Multi-modal models using fMRI, urine and serum biomarkers for classification and risk prognosis in diabetic kidney disease.
Authors
Affiliations (6)
Affiliations (6)
- NHC Key Lab of Hormones and Development, Tianjin Key Lab of Metabolic Diseases, Tianjin Medical University Chu Hsien-I Memorial Hospital & Institute of Endocrinology, Tianjin, China.
- Division of Nephrology, National Clinical Research Center for Kidney Disease, State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China.
- School of Medical Information Engineering, Anhui University of Chinese Medicine, Hefei, China.
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Breast Tumor Center, Clinical Research Design Division, Clinical Research Center, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.
- WHO Collaborating Centre for Public Health Education and Training, School of Public Health, Department of Primary Care and Public Health, Faculty of Medicine, Imperial College London, London, UK.
- Department of Nephrology & Blood Purification Center, The Second Hospital of Tianjin Medical University, Tianjin, China.
Abstract
Functional magnetic resonance imaging (fMRI) is a powerful tool for non-invasive evaluation of micro-changes in the kidneys. This study aims to develop classification and prognostic models based on multi-modal data. A total of 172 participants were included, and high-resolution multi-parameter fMRI technology was employed to obtain T2-weighted imaging (T2WI), blood oxygen level dependent (BOLD), and diffusion tensor imaging (DTI) sequence images. Based on clinical indicators, fMRI markers, serum and urine biomarkers (CD300LF, CST4, MMRN2, SERPINA1, l-glutamic acid dimethyl ester and phosphatidylcholine), machine learning algorithms were applied to establish and validate classification diagnosis models (Models 1-6) and risk-prognostic models (Models A-E). Additionally, accuracy, sensitivity, specificity, precision, area under the curve (AUC) and recall were used to evaluate the predictive performance of the models. A total of six classification models were established. Model 5 (fMRI + clinical indicators) exhibited superior performance, with an accuracy of 0.833 (95% confidence interval [CI]: 0.653-0.944). Notably, the multi-modal model incorporating image, serum and urine multi-omics and clinical indicators (Model 6) demonstrated higher predictive performance, achieving an accuracy of 0.923 (95% CI: 0.749-0.991). Furthermore, a total of five prognostic models at 2-year and 3-year follow-up were established. The Model E exhibited superior performance, achieving AUC values of 0.975 at the 2-year follow-up and 0.932 at the 3-year follow-up. Furthermore, Model E can identify patients with a high-risk prognosis. In clinical practice, the multi-modal models presented in this study demonstrate potential to enhance clinical decision-making capabilities regarding patient classification and prognosis prediction.