Automated machine learning for the identification of asymptomatic COVID-19 carriers based on chest CT images.

Publication date: Feb 27, 2024

Asymptomatic COVID-19 carriers with normal chest computed tomography (CT) scans have perpetuated the ongoing pandemic of this disease. This retrospective study aimed to use automated machine learning (AutoML) to develop a prediction model based on CT characteristics for the identification of asymptomatic carriers. Asymptomatic carriers were from Yangzhou Third People’s Hospital from August 1st, 2020, to March 31st, 2021, and the control group included a healthy population from a nonepizootic area with two negative RT‒PCR results within 48 h. All CT images were preprocessed using MATLAB. Model development and validation were conducted in R with the H2O package. The models were built based on six algorithms, e. g., random forest and deep neural network (DNN), and a training set (n = 691). The models were improved by automatically adjusting hyperparameters for an internal validation set (n = 306). The performance of the obtained models was evaluated based on a dataset from Suzhou (n = 178) using the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score. A total of 1,175 images were preprocessed with high stability. Six models were developed, and the performance of the DNN model ranked first, with an AUC value of 0. 898 for the test set. The sensitivity, specificity, PPV, NPV, F1 score and accuracy of the DNN model were 0. 820, 0. 854, 0. 849, 0. 826, 0. 834 and 0. 837, respectively. A plot of a local interpretable model-agnostic explanation demonstrated how different variables worked in identifying asymptomatic carriers. Our study demonstrates that AutoML models based on CT images can be used to identify asymptomatic carriers. The most promising model for clinical implementation is the DNN-algorithm-based model.

Open Access PDF

Concepts Keywords
Agnostic Asymptomatic
August Automated machine learning
Predictive Prediction model


Type Source Name
disease MESH COVID-19
disease VO population
disease IDO algorithm
pathway REACTOME Reproduction
drug DRUGBANK Coenzyme M
disease MESH common cold
disease MESH infections
disease MESH pneumonia
disease MESH atelectasis
drug DRUGBANK Gold
disease IDO asymptomatic carrier
disease MESH asymptomatic infections
drug DRUGBANK Trestolone
disease MESH viral pneumonia
disease VO volume
disease MESH abnormalities
disease MESH mycoplasma pneumonia
disease MESH pulmonary emphysema
disease MESH tuberculosis
pathway KEGG Tuberculosis
disease MESH bronchiectasis
disease IDO infection
drug DRUGBANK Flunarizine
disease VO document
disease IDO process
drug DRUGBANK Saquinavir
drug DRUGBANK L-Valine
drug DRUGBANK Ademetionine
disease IDO symptom
disease VO efficient
disease VO time
drug DRUGBANK L-Citrulline
drug DRUGBANK Indoleacetic acid
disease VO organization
disease MESH Coronavirus infections
drug DRUGBANK Guanosine
drug DRUGBANK Nonoxynol-9
disease MESH hepatocellular carcinoma
pathway KEGG Hepatocellular carcinoma
disease MESH cognitive decline
disease MESH Interstitial pneumonia
disease MESH pulmonary fibrosis
disease MESH emphysema
disease MESH syndrome
disease MESH connective tissue disease
disease MESH idiopathic pulmonary fibrosis

Original Article

(Visited 1 times, 1 visits today)