1
|
Dai R, Sun M, Lu M, Deng L. Interpretable machine learning models based on shear-wave elastography radiomics for predicting cardiovascular disease in diabetic kidney disease patients. J Diabetes Investig 2024. [PMID: 39171653 DOI: 10.1111/jdi.14294] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/09/2024] [Revised: 07/24/2024] [Accepted: 08/02/2024] [Indexed: 08/23/2024] Open
Abstract
BACKGROUND The risk of cardiovascular complications is significantly elevated in patients with diabetic kidney disease (DKD). Recognizing the link between the progression of DKD and an increased risk of cardiovascular disease (CVD), it is crucial to focus on the early prediction and management of CVD risk factors among these patients to potentially enhance their health outcomes. OBJECTIVE This study sought to bridge the existing gap by developing and validating machine learning (ML) models that utilize clinical data and shear wave elastography (SWE) radiomics features to identify patients at risk of CVD, ultimately aiming to improve the management of DKD. MATERIALS AND METHODS This study conducted a retrospective analysis of 586 patients with DKD, dividing them into training and external validation cohorts. We categorized patients based on the presence or absence of CVD. Utilizing SWE imaging, we extracted and standardized radiomics features to develop multiple ML models. These models underwent internal validation using radiomics features alone, clinical data, or a combination thereof. The optimal model was then identified, and its feature importance was assessed through the Shapley Additive Explanations (SHAP) method, before proceeding to external validation. RESULTS Among the 586 patients analyzed, 30.7% (180/586) were identified as at risk for CVD. The study pinpointed six significant radiomics features related to CVD, alongside six critical pieces of clinical data. The Support Vector Machine (SVM) model outperformed others in both internal and external validations. Further, SHAP analysis highlighted five principal determinants of CVD risk, comprising three clinical indicators and two SWE radiomics features. CONCLUSIONS This study highlights the effectiveness of an SVM model that combines clinical and radiomics features in predicting CVD risk among DKD patients. It enables early prediction of CVD in this patient group, thereby supporting the implementation of timely and suitable interventions.
Collapse
Affiliation(s)
- Ruihong Dai
- Department of Ultrasound, Meng Cheng County Hospital of Chinese Medicine, Bozhou City, Anhui Province, China
| | - Miaomiao Sun
- Department of Ultrasound, Meng Cheng County Hospital of Chinese Medicine, Bozhou City, Anhui Province, China
| | - Mei Lu
- Department of Ultrasound, Meng Cheng County Hospital of Chinese Medicine, Bozhou City, Anhui Province, China
| | - Lanhua Deng
- Department of Ultrasound, Meng Cheng County Hospital of Chinese Medicine, Bozhou City, Anhui Province, China
| |
Collapse
|
2
|
Wei C, Jin Z, Ma Q, Xu Y, Zhu Y, Zeng Y, Zhang R, Zhang Y, Jiang L, Song K, Jiang Z. Native T 1 mapping-based radiomics diagnosis of kidney function and renal fibrosis in chronic kidney disease. iScience 2024; 27:110493. [PMID: 39175777 PMCID: PMC11339247 DOI: 10.1016/j.isci.2024.110493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Revised: 04/26/2024] [Accepted: 07/09/2024] [Indexed: 08/24/2024] Open
Abstract
Chronic kidney disease (CKD) raises major concerns for global public health as it is characterized by high prevalence, low awareness, high healthcare costs, and poor prognosis. Therefore, our study prospectively established and validated native T1 mapping-based radiomics models for the prediction of renal fibrosis and renal function in patients with CKD. Moreover, the area under the receiver operating characteristic curve (AUC) and diagnostic sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were used to evaluate its performance. Thus, our results show that radiomics based on native T1 mapping images can better identify renal function and renal fibrosis in patients with CKD and outperform conventional T1 mapping parameters of ΔT1 and T1%, thus providing more information for CKD management and clinical decision-making.
Collapse
Affiliation(s)
- Chaogang Wei
- Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Zhicheng Jin
- Department of Nuclear Medicine, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Qing Ma
- Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Yilin Xu
- Department of Nephrology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Ye Zhu
- Department of Nephrology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Ying Zeng
- Department of Nephrology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Rui Zhang
- Department of Radiology, Hulunbuir People’s Hospital, Hulunbuir 021008, China
| | - Yueyue Zhang
- Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Linsen Jiang
- Department of Nephrology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Kai Song
- Department of Nephrology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| | - Zhen Jiang
- Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China
| |
Collapse
|
3
|
Reiss AB, Jacob B, Zubair A, Srivastava A, Johnson M, De Leon J. Fibrosis in Chronic Kidney Disease: Pathophysiology and Therapeutic Targets. J Clin Med 2024; 13:1881. [PMID: 38610646 PMCID: PMC11012936 DOI: 10.3390/jcm13071881] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Revised: 03/18/2024] [Accepted: 03/20/2024] [Indexed: 04/14/2024] Open
Abstract
Chronic kidney disease (CKD) is a slowly progressive condition characterized by decreased kidney function, tubular injury, oxidative stress, and inflammation. CKD is a leading global health burden that is asymptomatic in early stages but can ultimately cause kidney failure. Its etiology is complex and involves dysregulated signaling pathways that lead to fibrosis. Transforming growth factor (TGF)-β is a central mediator in promoting transdifferentiation of polarized renal tubular epithelial cells into mesenchymal cells, resulting in irreversible kidney injury. While current therapies are limited, the search for more effective diagnostic and treatment modalities is intensive. Although biopsy with histology is the most accurate method of diagnosis and staging, imaging techniques such as diffusion-weighted magnetic resonance imaging and shear wave elastography ultrasound are less invasive ways to stage fibrosis. Current therapies such as renin-angiotensin blockers, mineralocorticoid receptor antagonists, and sodium/glucose cotransporter 2 inhibitors aim to delay progression. Newer antifibrotic agents that suppress the downstream inflammatory mediators involved in the fibrotic process are in clinical trials, and potential therapeutic targets that interfere with TGF-β signaling are being explored. Small interfering RNAs and stem cell-based therapeutics are also being evaluated. Further research and clinical studies are necessary in order to avoid dialysis and kidney transplantation.
Collapse
Affiliation(s)
- Allison B. Reiss
- Department of Medicine and Biomedical Research Institute, NYU Grossman Long Island School of Medicine, Mineola, NY 11501, USA; (B.J.); (A.Z.); (A.S.); (M.J.); (J.D.L.)
| | | | | | | | | | | |
Collapse
|
4
|
Chen Z, Wang Y, Gunda ST, Han X, Su Z, Ying MTC. Integrating shear wave elastography and estimated glomerular filtration rate to enhance diagnostic strategy for renal fibrosis assessment in chronic kidney disease. Quant Imaging Med Surg 2024; 14:1766-1777. [PMID: 38415158 PMCID: PMC10895140 DOI: 10.21037/qims-23-962] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2023] [Accepted: 11/29/2023] [Indexed: 02/29/2024]
Abstract
Background Assessing renal fibrosis non-invasively in patients with chronic kidney disease (CKD) remains a considerable clinical challenge. This study aimed to investigate the diagnostic efficacy of different approaches that combine shear wave elastography (SWE) and estimated glomerular filtration rate (eGFR) in distinguishing between mild fibrosis and moderate-to-severe fibrosis in CKD patients. Methods In this prospective study, 162 patients underwent renal SWE examinations and renal biopsies. Using SWE, the right renal cortex stiffness was measured, and the corresponding SWE value was recorded. Four diagnostic patterns were used to combine eGFR and SWE value: in isolation, in series, in parallel, and in integration. The receiver operating characteristic (ROC) curve was established, and the area under the ROC curve (AUC) was calculated to quantify diagnostic performance. Sensitivity, specificity, and accuracy were computed. Results The eGFR demonstrated sensitivity of 68.2% and specificity of 83.8%, whereas the SWE value displayed sensitivity of 84.1% and specificity of 62.2%, yielding a similar AUC (78.2% and 77.8%, respectively). Combining in series improved specificity to 97.3%, superior to other diagnostic patterns (all P values <0.01), but compromised sensitivity to 58.0%. When combined in parallel, the sensitivity increased to 94.3%, exceeding any other strategies (all P values <0.05), but the specificity dropped to 48.7%. The integrated strategy, incorporating eGFR with SWE value via the logistic regression algorithm, exhibited an AUC of 85.8%, outperforming all existing approaches (all P values <0.01), with balanced sensitivity, specificity, and accuracy of 86.4%, 74.3%, and 80.9%, respectively. Conclusions Using an integrated strategy to combine eGFR and SWE value could improve diagnostic performance in distinguishing between mild renal fibrosis and moderate-to-severe renal fibrosis in patients with CKD, thereby helping clinicians perform a more accurate clinical diagnosis.
Collapse
Affiliation(s)
- Ziman Chen
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
| | - Yingli Wang
- Department of Ultrasound, EDAN Instruments, Inc., Shenzhen, China
| | - Simon Takadiyi Gunda
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
| | - Xinyang Han
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
| | - Zhongzhen Su
- Department of Ultrasound, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
| | - Michael Tin Cheung Ying
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China
| |
Collapse
|
5
|
Yang D, Tian C, Liu J, Peng Y, Xiong Z, Da J, Yang Y, Zha Y, Zeng X. Diffusion Tensor and Kurtosis MRI-Based Radiomics Analysis of Kidney Injury in Type 2 Diabetes. J Magn Reson Imaging 2024. [PMID: 38299753 DOI: 10.1002/jmri.29263] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2023] [Revised: 01/13/2024] [Accepted: 01/16/2024] [Indexed: 02/02/2024] Open
Abstract
BACKGROUND Diffusion tensor imaging (DTI) and diffusion kurtosis imaging (DKI) can provide quantitative parameters that show promise for evaluation of diabetic kidney disease (DKD). The combination of radiomics with DTI and DKI may hold potential clinical value in detecting DKD. PURPOSE To investigate radiomics models of DKI and DTI for predicting DKD in type 2 diabetes mellitus (T2DM) and evaluate their performance in automated renal parenchyma segmentation. STUDY TYPE Prospective. POPULATION One hundred and sixty-three T2DM patients (87 DKD; 63 females; 27-80 years), randomly divided into training cohort (N = 114) and validation cohort (N = 49). FIELD STRENGTH/SEQUENCE 1.5-T, diffusion spectrum imaging (DSI) with 9 different b-values. ASSESSMENT The images of DSI were processed to generate DKI and DTI parameter maps, including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD). The Swin UNETR model was trained with 5-fold cross-validation using 100 samples for renal parenchyma segmentation. Subsequently, radiomics features were automatically extracted from each parameter map. The performance of the radiomics models on the validation cohort was evaluated by utilizing the receiver operating characteristic (ROC) curve. STATISTICAL TESTS Mann-Whitney U test, Chi-squared test, Pearson correlation coefficient, least absolute shrinkage and selection operator (LASSO), dice similarity coefficient (DSC), decision curve analysis (DCA), area under the curve (AUC), and DeLong's test. The threshold for statistical significance was set at P < 0.05. RESULTS The DKI_MD achieved the best segmentation performance (DSC, 0.925 ± 0.011). A combined radiomics model (DTI_FA, DTI_MD, DKI_FA, DKI_MD, and DKI_RD) showed the best performance (AUC, 0.918; 95% confidence interval [CI]: 0.820-0.991). When the threshold probability was greater than 20%, the combined model provided the greatest net benefit. Among the single parameter maps, the DTI_FA exhibited superior diagnostic performance (AUC, 887; 95% CI: 0.779-0.972). DATA CONCLUSION The radiomics signature constructed based on DKI and DTI may be used as an accurate and non-invasive tool to identify T2DM and DKD. LEVEL OF EVIDENCE 2 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Daoyu Yang
- Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, China
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, China
| | - Chong Tian
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, China
- School of Medicine, Guizhou University, Guiyang, China
| | - Jian Liu
- Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, China
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, China
| | - Yunsong Peng
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, China
| | - Zhenliang Xiong
- Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, China
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, China
| | - Jingjing Da
- Renal Division, Department of Medicine, Guizhou Provincial People's Hospital, Guiyang, China
| | - Yuqi Yang
- Renal Division, Department of Medicine, Guizhou Provincial People's Hospital, Guiyang, China
| | - Yan Zha
- School of Medicine, Guizhou University, Guiyang, China
- Renal Division, Department of Medicine, Guizhou Provincial People's Hospital, Guiyang, China
| | - Xianchun Zeng
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, China
| |
Collapse
|
6
|
Fu J, Lin Z, Zhang B, Song L, Qin N, Qiu J, Yang M, Zou Y. Magnetic Resonance Imaging in Atherosclerotic Renal Artery Stenosis: The Update and Future Directions from Interventional Perspective. KIDNEY DISEASES (BASEL, SWITZERLAND) 2024; 10:23-31. [PMID: 38322626 PMCID: PMC10843188 DOI: 10.1159/000534499] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Accepted: 08/23/2023] [Indexed: 02/08/2024]
