Pre-Operative Predictors for Post-Operative Pneumonia in Aneurysmal Subarachnoid Hemorrhage After Surgical Clipping and Endovascular Coiling: A Single-Center Retrospective Study

Development and validation of a machine-learning model for predicting postoperative pneumonia in aneurysmal subarachnoid hemorrhage

Pneumonia is a common postoperative complication in patients with aneurysmal subarachnoid hemorrhage (aSAH), which is associated with poor prognosis and increased mortality. The aim of this study was to develop a predictive model for postoperative pneumonia (POP) in patients with aSAH. A retrospective analysis was conducted on 308 patients with aSAH who underwent surgery at the Neurosurgery Department of the First Affiliated Hospital of Soochow University. Univariate and multivariate logistic regression and lasso regression analysis were used to analyze the risk factors for POP. Receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the constructed model. Finally, the effectiveness of modeling these six variables in different machine learning methods was investigated. In our patient cohort, 23.4% (n = 72/308) of patients experienced POP. Univariate, multivariate logistic regression analysis and lasso regression analysis revealed age, Hunt-Hess grade, mechanical ventilation, leukocyte count, lymphocyte count, and platelet count as independent risk factors for POP. Subsequently, these six factors were used to build the final model. We found that age, Hunt-Hess grade, mechanical ventilation, leukocyte count, lymphocyte count, and platelet count were independent risk factors for POP in patients with aSAH. Through validation and comparison with other studies and machine learning models, our novel predictive model has demonstrated high efficacy in effectively predicting the likelihood of pneumonia during the hospitalization of aSAH patients.

A Mediation Analysis of the Association Between Systemic Inflammation Response Index, in-Hospital Complications, and Poor Long-Term Functional Outcomes in Patients with Aneurysmal Subarachnoid Hemorrhage: Insights from a Large Prospective Cohort Study

Purpose

Early systemic inflammatory changes are increasingly recognized as factors influencing outcomes after aneurysmal subarachnoid hemorrhage (aSAH). Systemic inflammation response index (SIRI), an inflammation biomarker, was thought to be associated with adverse outcomes in many other diseases. However, in aSAH, research on SIRI remains limited. Thus, our objective was to investigate the association between SIRI and poor long-term functional outcomes while evaluating the mediating role of in-hospital complications in this association.

Patients and Methods

SIRI was defined as neutrophil count × monocyte count/lymphocyte count. Patients were categorized according to SIRI quartiles. Stabilized inverse probability of treatment weighting (sIPTW) was utilized to minimize group differences. The association between SIRI and in-hospital complications as well as poor 90-day functional outcomes (mRS 3-6) was estimated by multivariable logistic regression analyses. Mediation analysis was performed to investigate the relationship between SIRI and poor functional outcomes mediated by in-hospital complications.

Results

A total of 650 patients were prospectively included. After sIPTW, compared to the lowest quartile, an elevated SIRI was associated with delayed cerebral ischemia (DCI) (OR 2.12, 95% CI 1.20-3.74), post-operative pneumonia (POP) (OR 2.16, 95% CI 1.29-3.62) and poor 90-day functional outcomes (OR 3.03, 95% CI 1.55-5.91). In-hospital complications including DCI (mediation proportion, 18.18% before sIPTW and 20.0% after sIPTW) and POP (mediation proportion, 18.18% before sIPTW and 26.7% after sIPTW) partially mediated the association between SIRI and poor 90-day functional outcomes. Mediation analysis yielded comparable results in subgroups stratified by age and sex.

Conclusion

In this study, SIRI was associated with poor long-term functional outcomes in aSAH, which was partially mediated by DCI and POP with a mediation proportion exceeding 18%. Our findings might underscore the potential utility of SIRI in prompting physicians to address systemic inflammatory status timely to prevent in-hospital complications, including DCI and POP, and ultimately improve long-term functional outcomes.

Construction and validation of a perioperative concomitant lower extremity deep vein thrombosis line graph model in patients with aneurysmal subarachnoid hemorrhage

Background

To develop and validate a nomogram for predicting the probability of deep venous thrombosis (DVT) in patients with aneurysmal subarachnoid hemorrhage (aSAH) during the perioperative period, using clinical features and readily available biochemical parameters.

