test set. Model 2 also had the highest sensitivity (0.84), the highest accuracy (0.81), and the highest NPV (0.36). In the test set, based on the AUC results, Model 2 significantly outperformed Model 1 (P=0.03).ConclusionsThe results showed that the identification ability of models that employ CT-based radiomics features combined with lung density parameters, and demographic and clinical characteristics using ML methods performed better than the chest CT image-based DL methods. ML methods are more suitable and beneficial for COPD identification.

Project description:OBJECTIVE:We aimed to evaluate correlations between computed tomography (CT) parameters and pulmonary function test (PFT) parameters according to disease severity in patients with chronic obstructive pulmonary disease (COPD), and to determine whether CT parameters can be used to predict PFT indices. MATERIALS AND METHODS:A total of 370 patients with COPD were grouped based on disease severity according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) I-IV criteria. Emphysema index (EI), air-trapping index, and airway parameters such as the square root of wall area of a hypothetical airway with an internal perimeter of 10 mm (Pi10) were measured using automatic segmentation software. Clinical characteristics including PFT results and quantitative CT parameters according to GOLD criteria were compared using ANOVA. The correlations between CT parameters and PFT indices, including the ratio of forced expiratory volume in one second to forced vital capacity (FEV₁/FVC) and FEV₁, were assessed. To evaluate whether CT parameters can be used to predict PFT indices, multiple linear regression analyses were performed for all patients, Group 1 (GOLD I and II), and Group 2 (GOLD III and IV). RESULTS:Pulmonary function deteriorated with increase in disease severity according to the GOLD criteria (p < 0.001). Parenchymal attenuation parameters were significantly worse in patients with higher GOLD stages (p < 0.001), and Pi10 was highest for patients with GOLD III (4.41 ± 0.94 mm). Airway parameters were nonlinearly correlated with PFT results, and Pi10 demonstrated mild correlation with FEV₁/FVC in patients with GOLD II and III (r = 0.16, p = 0.06 and r = 0.21, p = 0.04, respectively). Parenchymal attenuation parameters, airway parameters, EI, and Pi10 were identified as predictors of FEV₁/FVC for the entire study sample and for Group 1 (R² = 0.38 and 0.22, respectively; p < 0.001). However, only parenchymal attenuation parameter, EI, was identified as a predictor of FEV₁/FVC for Group 2 (R² = 0.37, p < 0.001). Similar results were obtained for FEV₁. CONCLUSION:Airway and parenchymal attenuation parameters are independent predictors of pulmonary function in patients with mild COPD, whereas parenchymal attenuation parameters are dominant independent predictors of pulmonary function in patients with severe COPD.

Project description:Purpose:Pulmonary rehabilitation (PR) is a well-established treatment for chronic obstructive pulmonary disease (COPD). The standard protocol for PR requires frequent hospital visits, which can be difficult for patients. We performed this study to assess whether unsupervised home-based PR (HBPR) is effective for patients with COPD. Patients and Methods:After assessing the outcome data, including the results of a COPD assessment test (CAT); the body mass index, airflow obstruction, dyspnea, and exercise capacity (BODE) index; a spirometry; the modified Medical Research Council (mMRC) dyspnea scale; and the 6-min walking test (6MWT), specialists imparted 1-hour education to patients regarding unsupervised HBPR at the baseline visit. This included methods for breathing, inhaler use, stretching, and exercise. On reviewing diaries after 8 weeks from the first visit, patients who exercised at least thrice per week were classified as the compliant group and the others were categorized as the noncompliant group. Changes in the outcomes were compared between the compliant and noncompliant groups. Results:A total of 41 patients were enrolled in this study; for 8 weeks of unsupervised HBPR, there were significant improvements in CAT scores (-4.62±4.61 vs 2.40±6.73; P=0.002), BODE index (-1.00±1.06 vs -0.20±0.56; P=0.01), and forced expiratory volume in 1 s (0.05±0.19 vs -0.09±0.16; P=0.02) among patients in the compliant group, compared with the noncompliant group. Moreover, their CAT (16.46±7.80 vs 11.85±7.23; P=0.03) and mMRC scores (2.54±0.76 vs 1.81±0.63; P=0.001) improved significantly after 8 weeks, compared with those at baseline. On the other hand, patients in the noncompliant group showed no significant improvement in any of the outcomes. Conclusion:In this study, compliant patients with unsupervised HBPR achieved favorable outcomes in 8 weeks. Thus, we recommend unsupervised HBPR for patients with COPD, even when regular hospital visits for PR are not possible. Trial Registration:NCT03754881.

Dataset Information

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets