MedicGo
Mining incomplete clinical data for the early assessment of Kawasaki disease based on feature clustering and convolutional neural networks.
Metadata
Journalartificial intelligence in medicine4.383Date
2020 May 03
5 months ago
Type
Research Support, Non-U.S. Gov't
Journal Article
Volume
2020-05 / 105 : 101859
Author
Wang H 1, Tan X 2, Huang Z 3, Pan B 3, Tian J 4
Affiliation
  • 2. Department of Pediatric, People's Hospital of Hongan, Hubei, 438401, China.
  • 3. Department of Heart Centre, Children's Hospital of Chongqing Medical University, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing, 400014, China.
  • 4. Department of Heart Centre, Children's Hospital of Chongqing Medical University, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing, 400014, China. Electronic address: [email protected]
Doi
PMIDMESH
Abstract
Kawasaki disease (KD) is the leading cause of acquired heart disease in children. Its prompt treatment can effectively lower the risk of severe complications, such as coronary aneurysms. However, accurately diagnosing KD at its early stage is impracticable given its unknown pathogenesis and lack of pathognomonic features. In this study, we investigated data-driven approaches by using a cohort of 10,367 patients extracted from electronic health records for early KD assessment. The incompleteness of clinical data presents group-based missing patterns associated with different clinical assessment measures. To address this problem, we developed a method integrating feature clustering to enable matrix-based representation and convolutional neural networks (CNN) for feature extraction and fusion to explicitly exploit the multi-source data structure. Integrating missing data imputation methods with the proposed method demonstrated superior accuracy (an AUC of 0.97) compared with a number of benchmark methods. The present method shows potential to improve clinical data mining. Our study highlighted the feasible utilization of matrix-based feature representation and CNN-based feature extraction for incomplete clinical data mining to support medical decision-making.
Keywords: Clinical data mining Convolutional neural networks Electronic health records Medical decision making
Fav
Like
Download
Share
Export
Cite
4.4
Artif Intell Medartificial intelligence in medicine
Metadata
LocationNetherlands
FromELSEVIER

No Data

© 2017 - 2020 Medicgo
Powered by some medical students