Severe brain atrophy in the elderly as a risk factor for lower respiratory tract infection

Development and validation of radiology-clinical statistical and machine learning model for stroke-associated pneumonia after first intracerebral haemorrhage

BACKGROUND

Society is burdened with stroke-associated pneumonia (SAP) after intracerebral haemorrhage (ICH). Cerebral small vessel disease (CSVD) complicates clinical manifestations of stroke. In this study, we redefined the CSVD burden score and incorporated it into a novel radiological-clinical prediction model for SAP.

MATERIALS AND METHODS

A total of 1278 patients admitted to a tertiary hospital between 1 January 2010 and 31 December 2019 were included. The participants were divided into training and testing groups using fivefold cross-validation method. Four models, two traditional statistical models (logistic regression and ISAN) and two machine learning models (random forest and support vector machine), were established and evaluated. The outcomes and baseline characteristics were compared between the SAP and non-SAP groups.

RESULTS

Among the of 1278 patients, 281(22.0%) developed SAP after their first ICH. Multivariate analysis revealed that the logistic regression (LR) model was superior in predicting SAP in both the training and testing groups. Independent predictors of SAP after ICH included total CSVD burden score (OR, 1.29; 95% CI, 1.03-1.54), haematoma extension into ventricle (OR, 2.28; 95% CI, 1.87-3.31), haematoma with multilobar involvement (OR, 2.14; 95% CI, 1.44-3.18), transpharyngeal intubation operation (OR, 3.89; 95% CI, 2.7-5.62), admission NIHSS score ≥ 10 (OR, 2.06; 95% CI, 1.42-3.01), male sex (OR, 1.69; 95% CI, 1.16-2.52), and age ≥ 67 (OR, 2.24; 95% CI, 1.56-3.22). The patients in the SAP group had worse outcomes than those in the non-SAP group.

CONCLUSION

This study established a clinically combined imaging model for predicting stroke-associated pneumonia and demonstrated superior performance compared with the existing ISAN model. Given the poor outcomes observed in patients with SAP, the use of individualised predictive nomograms is vital in clinical practice.

Feasibility of a clinical-radiomics combined model to predict the occurrence of stroke-associated pneumonia

PURPOSE

To explore the predictive value of radiomics in predicting stroke-associated pneumonia (SAP) in acute ischemic stroke (AIS) patients and construct a prediction model based on clinical features and DWI-MRI radiomics features.

METHODS

Univariate and multivariate logistic regression analyses were used to identify the independent clinical predictors for SAP. Pearson correlation analysis and the least absolute shrinkage and selection operator with ten-fold cross-validation were used to calculate the radiomics score for each feature and identify the predictive radiomics features for SAP. Multivariate logistic regression was used to combine the predictive radiomics features with the independent clinical predictors. The prediction performance of the SAP models was evaluated using receiver operating characteristics (ROC), calibration curves, decision curve analysis, and subgroup analyses.

RESULTS

Triglycerides, the neutrophil-to-lymphocyte ratio, dysphagia, the National Institutes of Health Stroke Scale (NIHSS) score, and internal carotid artery stenosis were identified as clinically independent risk factors for SAP. The radiomics scores in patients with SAP were generally higher than in patients without SAP (P < 0. 05). There was a linear positive correlation between radiomics scores and NIHSS scores, as well as between radiomics scores and infarct volume. Infarct volume showed moderate performance in predicting the occurrence of SAP, with an AUC of 0.635. When compared with the other models, the combined prediction model achieved the best area under the ROC (AUC) in both training (AUC = 0.859, 95% CI 0.759-0.936) and validation (AUC = 0.830, 95% CI 0.758-0.896) cohorts (P < 0.05). The calibration curves and decision curve analysis further confirmed the clinical value of the nomogram. Subgroup analysis showed that this nomogram had potential generalization ability.

CONCLUSION

The addition of the radiomics features to the clinical model improved the prediction of SAP in AIS patients, which verified its feasibility.

A2DS2 Score Combined With Clinical and Neuroimaging Factors Better Predicts Stroke-Associated Pneumonia in Hyperacute Cerebral Infarction

Objective

To investigate the predictors of stroke-associated pneumonia (SAP) and poor functional outcome in patients with hyperacute cerebral infarction (HCI) by combining clinical factors, laboratory tests and neuroimaging features.

Methods

We included 205 patients with HCI from November 2018 to December 2019. The diagnostic criterion for SAP was occurrence within 7 days of the onset of stroke. Poor outcome was defined as a functional outcome based on a 3-months MRS score >3. The relationship of demographic, laboratory and neuroimaging variables with SAP and poor outcome was investigated using univariate and multivariate analyses.

Results

Fifty seven (27.8%) patients were diagnosed with SAP and 40 (19.5%) developed poor outcomes. A²DS² score (OR = 1.284; 95% CI: 1.048–1.574; P = 0.016), previous stroke (OR = 2.630; 95% CI: 1.122–6.163; P = 0.026), consciousness (OR = 2.945; 95% CI: 1.514–5.729; P < 0.001), brain atrophy (OR = 1.427; 95% CI: 1.040–1.959; P = 0.028), and core infarct volume (OR = 1.715; 95% CI: 1.163–2.528; P = 0.006) were independently associated with the occurrence of SAP. Therefore, we combined these variables into a new SAP prediction model with the C-statistic of 0.84 (95% CI: 0.78–0.90). Fasting plasma glucose (OR = 1.404; 95% CI: 1.202–1.640; P < 0.001), NIHSS score (OR = 1.088; 95% CI: 1.010–1.172; P = 0.026), previous stroke (OR = 4.333; 95% CI: 1.645–11.418; P = 0.003), SAP (OR = 3.420; 95% CI: 1.332–8.787; P = 0.011), basal ganglia-dilated perivascular spaces (BG-dPVS) (OR = 2.124; 95% CI: 1.313–3.436; P = 0.002), and core infarct volume (OR = 1.680; 95% CI: 1.166–2.420; P = 0.005) were independently associated with poor outcome. The C-statistic of the outcome model was 0.87 (95% CI: 0.81–0.94). Furthermore, the SAP model significantly improved discrimination and net benefit more than the A²DS² scale, with a C-statistic of 0.76 (95% CI: 0.69–0.83).

Conclusions

After the addition of neuroimaging features, the models exhibit good differentiation and calibration for the prediction of the occurrence of SAP and the development of poor outcomes in HCI patients. The SAP model could better predict the SAP, representing a helpful and valid tool to obtain a net benefit compared with the A²DS² scale.