A brain CT-based approach for predicting and analyzing stroke-associated pneumonia from intracerebral hemorrhage

Abstract

Introduction: Stroke-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.

Methods: Our 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.

Results: Our 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.

Discussion: Our 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.

Keywords: image registration; intracerebral hemorrhage; machine learning; statistical analysis; stroke-associated pneumonia.

Figure 1

Research workflow of this study.

Figure 2

Images utilized in this paper. (A) Brain MRI used in the registration as a reference image. (B) Brain anatomical structure MRI having 35 regions. (C) One brain CT sample with ICH area labeled. (D) Transformed bleeding image shown with brain anatomical image. (E) Three-dimensional schematic diagram of the anatomical structure of the brain.

Figure 3

Resulted images of preprocess and registration.

Figure 4

ROC curves of the random forest model. (A) For predicting SAP. (B) For predicting SAP above the moderate level.

Figure 5

The box plot of the ratio of bleeding volume to total volume based on four SAP types.

Figure 6

Bleeding probability map of four types of pneumonia. (A) Severe pneumonia. (B) Moderate pneumonia. (C) Mild pneumonia. (D) No pneumonia.

Figure 7

Feature weights of the logistic regression model. (A) For predicting SAP. (B) For predicting SAP above the moderate level.