Methods

The least absolute shrinkage and selection operator (LASSO) regression technique was employed for data dimensionality reduction and selection of predictive factors. A multivariable logistic regression analysis was conducted to establish a predictive model and nomogram for post-aSAH DVT. The discriminative ability of the model was determined by calculating the area under the curve (AUC).

Results

A total of 358 aSAH patients were included in the study, with an overall incidence of DVT of 20.9%. LASSO regression identified four variables, including age, modified Fisher grade, total length of hospital stay, and anticoagulation therapy, as highly predictive factors for post-aSAH DVT. The patients were randomly divided into a modeling group and a validation group in a 6:4 ratio to construct the nomogram. The AUCs of the modeling and validation groups were 0.8511 (95% CI, 0.7922-0.9099) and 0.8633 (95% CI, 0.7968-0.9298), respectively.

Conclusions

The developed nomogram exhibits good accuracy, discriminative ability, and clinical utility in predicting DVT, aiding clinicians in identifying high-risk individuals and implementing appropriate preventive and treatment measures.

Neutrophil-lymphocyte ratio on first and third postoperative days: associated with severe pneumonia in aneurysmal subarachnoid hemorrhage patients undergoing surgeries

Severe postoperative pneumonia can increase the risk of poor outcomes in patients with aneurysmal subarachnoid hemorrhage (aSAH). We aimed to explore the associations of preoperative or postoperative inflammatory markers calculated from blood cell counts with severe pneumonia. This retrospective study was conducted at the First Affiliated Hospital of Yangtze University from January 2019 to June 2023. The associations of neutrophil-lymphocyte ratio (NLR), monocyte-lymphocyte ratio (MLR), platelet-lymphocyte ratio (PLR), systemic immune inflammation index (SII), and systemic inflammation response index (SIRI) with severe pneumonia were analyzed. There were 159 patients with pneumonia and 21 patients without pneumonia. There were 41 patients with severe pneumonia and 118 patients with non-severe pneumonia. The multivariate logistic regression analysis showed that NLR on the first postoperative (OR = 2.574, 95%CI: 1.035-6.403, p = 0.042) and third postoperative days (OR = 4.296, 95%CI: 1.699-10.860, p = 0.002) were associated with severe pneumonia in aSAH patients. Among patients ≥ 60 years, SIRI on the preoperative day (OR = 7.430, 95%CI: 1.443-38.251, p = 0.016) and NLR on the third postoperative day (OR = 4.748, 95%CI: 1.286-17.801, p = 0.020) were associated with severe pneumonia. Among patients < 60 years, NLR on the first postoperative day (OR = 24.149, 95%CI: 3.476-167.747, p = 0.001) was associated with severe pneumonia. The NLR on the first and third postoperative days were possibly associated with severe pneumonia in aneurysmal subarachnoid hemorrhage patients undergoing clipping or embolization surgeries. Dynamic detection of NLR during early perioperative period may help clinicians to predict the development of severe pneumonia.

Development and external validation of a nomogram for predicting postoperative pneumonia in aneurysmal subarachnoid hemorrhage

Background

Postoperative pneumonia (POP) is a common complication after aneurysmal subarachnoid hemorrhage (aSAH) associated with increased mortality rates, prolonged hospitalization, and high medical costs. It is currently understood that identifying pneumonia early and implementing aggressive treatment can significantly improve patients' outcomes. The primary objective of this study was to explore risk factors and develop a logistic regression model that assesses the risks of POP.

Methods

An internal cohort of 613 inpatients with aSAH who underwent surgery at the Neurosurgical Department of First Affiliated Hospital of Wenzhou Medical University was retrospectively analyzed to develop a nomogram for predicting POP. We assessed the discriminative power, accuracy, and clinical validity of the predictions by using the area under the receiver operating characteristic curve (AUC), the calibration curve, and decision curve analysis (DCA). The final model was validated using an external validation set of 97 samples from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.

