Can natural language processing help differentiate inflammatory intestinal diseases in China? Models applying random forest and convolutional neural network approaches.

Journal: BMC medical informatics and decision making
PMID: 32993636

Abstract

BACKGROUND: Differentiating between ulcerative colitis (UC), Crohn's disease (CD) and intestinal tuberculosis (ITB) using endoscopy is challenging. We aimed to realize automatic differential diagnosis among these diseases through machine learning algorithms.

Authors

  • Yuanren Tong
    Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China.
  • Keming Lu
    Department of Automation, Tsinghua University, Beijing, Beijing, China.
  • Yingyun Yang
    Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China.
  • Ji Li
    Department of Biostatistics and Epidemiology, College of Public Health, University of Oklahoma Health Sciences Center, 801 NE 13th Street, CHB 203, Oklahoma City, OK 73104, x 30126.
  • Yucong Lin
    Center for Statistical Science, Tsinghua University, Beijing, Beijing, China; Department of Industrial Engineering, Tsinghua University, Beijing, Beijing, China.
  • Dong Wu
  • Aiming Yang
    Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China.
  • Yue Li
    School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, China.
  • Sheng Yu
    Medical College, Guangxi University of Science and Technology, Liuzhou, Guangxi, 545005, China.
  • Jiaming Qian
    Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China.

Keywords

External Resources

Popular Topics
Recent Journals