A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage
IntroductionStroke-associated pneumonia (SAP) is a common complication of stroke that can increase the mortality rate of patients and the burden on their families. In contrast to prior clinical scoring models that rely on baseline data, we propose constructing models based on brain CT scans due to t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1139048/full |
| _version_ | 1827935527083442176 |
|---|---|
| author | Guangtong Yang Min Xu Wei Chen Xu Qiao Hongfeng Shi Yongmei Hu |
| author_facet | Guangtong Yang Min Xu Wei Chen Xu Qiao Hongfeng Shi Yongmei Hu |
| author_sort | Guangtong Yang |
| collection | DOAJ |
| description | IntroductionStroke-associated pneumonia (SAP) is a common complication of stroke that can increase the mortality rate of patients and the burden on their families. In contrast to prior clinical scoring models that rely on baseline data, we propose constructing models based on brain CT scans due to their accessibility and clinical universality.MethodsOur study aims to explore the mechanism behind the distribution and lesion areas of intracerebral hemorrhage (ICH) in relation to pneumonia, we utilized an MRI atlas that could present brain structures and a registration method in our program to extract features that may represent this relationship. We developed three machine learning models to predict the occurrence of SAP using these features. Ten-fold cross-validation was applied to evaluate the performance of models. Additionally, we constructed a probability map through statistical analysis that could display which brain regions are more frequently impacted by hematoma in patients with SAP based on four types of pneumonia.ResultsOur study included a cohort of 244 patients, and we extracted 35 features that captured the invasion of ICH to different brain regions for model development. We evaluated the performance of three machine learning models, namely, logistic regression, support vector machine, and random forest, in predicting SAP, and the AUCs for these models ranged from 0.77 to 0.82. The probability map revealed that the distribution of ICH varied between the left and right brain hemispheres in patients with moderate and severe SAP, and we identified several brain structures, including the left-choroid-plexus, right-choroid-plexus, right-hippocampus, and left-hippocampus, that were more closely related to SAP based on feature selection. Additionally, we observed that some statistical indicators of ICH volume, such as mean and maximum values, were proportional to the severity of SAP.DiscussionOur findings suggest that our method is effective in classifying the development of pneumonia based on brain CT scans. Furthermore, we identified distinct characteristics, such as volume and distribution, of ICH in four different types of SAP. |
| first_indexed | 2024-03-13T07:56:06Z |
| format | Article |
| id | doaj.art-5b5469ee862948c69d76aa818801c384 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-03-13T07:56:06Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-5b5469ee862948c69d76aa818801c3842023-06-02T04:59:35ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-06-011410.3389/fneur.2023.11390481139048A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhageGuangtong Yang0Min Xu1Wei Chen2Xu Qiao3Hongfeng Shi4Yongmei Hu5School of Control Science and Engineering, Shandong University, Jinan, ChinaNeurointensive Care Unit, Shengli Oilfield Central Hospital, Dongying, ChinaDepartment of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, ChinaSchool of Control Science and Engineering, Shandong University, Jinan, ChinaNeurointensive Care Unit, Shengli Oilfield Central Hospital, Dongying, ChinaSchool of Control Science and Engineering, Shandong University, Jinan, ChinaIntroductionStroke-associated pneumonia (SAP) is a common complication of stroke that can increase the mortality rate of patients and the burden on their families. In contrast to prior clinical scoring models that rely on baseline data, we propose constructing models based on brain CT scans due to their accessibility and clinical universality.MethodsOur study aims to explore the mechanism behind the distribution and lesion areas of intracerebral hemorrhage (ICH) in relation to pneumonia, we utilized an MRI atlas that could present brain structures and a registration method in our program to extract features that may represent this relationship. We developed three machine learning models to predict the occurrence of SAP using these features. Ten-fold cross-validation was applied to evaluate the performance of models. Additionally, we constructed a probability map through statistical analysis that could display which brain regions are more frequently impacted by hematoma in patients with SAP based on four types of pneumonia.ResultsOur study included a cohort of 244 patients, and we extracted 35 features that captured the invasion of ICH to different brain regions for model development. We evaluated the performance of three machine learning models, namely, logistic regression, support vector machine, and random forest, in predicting SAP, and the AUCs for these models ranged from 0.77 to 0.82. The probability map revealed that the distribution of ICH varied between the left and right brain hemispheres in patients with moderate and severe SAP, and we identified several brain structures, including the left-choroid-plexus, right-choroid-plexus, right-hippocampus, and left-hippocampus, that were more closely related to SAP based on feature selection. Additionally, we observed that some statistical indicators of ICH volume, such as mean and maximum values, were proportional to the severity of SAP.DiscussionOur findings suggest that our method is effective in classifying the development of pneumonia based on brain CT scans. Furthermore, we identified distinct characteristics, such as volume and distribution, of ICH in four different types of SAP.https://www.frontiersin.org/articles/10.3389/fneur.2023.1139048/fullimage registrationintracerebral hemorrhagestroke-associated pneumoniamachine learningstatistical analysis |
| spellingShingle | Guangtong Yang Min Xu Wei Chen Xu Qiao Hongfeng Shi Yongmei Hu A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage Frontiers in Neurology image registration intracerebral hemorrhage stroke-associated pneumonia machine learning statistical analysis |
| title | A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage |
| title_full | A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage |
| title_fullStr | A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage |
| title_full_unstemmed | A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage |
| title_short | A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage |
| title_sort | brain ct based approach for predicting and analyzing stroke associated pneumonia from intracerebral hemorrhage |
| topic | image registration intracerebral hemorrhage stroke-associated pneumonia machine learning statistical analysis |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1139048/full |
| work_keys_str_mv | AT guangtongyang abrainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT minxu abrainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT weichen abrainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT xuqiao abrainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT hongfengshi abrainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT yongmeihu abrainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT guangtongyang brainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT minxu brainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT weichen brainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT xuqiao brainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT hongfengshi brainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage AT yongmeihu brainctbasedapproachforpredictingandanalyzingstrokeassociatedpneumoniafromintracerebralhemorrhage |