Predicting factors for shunt-dependent hydrocephalus in patients with aneurysmal subarachnoid hemorrhage

A predictive model in patients with chronic hydrocephalus following aneurysmal subarachnoid hemorrhage: a retrospective cohort study

Objective

Our aim was to develop a nomogram that integrates clinical and radiological data obtained from computed tomography (CT) scans, enabling the prediction of chronic hydrocephalus in patients with aneurysmal subarachnoid hemorrhage (aSAH).

Method

A total of 318 patients diagnosed with subarachnoid hemorrhage (SAH) and admitted to the Department of Neurosurgery at the Affiliated People's Hospital of Jiangsu University between January 2020 and December 2022 were enrolled in our study. We collected clinical characteristics from the hospital's medical record system. To identify risk factors associated with chronic hydrocephalus, we conducted both univariate and LASSO regression models on these clinical characteristics and radiological features, accompanied with penalty parameter adjustments conducted through tenfold cross-validation. All features were then incorporated into multivariate logistic regression analyses. Based on these findings, we developed a clinical-radiological nomogram. To evaluate its discrimination performance, we conducted Receiver Operating Characteristic (ROC) curve analysis and calculated the Area Under the Curve (AUC). Additionally, we employed calibration curves, and utilized Brier scores as an indicator of concordance. Additionally, Decision Curve Analysis (DCA) was performed to determine the clinical utility of our models by estimating net benefits at various threshold probabilities for both training and testing groups.

Results

The study included 181 patients, with a determined chronic hydrocephalus prevalence of 17.7%. Univariate logistic regression analysis identified 11 potential risk factors, while LASSO regression identified 7 significant risk factors associated with chronic hydrocephalus. Multivariate logistic regression analysis revealed three independent predictors for chronic hydrocephalus following aSAH: Periventricular white matter changes, External lumbar drainage, and Modified Fisher Grade. A nomogram incorporating these factors accurately predicted the risk of chronic hydrocephalus in both the training and testing cohorts. The AUC values were calculated as 0.810 and 0.811 for each cohort respectively, indicating good discriminative ability of the nomogram model. Calibration curves along with Hosmer-Lemeshow tests demonstrated excellent agreement between predicted probabilities and observed outcomes in both cohorts. Furthermore, Brier scores (0.127 for the training and 0.09 for testing groups) further validated the predictive performance of our nomogram model. The DCA confirmed that this nomogram provides superior net benefit across various risk thresholds when predicting chronic hydrocephalus. The decision curve demonstrated that when an individual's threshold probability ranged from 5 to 62%, this model is more effective in predicting the occurrence of chronic hydrocephalus after aSAH.

Conclusion

A clinical-radiological nomogram was developed to combine clinical characteristics and radiological features from CT scans, aiming to enhance the accuracy of predicting chronic hydrocephalus in patients with aSAH. This innovative nomogram shows promising potential in assisting clinicians to create personalized and optimal treatment plans by providing precise predictions of chronic hydrocephalus among aSAH patients.

A systematic review on intracranial aneurysm and hemorrhage detection using machine learning and deep learning techniques

The risk of discovering an intracranial aneurysm during the initial screening and follow-up screening are reported as around 11%, and 7% respectively (Zuurbie et al., 2023) to these mass effects, unruptured aneurysms frequently generate symptoms, however, the real hazard occurs when an aneurysm ruptures and results in a cerebral hemorrhage known as a subarachnoid hemorrhage. The objective is to study the multiple kinds of hemorrhage and aneurysm detection problems and develop machine and deep learning models to recognise them. Due to its early stage, subarachnoid hemorrhage, the most typical symptom after aneurysm rupture, is an important medical condition. It frequently results in severe neurological emergencies or even death. Although most aneurysms are asymptomatic and won't burst, because of their unpredictable growth, even small aneurysms are susceptible. A timely diagnosis is essential to prevent early mortality because a large percentage of hemorrhage cases present can be fatal. Physiological/imaging markers and the degree of the subarachnoid hemorrhage can be used as indicators for potential early treatments in hemorrhage. The hemodynamic pathomechanisms and microcellular environment should remain a priority for academics and medical professionals. There is still disagreement about how and when to care for aneurysms that have not ruptured despite studies reporting on the risk of rupture and outcomes. We are optimistic that with the progress in our understanding of the pathophysiology of hemorrhages and aneurysms and the advancement of artificial intelligence has made it feasible to conduct analyses with a high degree of precision, effectiveness and reliability.

