Your browser doesn't support javascript.
loading
Accurately Differentiating COVID-19, Other Viral Infection, and Healthy Individuals Using Multimodal Features via Late Fusion Learning
Ming Xu; Liu Ouyang; Yan Gao; Yuanfang Chen; Tingting Yu; Qian Li; Kai Sun; Forrest S Bao; Lida Safarnejad; Jing Wen; Chao Jiang; Tianyang Chen; Lei Han; Hengdong Zhang; Yue Gao; Zhengmin Yu; Xiaowen Liu; Tianyu Yan; Hebi Li; Patrick Robinson; Baoli Zhu; Jie Liu; Yang Liu; Zengli Zhang; Yaorong Ge; Shi Chen.
Afiliação
  • Ming Xu; Department of Occupational Disease Prevention, Jiangsu Provincial Center for Disease Control and Prevention, Nanjing 210009, China
  • Liu Ouyang; Department of Orthopedics, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
  • Yan Gao; Institute of Suzhou Biobank, Suzhou Center for Disease Prevention and Control, Suzhou 215004, China
  • Yuanfang Chen; Public Health Research Institute of Jiangsu Province, Nanjing 210009, China
  • Tingting Yu; Department of Medical Genetics, School of Basic Medical Science Jiangsu Key Laboratory of Xenotransplantation, Nanjing Medical University, Nanjing 211166, China
  • Qian Li; Department of Pediatrics, Affiliated Kunshan Hospital of Jiangsu University, Kunshan 215300, China
  • Kai Sun; Department of Emergency Medicine, the First Hospital with Nanjing Medical University, Nanjing 210009, China
  • Forrest S Bao; Department of Computer Science, Iowa State University, Ames, IA, 50011, USA
  • Lida Safarnejad; Department of Software and Information Systems, College of Computing and Informatics, University of North Carolina Charlotte, Charlotte, NC 28223
  • Jing Wen; Ultrasound Center, Affiliated Hospital of Guizhou Medical University, Guiyang 550004, China
  • Chao Jiang; Department of Public Health, School of Medicine and Life Science, Nanjing University of Chinese Medicine, Nanjing 210046, China
  • Tianyang Chen; Center for Applied Geographic Information Science, University of North Carolina Charlotte, Charlotte 28262, USA
  • Lei Han; Public Health Research Institute of Jiangsu Province, Nanjing 210009, China
  • Hengdong Zhang; Public Health Research Institute of Jiangsu Province, Nanjing 210009, China
  • Yue Gao; Public Health Research Institute of Jiangsu Province, Nanjing 210009, China
  • Zhengmin Yu; Public Health Research Institute of Jiangsu Province, Nanjing 210009, China
  • Xiaowen Liu; Public Health Research Institute of Jiangsu Province, Nanjing 210009, China
  • Tianyu Yan; Department of Chemical Engineering, Pennsylvania State University, University Park, Pennsylvania 16802, USA
  • Hebi Li; Department of Computer Science, Iowa State University, Ames, IA, 50011, USA
  • Patrick Robinson; Department of Public Health Sciences, College of Health and Human Services, University of North Carolina Charlotte, Charlotte, NC 28223, USA
  • Baoli Zhu; Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, China
  • Jie Liu; Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
  • Yang Liu; School of Pharmacy, Nanjing Medical University, Nanjing 211166, Jiangsu, China
  • Zengli Zhang; Department of Occupational and Environmental Health, School of Public Health, Medical College of Soochow University, Suzhou 215123, China
  • Yaorong Ge; Department of Software and Information Systems, College of Computing and Informatics, University of North Carolina Charlotte, Charlotte, NC 28223, USA
  • Shi Chen; UNC Charlotte
Preprint em Inglês | medRxiv | ID: ppmedrxiv-20176776
ABSTRACT
Effectively identifying COVID-19 patients using non-PCR clinical data is critical for the optimal clinical outcomes. Currently, there is a lack of comprehensive understanding of various biomedical features and appropriate technical approaches to accurately detecting COVID-19 patients. In this study, we recruited 214 confirmed COVID-19 patients in non-severe (NS) and 148 in severe (S) clinical type, 198 non-infected healthy (H) participants and 129 non-COVID viral pneumonia (V) patients. The participants clinical information (23 features), lab testing results (10 features), and thoracic CT scans upon admission were acquired as three input feature modalities. To enable late fusion of multimodality data, we developed a deep learning model to extract a 10-feature high-level representation of the CT scans. Exploratory analyses showed substantial differences of all features among the four classes. Three machine learning models (k-nearest neighbor kNN, random forest RF, and support vector machine SVM) were developed based on the 43 features combined from all three modalities to differentiate four classes (NS, S, V, and H) at once. All three models had high accuracy to differentiate the overall four classes (95.4%-97.7%) and each individual class (90.6%-99.9%). Multimodal features provided substantial performance gain from using any single feature modality. Compared to existing binary classification benchmarks often focusing on single feature modality, this study provided a novel and effective breakthrough for clinical applications. Findings and the analytical workflow can be used as clinical decision support for current COVID-19 and other clinical applications with high-dimensional multimodal biomedical features. One sentence summaryWe trained and validated late fusion deep learning-machine learning models to predict non-severe COVID-19, severe COVID-19, non-COVID viral infection, and healthy classes from clinical, lab testing, and CT scan features extracted from convolutional neural network and achieved predictive accuracy of > 96% to differentiate all four classes at once based on a large dataset of 689 participants.
Licença
cc_by_nc_nd
Texto completo: Disponível Coleções: Preprints Base de dados: medRxiv Tipo de estudo: Estudo prognóstico / Rct Idioma: Inglês Ano de publicação: 2020 Tipo de documento: Preprint
Texto completo: Disponível Coleções: Preprints Base de dados: medRxiv Tipo de estudo: Estudo prognóstico / Rct Idioma: Inglês Ano de publicação: 2020 Tipo de documento: Preprint
...