Results

Among patients in our internal cohort, 15.66% (n = 96/613) of patients had POP. The least absolute shrinkage and selection operator (LASSO) regression analysis identified the Glasgow Coma Scale (GCS), mechanical ventilation time (MVT), albumin, C-reactive protein (CRP), smoking, and delayed cerebral ischemia (DCI) as potential predictors of POP. We then used multivariable logistic regression analysis to evaluate the effects of these predictors and create a final model. Eighty percentage of patients in the internal cohort were randomly assigned to the training set for model development, while the remaining 20% of patients were allocated to the internal validation set. The AUC values for the training, internal, and external validation sets were 0.914, 0.856, and 0.851, and the corresponding Brier scores were 0.084, 0.098, and 0.143, respectively.

Conclusion

We found that GCS, MVT, albumin, CRP, smoking, and DCI are independent predictors for the development of POP in patients with aSAH. Overall, our nomogram represents a reliable and convenient approach to predict POP in the patient population.

Platelet-to-white blood cell ratio: A feasible predictor for unfavorable functional outcome in patients with aneurysmal subarachnoid hemorrhage

This study aimed to identify the association between the platelet-to-white blood cell ratio (PWR) and outcomes in patients with aneurysmal subarachnoid hemorrhage (aSAH). Data for patients diagnosed with aSAH and admitted from January 2015 to December 2020 were retrospectively analyzed. Multivariate logistic regression analysis was performed to identify factors that correlated with unfavorable outcomes at 3 months. Receiver operating characteristic (ROC) curve analysis was used to determine the optimal cut-off value for the PWR to discriminate favorable and unfavorable outcomes at 3 months. The patients were then divided into two groups based on this cut-off value. To reduce selection bias, propensity score matching (PSM) was performed to balance the baseline characteristics. In total, 800 patients were enrolled in this study. The multivariate logistic regression analysis showed that the PWR (odds ratio, 1.05; 95% confidence interval, 1.00-1.09; p = 0.034) at admission was independently associated with unfavorable 3-month outcomes. ROC curve analysis identified 15.69 as the best cut-off PWR value for predicting clinical outcomes. After PSM, patients with a PWR < 15.69 exhibited a higher incidence of postoperative pneumonia (POP) (37.2% vs. 25.6%, p = 0.011) and unfavorable 3-month outcomes (19.3% vs. 12.1%, p = 0.043). These findings suggest that patients with aSAH showing a PWR < 15.69 at admission have a higher probability of developing POP, which may be the main factor causing unfavorable outcomes at 3 months.

Machine learning algorithms to predict risk of postoperative pneumonia in elderly with hip fracture

BACKGROUND

Hip fracture (HF) is one of the most common fractures in the elderly and is significantly associated with high mortality and unfavorable prognosis. Postoperative pneumonia (POP), the most common postoperative complication of HF, can seriously affect patient prognosis and increase the burden on the healthcare system. The aim of this study was to develop machine learning models for identifying elderly patients at high risk of pneumonia after hip fracture surgery.

METHODS

From May 2016 to November 2022, patients admitted to a single central hospital for HF served as the study population. We extracted data that could be collected within 24 h of patient admission. The dataset was divided into training and validation sets according to 70:30. Based on the screened risk factors, prediction models were developed using seven machine learning algorithms, namely CART, GBM, KNN, LR, NNet, RF, and XGBoost, and their performance was evaluated.

RESULTS

Eight hundred five patients were finally included in the analysis and 75 (9.3%) patients suffered from POP. Age, CI, COPD, WBC, HB, GLU, STB, GLOB, Ka+ which are used as features to build machine learning models. By evaluating the model's AUC value, accuracy, sensitivity, specificity, Kappa value, MCC value, Brier score value, calibration curve, and DCA curve, the model constructed by XGBoost algorithm has the best and near-perfect performance.

CONCLUSION

The machine learning model we created is ideal for detecting elderly patients at high risk of POP after HF at an early stage.

