Congenital heart disease detection by pediatric electrocardiogram based deep learning integrated with human concepts.

Journal: Nature communications
PMID: 38302502

Abstract

Early detection is critical to achieving improved treatment outcomes for child patients with congenital heart diseases (CHDs). Therefore, developing effective CHD detection techniques using low-cost and non-invasive pediatric electrocardiogram are highly desirable. We propose a deep learning approach for CHD detection, CHDdECG, which automatically extracts features from pediatric electrocardiogram and wavelet transformation characteristics, and integrates them with key human-concept features. Developed on 65,869 cases, CHDdECG achieved ROC-AUC of 0.915 and specificity of 0.881 on a real-world test set covering 12,000 cases. Additionally, on two external test sets with 7137 and 8121 cases, the overall ROC-AUC were 0.917 and 0.907 while specificities were 0.937 and 0.907. Notably, CHDdECG surpassed cardiologists in CHD detection performance comparison, and feature importance scores suggested greater influence of automatically extracted electrocardiogram features on CHD detection compared with human-concept features, implying that CHDdECG may grasp some knowledge beyond human cognition. Our study directly impacts CHD detection with pediatric electrocardiogram and demonstrates the potential of pediatric electrocardiogram for broader benefits.

Authors

  • Jintai Chen
  • Shuai Huang
    Department of Industrial and Systems Engineering, University of Washington, Seattle, WA 98195 USA.
  • Ying Zhang
    Department of Nephrology, Nanchong Central Hospital Affiliated to North Sichuan Medical College, Nanchong, China.
  • Qing Chang
    Department of Ultrasound, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China.
  • Yixiao Zhang
    Computational Cognition, Vision, and Learning (CCVL), Johns Hopkins University, Baltimore, MD, USA.
  • Dantong Li
    Medical Big Data Center, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, China.
  • Jia Qiu
    Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 510080, Guangzhou, Guangdong Province, China.
  • Lianting Hu
    Medical Big Data Center, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangdong, China.
  • Xiaoting Peng
    Medical Big Data Center, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 510080, Guangzhou, Guangdong Province, China.
  • Yunmei Du
    College of Information Technology and Engineering, Guangzhou College of Commerce, 510363, Guangzhou, Guangdong Province, China.
  • Yunfei Gao
    Zhuhai Precision Medical Center, Zhuhai People's Hospital/ Zhuhai Hospital Affiliated with Jinan University, Jinan University, 519000, Zhuhai, Guangdong Province, China.
  • Danny Z Chen
    Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN 46556.
  • Abdelouahab Bellou
    Institute of Sciences in Emergency Medicine, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, 510080, Guangzhou, China. abellou402@gmail.com.
  • Jian Wu
    Department of Medical Technology, Jiangxi Medical College, Shangrao, Jiangxi, China.
  • Huiying Liang
    Institute of Pediatrics, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China.

Keywords

External Resources

Popular Topics
Recent Journals