Abstract
Background Atherosclerotic renal artery stenosis (ARAS) is a condition where the renal arteries become narrowed due to atherosclerosis, leading to reduced blood flow to the kidneys and various renal complications. The effectiveness of interventional treatments, such as renal artery angioplasty and stenting, remains debated, making patient selection for these procedures challenging. Summary This review focuses on the diagnosis and management of ARAS, with a particular emphasis on the potential role of functional magnetic resonance imaging (MRI) in evaluating renal function and mechanisms. By summarizing current diagnostic approaches and outcomes of interventional treatments, the review highlights the importance of informed clinical decision-making in ARAS management. Functional MRI emerges as a promising noninvasive tool to assess renal function, aiding in patient stratification and treatment planning. Key Messages The efficacy of interventional treatments for ARAS requires further investigation and careful patient selection. Functional MRI holds promise as a noninvasive means to assess renal function and mechanisms, potentially guiding more effective clinical decisions in ARAS management. Advancing research in diagnostic methods, particularly functional MRI, can enhance our understanding and improve the treatment outcomes for ARAS patients.
Collapse
Affiliation(s)
- Jia Fu
- Department of Interventional Radiology and Vascular Surgery, Peking University First Hospital, Beijing, China
| | - Zhiyong Lin
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Bihui Zhang
- Department of Interventional Radiology and Vascular Surgery, Peking University First Hospital, Beijing, China
| | - Li Song
- Department of Interventional Radiology and Vascular Surgery, Peking University First Hospital, Beijing, China
| | - Naishan Qin
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Jianxing Qiu
- Department of Radiology, Peking University First Hospital, Beijing, China
| | - Min Yang
- Department of Interventional Radiology and Vascular Surgery, Peking University First Hospital, Beijing, China
| | - Yinghua Zou
- Department of Interventional Radiology and Vascular Surgery, Peking University First Hospital, Beijing, China
| |
Collapse
|
7
|
Yin C, Xiao W, Hu X, Liu X, Xian H, Su J, Zhang C, Qin X. Non-invasive prediction of the chronic degree of lupus nephropathy based on ultrasound radiomics. Lupus 2024; 33:121-128. [PMID: 38320976 DOI: 10.1177/09612033231223373] [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] [Indexed: 02/08/2024]
Abstract
OBJECTIVE Through machine learning (ML) analysis of the radiomics features of ultrasound extracted from patients with lupus nephritis (LN), this attempt was made to non-invasively predict the chronicity index (CI)of LN. METHODS A retrospective collection of 136 patients with LN who had renal biopsy was retrospectively collected, and the patients were randomly divided into training set and validation set according to 7:3. Radiomics features are extracted from ultrasound images, independent factors are obtained by using LASSO dimensionality reduction, and then seven ML models were used to establish predictive models. At the same time, a clinical model and an US model were established. The diagnostic efficacy of the model is evaluated by analysis of the receiver operating characteristics (ROC) curve, accuracy, specificity, and sensitivity. The performance of the seven machine learning models was compared with each other and with clinical and US models. RESULTS A total of 1314 radiomics features are extracted from ultrasound images, and 5 features are finally screened out by LASSO for model construction, and the average ROC of the seven ML is 0.683, among which the Xgboost model performed the best, and the AUC in the test set is 0.826 (95% CI: 0.681-0.936). For the same test set, the AUC of clinical model constructed based on eGFR is 0.560 (95% CI: 0.357-0.761), and the AUC of US model constructed based on Ultrasound parameters is 0.679 (95% CI: 0.489-0.853). The Xgboost model is significantly more efficient than the clinical and US models. CONCLUSION ML model based on ultrasound radiomics features can accurately predict the chronic degree of LN, which can provide a valuable reference for clinicians in the treatment strategy of LN patients.
