Prediction of New-Onset Diabetes After Pancreatectomy With Subspace Clustering Based Multi-View Feature Selection
- 2 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (3) , 1588-1599
Abstract
The pancreas plays an important role in glucose metabolism, and developing diabetes or long-term glucose metabolism disturbance may be a prevalent sequela after pancreatectomy. Nevertheless, relative factors of new-onset diabetes after pancreatectomy stay unclear. Radiomics analysis is potential to identify image markers for disease prediction or prognosis. Meanwhile, combination of imaging and electronic medical record (EMR) showed superior performance than imaging or EMR alone in previous studies. One critical step is to identity predictors from high-dimensional features, and it is even more challenging to select and fuse imaging and EMR features. In this work, we develop a radiomics pipeline to assess postoperative new-onset diabetes risk of patients undergoing distal pancreatectomy. Specifically, we extract multiscale image features with 3D wavelet transformation, and include patients' characteristics, body composition and pancreas volume information as clinical features. Then, we propose a multi-view subspace clustering guided feature selection method (MSCUFS) for the selection and fusion of image and clinical features. Finally, a prediction model is constructed with classical machine learning classifier. Experimental results on an established distal pancreatectomy cohort showed that the SVM model with combined imaging and EMR features demonstrated good discrimination, with an AUC value of 0.824, which improved the model with image features alone by 0.037 AUC. Compared with state-of-the-art feature selection methods, the proposed MSCUFS has superior performance in fusing image and clinical features.Keywords
Funding Information
- National Natural Science Foundation of China (12101571, 82071867, 81871925, 82071916)
- Zhejiang Provincial Natural Science Foundation of China (LQ20H180001)
- Fundamental Research Funds for the Zhejiang Provincial Universities (2021XZZX031)
- Key Research and Development Project of Zhejiang Province (2020C03117)
- Postdoctoral Research from Zhejiang Province (ZJ2020029)
- Key Research Project of Zhejiang Laboratory (2022ND0AC01)
This publication has 38 references indexed in Scilit:
- Subspace clustering guided unsupervised feature selectionPattern Recognition, 2017
- A machine learning-based framework to identify type 2 diabetes through electronic health recordsInternational Journal of Medical Informatics, 2017
- Electronic health record phenotyping improves detection and screening of type 2 diabetes in the general United States population: A cross-sectional, unselected, retrospective studyJournal of Biomedical Informatics, 2016
- Multi-view Subspace Clustering2015
- Body Composition Assessment in Axial CT Images Using FEM-Based Automatic Segmentation of Skeletal MuscleIEEE Transactions on Medical Imaging, 2015
- Endocrine Function Impairment After Distal Pancreatectomy: Incidence and Related FactorsWorld Journal of Surgery, 2015
- Impact of preoperative quality as well as quantity of skeletal muscle on survival after resection of pancreatic cancerSurgery, 2015
- Sparse Subspace Clustering: Algorithm, Theory, and ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- On a Theorem of Weyl Concerning Eigenvalues of Linear Transformations IProceedings of the National Academy of Sciences, 1949