Pre-operative prognostic nutrition index and post-operative pneumonia in aneurysmal subarachnoid hemorrhage patients

Background and objective

Post-operative pneumonia (POP), a common complication, may be associated with prolonged hospitalization and long-term mortality in aneurysmal subarachnoid hemorrhage (aSAH) patients. This study aimed to explore the association between pre-operative prognostic nutrition index (PNI) and POP in aSAH patients.

Methods

A total of 280 aSAH patients were enrolled from Nanjing Drum Tower Hospital. PNI was calculated as follows: [10 × albumin(gr/dl)] + [0.005 × absolute pre-operative lymphocyte count (per mm³)]. We utilized multivariate analyses, restricted cubic spline, net reclassification improvement (NRI), and integrated discrimination improvement (IDI) to elucidate the role of PNI in POP.

Results

Pre-operative PNI levels in the POP group were higher, compared with the non-POP group (41.0 [39.0, 45.4] vs. 44.4 [40.5, 47.3], P = 0.001). When we included PNI as a categorical variable in the multivariate analysis, the levels of PNI were associated with POP (odds ratio, 0.433; 95% confidence interval, 0.253-0.743; P=0.002). In addition, when we included PNI as a continuous variable in the multivariate analysis, the PNI levels were also associated with POP (odds ratio, 0.942; 95% confidence interval, 0.892-0.994; P = 0.028). The level of albumin was also a predictor of the occurrence of POP, with a lower diagnostic power than PNI [AUC: 0.611 (95% confidence interval, 0.549-0.682; P = 0.001) for PNI vs. 0.584 (95% confidence interval, 0.517-0.650; P = 0.017) for albumin]. Multivariable-adjusted spline regression indicated a linear dose-response association between PNI and POP in aSAH participants (P for linearity = 0.027; P for non-linearity = 0.130). Reclassification assessed by IDI and NRI was significantly improved with the addition of PNI to the conventional model of POP in aSAH patients (NRI: 0.322 [0.089-0.555], P = 0.007; IDI: 0.016 [0.001-0.031], P = 0.040).

Conclusion

The lower levels of pre-operative PNI may be associated with the higher incidence of POP in aSAH patients. Neurosurgeons are supposed to pay more attention to pre-operative nutrition status in aSAH patients.

Predictive Values of White Blood Cell Count in Peripheral Blood at Admission on In-Hospital Complications and 90-Day Outcomes of Patients with Aneurysmal Subarachnoid Hemorrhage: Insights from the LongTEAM Registry

PURPOSE

This study aimed to explore the relationship between white blood cells (WBCs) at admission and clinical outcomes in patients with aneurysmal subarachnoid hemorrhage (aSAH).

PATIENTS AND METHODS

We analyzed data from patients with aSAH between January 2015 and September 2021 who were included in the LongTEAM (Long-term Prognosis of Emergency Aneurysmal Subarachnoid Hemorrhage) registry study. WBC is classified into four groups according to the quartile. We used the logistic model for in-hospital complications, mortality, modified Rankin scale (mRS) at discharge and 90 days to examine the relationship between WBC and clinical outcomes. We used WBC levels near odds ratio (OR) = 1 (Q1) in restricted cubic splines as the reference to evaluate whether there is a nonlinear relationship between WBC and clinical outcomes. Another Kaplan-Meier method was used to analyze the relationship between WBC levels and the risk of developing pneumonia.

RESULTS

Of the 988 patients included, the results showed that compared with patients in the Q1 group, patients in the highest quartile (Q4) had an increased incidence of 90-day unfavorable outcomes after adjusting the confounders (adjusted OR = 1.81, 95% CI = 1.02-3.20, p = 0.042), which may be caused by the increased incidence and risk of pneumonia (adjusted OR = 2.06, 95% CI = 1.30-3.29, p = 0.002; adjusted hazard ratio [HR]=1.63, 95% CI = 1.13-2.36, p < 0.001). The restricted cubic spline indicated that the incidence of developing pneumonia and 90-day unfavorable outcomes rises with increasing WBC levels (p for nonlinear = 0.135 and 0.113).

CONCLUSION

Patients with higher WBC at admission were associated with an increased incidence of 90-day unfavorable outcomes, which might be related to pneumonia.