Collapse
Affiliation(s)
- Chen Yin
- Department of Ultrasound, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
| | - Weihan Xiao
- Department of Ultrasound, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
| | - Xiaomin Hu
- Department of Ultrasound, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
| | - Xuebin Liu
- Department of Ultrasound, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
| | - Huaming Xian
- Department of Nephrology, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
| | - Jun Su
- Department of Ultrasound, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
| | - Chaoxue Zhang
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Xiachuan Qin
- Department of Ultrasound, The Second Clinical Medical College, North Sichuan Medical College, Nan Chong, China
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, China
| |
Collapse
|
8
|
Su X, Lin S, Huang Y. Value of radiomics-based two-dimensional ultrasound for diagnosing early diabetic nephropathy. Sci Rep 2023; 13:20427. [PMID: 37993534 PMCID: PMC10665410 DOI: 10.1038/s41598-023-47449-2] [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: 09/22/2023] [Accepted: 11/14/2023] [Indexed: 11/24/2023] Open
Abstract
Despite efforts to diagnose diabetic nephropathy (DN) using biochemical data or ultrasound imaging separately, a significant gap exists regarding the development of integrated models combining both modalities for enhanced early DN diagnosis. Therefore, we aimed to assess the ability of machine learning models containing two-dimensional ultrasound imaging and biochemical data to diagnose early DN in patients with type 2 diabetes mellitus (T2DM). This retrospective study included 219 patients, divided into a training or test group at an 8:2 ratio. Features were selected using minimum redundancy maximum relevance and random forest-recursive feature elimination. The predictive performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) for sensitivity, specificity, Matthews Correlation Coefficient, F1 score, and accuracy. K-nearest neighbor, support vector machine, and logistic regression models could diagnose early DN, with AUC values of 0.94, 0.85, and 0.85 in the training cohort and 0.91, 0.84, and 0.84 in the test cohort, respectively. Early DN diagnosing using two-dimensional ultrasound-based radiomics models can potentially revolutionize T2DM patient care by enabling proactive interventions, ultimately improving patient outcomes. Our integrated approach showcases the power of artificial intelligence in medical imaging, enhancing early disease detection strategies with far-reaching applications across medical disciplines.
Collapse
Affiliation(s)
- Xuee Su
- Centre of Neurological and Metabolic Research, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China
- Department of Anaesthesia, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China
| | - Shu Lin
- Centre of Neurological and Metabolic Research, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China.
- Diabetes and Metabolism Division, Garvan Institute of Medical Research, 384 Victoria Street, Darlinghurst, Sydney, NSW, 2010, Australia.
| | - Yinqiong Huang
- Centre of Neurological and Metabolic Research, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China.
- Department of Endocrinology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, China.
| |
Collapse
|
9
|
Meng F, Wu Q, Zhang W, Hou S. Shear-Wave Elastography-Based Radiomics Nomogram for the Prediction of Cardiovascular Disease in Patients with Diabetic Kidney Disease. Diabetes Metab Syndr Obes 2023; 16:2705-2716. [PMID: 37701720 PMCID: PMC10494864 DOI: 10.2147/dmso.s422364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/23/2023] [Accepted: 08/29/2023] [Indexed: 09/14/2023] Open
Abstract
Background Diabetic kidney disease (DKD) patients have a high risk of suffering from cardiovascular disease (CVD), placing a heavy cost on the public health system. In this study, we intended to develop and validate a shear-wave elastography (SWE)-based radiomics nomogram for predicting the development of CVD in DKD patients. This approach allows extensive use of the valuable information contained in ultrasound images, thus helping clinicians to identify CVD in DKD patients. Methods Totally 337 and 145 patients constituted the training and validation cohorts, respectively. The radiomics features of the segmented kidney in ultrasound images were extracted and selected to generate the rad-score of each patient. These rad-score, as well as the predictors of risk of CVD occurrence from the clinical characteristics, were included in the multivariate analysis to develop a nomogram. It was further assessed in the training and validation cohorts. Results Patients with CVD accounted for 30.9% (104/337) in the training cohort and 31.0% (45/145) in the validation cohort. The rad-score was calculated for each patient using 6 features extracted from the ultrasound images. The radiomics nomogram was built with the rad-score, age, systolic blood pressure (SBP), low-density lipoprotein cholesterol (LDL-C). It was superior to the clinical nomogram developed without the rad-score and demonstrated promising discrimination, calibration, and clinical utility in both training and validation cohorts. Conclusion We developed and validated an SWE-based radiomics nomogram to predict CVD risk in patients with DKD. The model was demonstrated to have a promising prediction performance, showing its potential to identify CVD in DKD patients and assist decision-making for appropriate early intervention.
