Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors

The study focused on the application value of classification algorithms in processing CT images of acute respiratory distress syndrome (ARDS) and aimed to analyze the pathogenic factors of ARDS. A total of 60 ARDS patients in hospital were selected, and they were divided into ARDS group (38 cases) a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Liang Chen, Qiong Li
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/df8afc67acab4d7597e8204b469ffdb8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:df8afc67acab4d7597e8204b469ffdb8
record_format	dspace
spelling	oai:doaj.org-article:df8afc67acab4d7597e8204b469ffdb82021-11-22T01:11:03ZClassification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors1875-919X10.1155/2021/4100856https://doaj.org/article/df8afc67acab4d7597e8204b469ffdb82021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/4100856https://doaj.org/toc/1875-919XThe study focused on the application value of classification algorithms in processing CT images of acute respiratory distress syndrome (ARDS) and aimed to analyze the pathogenic factors of ARDS. A total of 60 ARDS patients in hospital were selected, and they were divided into ARDS group (38 cases) and non-ARDS group (22 cases) as per diagnostic criteria. There was no significant difference in general data between the two groups (P>0.05). The FWAC algorithm was introduced into CT imaging to classify the image data more accurately. The two groups were compared for the left ventricular ejection fraction (LVEF), oxygenation index PaO2/FiO2 (P/F), Acute Physiology and Chronic Health Evaluation (APACHE II) scores, pH, and PaO2. The results showed that the PaO2, P/F, and APACHE II scores of the two groups were not statistically significant (P>0.05). The P/F of the ARDS group was 136.12, and that of the non-ARDS group was 143.04; the APACHE II score of the ARDS group was 40.1, and that of the non-ARDS group was 62.3, showing no significant difference (P>0.05); the LVEF of the ARDS group was 58.14, and that of the non-ARDS group was 46.26, showing statistically significant differences (P>0.05). When the minimum support was 0.3 and the minimum confidence was 0.5, the value of Recurrence was 0.7082 and the value of Diagnosis was 0.968. The rules generated by the FWAC algorithm can accurately predict the category and were consistent with the expected results. The accuracy of this algorithm was as high as 98.7%, which was significantly higher than that of the conventional CT imaging (88.4%). The rules generated by FWAC were more accurate, assisting doctors in the prevention and diagnosis of ARDS disease. Premature delivery and asphyxia are high-risk factors of ARDS. In conclusion, the FWAC algorithm has a good classification ability of the CT images of ARDS and demonstrates high accuracy.Liang ChenQiong LiHindawi LimitedarticleComputer softwareQA76.75-76.765ENScientific Programming, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer software QA76.75-76.765
spellingShingle	Computer software QA76.75-76.765 Liang Chen Qiong Li Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors
description	The study focused on the application value of classification algorithms in processing CT images of acute respiratory distress syndrome (ARDS) and aimed to analyze the pathogenic factors of ARDS. A total of 60 ARDS patients in hospital were selected, and they were divided into ARDS group (38 cases) and non-ARDS group (22 cases) as per diagnostic criteria. There was no significant difference in general data between the two groups (P>0.05). The FWAC algorithm was introduced into CT imaging to classify the image data more accurately. The two groups were compared for the left ventricular ejection fraction (LVEF), oxygenation index PaO2/FiO2 (P/F), Acute Physiology and Chronic Health Evaluation (APACHE II) scores, pH, and PaO2. The results showed that the PaO2, P/F, and APACHE II scores of the two groups were not statistically significant (P>0.05). The P/F of the ARDS group was 136.12, and that of the non-ARDS group was 143.04; the APACHE II score of the ARDS group was 40.1, and that of the non-ARDS group was 62.3, showing no significant difference (P>0.05); the LVEF of the ARDS group was 58.14, and that of the non-ARDS group was 46.26, showing statistically significant differences (P>0.05). When the minimum support was 0.3 and the minimum confidence was 0.5, the value of Recurrence was 0.7082 and the value of Diagnosis was 0.968. The rules generated by the FWAC algorithm can accurately predict the category and were consistent with the expected results. The accuracy of this algorithm was as high as 98.7%, which was significantly higher than that of the conventional CT imaging (88.4%). The rules generated by FWAC were more accurate, assisting doctors in the prevention and diagnosis of ARDS disease. Premature delivery and asphyxia are high-risk factors of ARDS. In conclusion, the FWAC algorithm has a good classification ability of the CT images of ARDS and demonstrates high accuracy.
format	article
author	Liang Chen Qiong Li
author_facet	Liang Chen Qiong Li
author_sort	Liang Chen
title	Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors
title_short	Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors
title_full	Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors
title_fullStr	Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors
title_full_unstemmed	Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors
title_sort	classification algorithm-based ct imaging in diagnosis of acute respiratory distress syndrome and analysis of pathogenic factors
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/df8afc67acab4d7597e8204b469ffdb8
work_keys_str_mv	AT liangchen classificationalgorithmbasedctimagingindiagnosisofacuterespiratorydistresssyndromeandanalysisofpathogenicfactors AT qiongli classificationalgorithmbasedctimagingindiagnosisofacuterespiratorydistresssyndromeandanalysisofpathogenicfactors
_version_	1718418373580161024

Classification Algorithm-Based CT Imaging in Diagnosis of Acute Respiratory Distress Syndrome and Analysis of Pathogenic Factors

Ejemplares similares