Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease
Objective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical...
Guardado en:
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/89db486264b0400d8e728b84e3b8044b |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:89db486264b0400d8e728b84e3b8044b |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:89db486264b0400d8e728b84e3b8044b2021-12-03T05:07:59ZClinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease2296-858X10.3389/fmed.2021.753055https://doaj.org/article/89db486264b0400d8e728b84e3b8044b2021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.753055/fullhttps://doaj.org/toc/2296-858XObjective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical image identification and clinical feature interpretation to assist radiologists in triage and diagnosis.Methods: The 3,463 CT images of pneumonia used in this multi-center retrospective study were divided into four categories: bacterial pneumonia (n = 507), fungal pneumonia (n = 126), common viral pneumonia (n = 777), and COVID-19 (n = 2,053). We used DL methods based on images to distinguish pulmonary infections. A machine learning (ML) model for risk interpretation was developed using key imaging (learned from the DL methods) and clinical features. The algorithms were evaluated using the areas under the receiver operating characteristic curves (AUCs).Results: The median AUC of DL models for differentiating pulmonary infection was 99.5% (COVID-19), 98.6% (viral pneumonia), 98.4% (bacterial pneumonia), 99.1% (fungal pneumonia), respectively. By combining chest CT results and clinical symptoms, the ML model performed well, with an AUC of 99.7% for SARS-CoV-2, 99.4% for common virus, 98.9% for bacteria, and 99.6% for fungus. Regarding clinical features interpreting, the model revealed distinctive CT characteristics associated with specific pneumonia: in COVID-19, ground-glass opacity (GGO) [92.5%; odds ratio (OR), 1.76; 95% confidence interval (CI): 1.71–1.86]; larger lesions in the right upper lung (75.0%; OR, 1.12; 95% CI: 1.03–1.25) with viral pneumonia; older age (57.0 years ± 14.2, OR, 1.84; 95% CI: 1.73–1.99) with bacterial pneumonia; and consolidation (95.8%, OR, 1.29; 95% CI: 1.05–1.40) with fungal pneumonia.Conclusion: For classifying common types of pneumonia and assessing the influential factors for triage, our AI system has shown promising results. Our ultimate goal is to assist clinicians in making quick and accurate diagnoses, resulting in the potential for early therapeutic intervention.Yu-han ZhangXiao-fei HuJie-chao MaXian-qi WangHao-ran LuoZi-feng WuShu ZhangDe-jun ShiYi-zhou YuXiao-ming QiuWen-bing ZengWen-bing ZengWei ChenJian WangFrontiers Media S.A.articlepulmonary infectious diseaseCOVID-19deep learningcomputed tomographypneumoniaMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
pulmonary infectious disease COVID-19 deep learning computed tomography pneumonia Medicine (General) R5-920 |
spellingShingle |
pulmonary infectious disease COVID-19 deep learning computed tomography pneumonia Medicine (General) R5-920 Yu-han Zhang Xiao-fei Hu Jie-chao Ma Xian-qi Wang Hao-ran Luo Zi-feng Wu Shu Zhang De-jun Shi Yi-zhou Yu Xiao-ming Qiu Wen-bing Zeng Wen-bing Zeng Wei Chen Jian Wang Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease |
description |
Objective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical image identification and clinical feature interpretation to assist radiologists in triage and diagnosis.Methods: The 3,463 CT images of pneumonia used in this multi-center retrospective study were divided into four categories: bacterial pneumonia (n = 507), fungal pneumonia (n = 126), common viral pneumonia (n = 777), and COVID-19 (n = 2,053). We used DL methods based on images to distinguish pulmonary infections. A machine learning (ML) model for risk interpretation was developed using key imaging (learned from the DL methods) and clinical features. The algorithms were evaluated using the areas under the receiver operating characteristic curves (AUCs).Results: The median AUC of DL models for differentiating pulmonary infection was 99.5% (COVID-19), 98.6% (viral pneumonia), 98.4% (bacterial pneumonia), 99.1% (fungal pneumonia), respectively. By combining chest CT results and clinical symptoms, the ML model performed well, with an AUC of 99.7% for SARS-CoV-2, 99.4% for common virus, 98.9% for bacteria, and 99.6% for fungus. Regarding clinical features interpreting, the model revealed distinctive CT characteristics associated with specific pneumonia: in COVID-19, ground-glass opacity (GGO) [92.5%; odds ratio (OR), 1.76; 95% confidence interval (CI): 1.71–1.86]; larger lesions in the right upper lung (75.0%; OR, 1.12; 95% CI: 1.03–1.25) with viral pneumonia; older age (57.0 years ± 14.2, OR, 1.84; 95% CI: 1.73–1.99) with bacterial pneumonia; and consolidation (95.8%, OR, 1.29; 95% CI: 1.05–1.40) with fungal pneumonia.Conclusion: For classifying common types of pneumonia and assessing the influential factors for triage, our AI system has shown promising results. Our ultimate goal is to assist clinicians in making quick and accurate diagnoses, resulting in the potential for early therapeutic intervention. |
format |
article |
author |
Yu-han Zhang Xiao-fei Hu Jie-chao Ma Xian-qi Wang Hao-ran Luo Zi-feng Wu Shu Zhang De-jun Shi Yi-zhou Yu Xiao-ming Qiu Wen-bing Zeng Wen-bing Zeng Wei Chen Jian Wang |
author_facet |
Yu-han Zhang Xiao-fei Hu Jie-chao Ma Xian-qi Wang Hao-ran Luo Zi-feng Wu Shu Zhang De-jun Shi Yi-zhou Yu Xiao-ming Qiu Wen-bing Zeng Wen-bing Zeng Wei Chen Jian Wang |
author_sort |
Yu-han Zhang |
title |
Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease |
title_short |
Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease |
title_full |
Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease |
title_fullStr |
Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease |
title_full_unstemmed |
Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease |
title_sort |
clinical applicable ai system based on deep learning algorithm for differentiation of pulmonary infectious disease |
publisher |
Frontiers Media S.A. |
publishDate |
2021 |
url |
https://doaj.org/article/89db486264b0400d8e728b84e3b8044b |
work_keys_str_mv |
AT yuhanzhang clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT xiaofeihu clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT jiechaoma clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT xianqiwang clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT haoranluo clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT zifengwu clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT shuzhang clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT dejunshi clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT yizhouyu clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT xiaomingqiu clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT wenbingzeng clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT wenbingzeng clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT weichen clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease AT jianwang clinicalapplicableaisystembasedondeeplearningalgorithmfordifferentiationofpulmonaryinfectiousdisease |
_version_ |
1718373943670210560 |