Collapse
Affiliation(s)
- Fei Meng
- Department of Ultrasound, Xuan Cheng City Central Hospital, Xuancheng, Anhui, People’s Republic of China
| | - Qin Wu
- Department of Ultrasound, Xuan Cheng City Central Hospital, Xuancheng, Anhui, People’s Republic of China
| | - Wei Zhang
- Department of Ultrasound, Xuan Cheng City Central Hospital, Xuancheng, Anhui, People’s Republic of China
| | - Shirong Hou
- Department of Ultrasound, Xuan Cheng City Central Hospital, Xuancheng, Anhui, People’s Republic of China
| |
Collapse
|
10
|
Chen Z, Ying MTC, Wang Y, Chen J, Wu C, Han X, Su Z. Ultrasound-based radiomics analysis in the assessment of renal fibrosis in patients with chronic kidney disease. Abdom Radiol (NY) 2023; 48:2649-2657. [PMID: 37256330 DOI: 10.1007/s00261-023-03965-3] [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: 02/24/2023] [Revised: 05/13/2023] [Accepted: 05/16/2023] [Indexed: 06/01/2023]
Abstract
PURPOSE Assessment of renal fibrosis non-invasively in chronic kidney disease (CKD) patients is still a clinical challenge. In this study, we aimed to establish a radiomics model integrating radiomics features derived from ultrasound (US) images with clinical characteristics for the assessment of renal fibrosis severity in CKD patients. METHODS A total of 160 patients with CKD who underwent kidney biopsy and renal US examination were prospectively enrolled. Patients were classified into the mild or moderate-severe fibrosis group based on pathology results. Radiomics features were extracted from the US images, and a radiomics signature was constructed using the maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) regression algorithms. Multivariable logistic regression was employed to construct the radiomics model, which incorporated the radiomics signature and the selected clinical variables. The established model was evaluated for discrimination, calibration, and clinical utility in the derivation cohort and internal cross-validation (CV) analysis, respectively. RESULTS The radiomics signature, consisting of nine identified fibrosis-related features, achieved moderate discriminatory ability with an area under the receiver operating characteristic curve (AUC) of 0.72 (95% confidence interval (CI) 0.64-0.79). By combining the radiomics signature with significant clinical risk factors, the radiomics model showed satisfactory discrimination performance, yielding an AUC of 0.85 (95% CI 0.79-0.91) in the derivation cohort and a mean AUC of 0.84 (95% CI 0.77-0.92) in the internal CV analysis. It also demonstrated fine accuracy via the calibration curve. Furthermore, the decision curve analysis indicated that the model was clinically useful. CONCLUSION The proposed radiomics model showed favorable performance in determining the individualized risk of moderate-severe renal fibrosis in patients with CKD, which may facilitate more effective clinical decision-making.
Collapse
Affiliation(s)
- Ziman Chen
- Department of Ultrasound, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
- Department of Health Technology and Informatics, Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Michael Tin Cheung Ying
- Department of Health Technology and Informatics, Hong Kong Polytechnic University, Kowloon, Hong Kong.
| | - Yingli Wang
- Ultrasound Department, EDAN Instruments, Inc., Shenzhen, China
| | - Jiaxin Chen
- Department of Ultrasound, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
| | - Chaoqun Wu
- Department of Ultrasound, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China
| | - Xinyang Han
- Department of Health Technology and Informatics, Hong Kong Polytechnic University, Kowloon, Hong Kong
| | - Zhongzhen Su
- Department of Ultrasound, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China.
| |
Collapse
|