Can Clinical Symptoms and Laboratory Results Predict CT Abnormality? Initial Findings Using Novel Machine Learning Techniques in Children With COVID-19 Infections

Frontiers in Medicine

Wade Menpes-Smith¹  Chengjia Wang²  Jianbo Shao³  Guang Yang⁴  Evandro Fei Fang⁵  Jun Xia⁶  Yuan Gao⁷  Yinghui Jiang⁸  Qinghao Ye⁸  Minhao Wang⁸  Huijing Ma⁹  Xi Zhou^1,10  Zhangming Niu^1,11  Weiping Ding^1,12 

[1] Aladdin Healthcare Technologies Ltd, London, United Kingdom;British Heart Foundation (BHF) Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom;COVID-19 Specialist Team, Wuhan Children's Hospital, Tongji Medical College, Huazhong University of Science & Technology, Wuhan, China;Cardiovascular Research Centre, Royal Brompton Hospital, London, United Kingdom;National Heart and Lung Institute, Imperial College London, London, United Kingdom;Department of Clinical Molecular Biology, University of Oslo, Oslo, Norway;Department of Radiology, Shenzhen Second People's Hospital, The First Affiliated Hospital of Shenzhen University Health Science Center, Shenzhen, China;Department of Radiology, Shenzhen Second People's Hospital, The First Affiliated Hospital of Shenzhen University Health Science Center, Shenzhen, China;Aladdin Healthcare Technologies Ltd, London, United Kingdom;Hangzhou Ocean's Smart Boya Co., Ltd, Hangzhou, China;Mind Rank Ltd, Hong Kong, China;Imaging Center, Tongji Medical College, Wuhan Children's Hospital (Wuhan Maternal and Child Healthcare Hospital), Huazhong University of Science & Technology, Wuhan, China;Institute of Biomedical Engineering, University of Oxford, Oxford, United Kingdom;Mind Rank Ltd, Hong Kong, China;School of Information Science and Technology, Nantong University, Nantong, China;

关键词: COVID-19;    decision trees;    machine learning;    RT-PCR—polymerase chain reaction with reverse transcription;    artificial intelligence;    pediatric;   

DOI  :  10.3389/fmed.2021.699984

来源: Frontiers

【 摘 要 】

The rapid spread of coronavirus 2019 disease (COVID-19) has manifested a global public health crisis, and chest CT has been proven to be a powerful tool for screening, triage, evaluation and prognosis in COVID-19 patients. However, CT is not only costly but also associated with an increased incidence of cancer, in particular for children. This study will question whether clinical symptoms and laboratory results can predict the CT outcomes for the pediatric patients with positive RT-PCR testing results in order to determine the necessity of CT for such a vulnerable group. Clinical data were collected from 244 consecutive pediatric patients (16 years of age and under) treated at Wuhan Children's Hospital with positive RT-PCR testing, and the chest CT were performed within 3 days of clinical data collection, from January 21 to March 8, 2020. This study was approved by the local ethics committee of Wuhan Children's Hospital. Advanced decision tree based machine learning models were developed for the prediction of CT outcomes. Results have shown that age, lymphocyte, neutrophils, ferritin and C-reactive protein are the most related clinical indicators for predicting CT outcomes for pediatric patients with positive RT-PCR testing. Our decision support system has managed to achieve an AUC of 0.84 with 0.82 accuracy and 0.84 sensitivity for predicting CT outcomes. Our model can effectively predict CT outcomes, and our findings have indicated that the use of CT should be reconsidered for pediatric patients, as it may not be indispensable.

【 授权许可】

CC BY