Pretreatment and Posttreatment Factors Associated with Shunt-Dependent Hydrocephalus After Aneurysmal Subarachnoid Hemorrhage: A Systematic Review and Meta-Analysis

BACKGROUND

Hydrocephalus is a common complication after aneurysmal subarachnoid hemorrhage (aSAH). This study aimed to evaluate novel preoperative and postoperative risk factors for shunt-dependent hydrocephalus (SDHC) after aSAH via a systematic review and meta-analysis.

METHODS

A systematic search was conducted using PubMed and Embase databases for studies pertaining to aSAH and SDHC. Articles were assessed by meta-analysis if the number of risk factors for SDHC was reported by >4 studies and could be extracted separately for patients who did or did not develop SDHC.

RESULTS

Thirty-seven studies were included, comprising 12,667 patients with aSAH (SDHC 2214 vs. non-SDHC 10,453). In a primary analysis of 15 novel potential risk factors, 8 were identified to be significantly associated with increased prevalence of SDHC after aSAH, including high World Federation of Neurological Surgeons grades (odds ratio [OR], 2.43), hypertension (OR, 1.33), anterior cerebral artery (OR, 1.36), middle cerebral artery (OR, 0.65), and vertebrobasilar artery (2.21) involvement, decompressive craniectomy (OR, 3.27), delayed cerebral ischemia (OR, 1.65), and intracerebral hematoma (OR, 3.91).

CONCLUSIONS

Several new factors associated with increased odds of developing SDHC after aSAH were found to be significant. By providing evidence-based risk factors for shunt dependency, we describe an identifiable list of preoperative and postoperative prognosticators that may influence how surgeons recognize, treat, and manage patients with aSAH at high risk for developing SDHC.

Review of the prevention and treatment of hydrocephalus after aneurysmal subarachnoid hemorrhage

Hydrocephalus following a ruptured aneurysm portends a poor prognosis. Patients have to face the risk of infection and shunt obstruction after shunt surgery, which may require a second procedure and greatly reduce the quality of life for survivors. It is crucial to minimize the incidence of hydrocephalus and reduce cerebrospinal fluid shunt dependency. This article reviews current interventions before and after hydrocephalus formation after aneurysmal subarachnoid hemorrhage, focusing on the relationships between treatment options and the incidence of postoperative hydrocephalus, management of cerebrospinal fluid drainage and shunt dependent hydrocephalus, and advocates the combination of prevention and treatment to develop individualized treatment plans for patients.

Predicting Ventriculoperitoneal Shunt Dependence in High Grade Aneurysmal Subarachnoid Hemorrhage

INTRODUCTION

Aneurysmal subarachnoid hemorrhage (aSAH) commonly presents with hydrocephalus due to obstruction of cerebrospinal fluid (CSF) passage across the ventricular system in the brain. Placement of an external ventricular device (EVD) and in some cases ventriculoperitoneal shunt (VPS) are often necessary for patients requiring prolonged CSF diversion. The study aimed at evaluating critical factors that play a role in determining the need for extended extraventricular drainage.

METHODS

We performed a retrospective observational cohort study of two groups of patients with radiological imaging confirmed high grade aSAH (Hunt & Hess grades 3-5) who required VPS placement, shunt-dependent group, and who did not require long term CSF diversion, non-shunt-dependent group. We collected and analyzed data regarding the daily CSF output for 10 days following EVD placement, daily EVD height, intracranial pressure (ICP) and cerebral perfusion pressure (CPP), indicators of hydrocephalus, and CSF characteristics.

RESULTS

The cohort, comprising of 8 patients in the shunt-dependent group and 32 patients in the non-shunt-dependent group, displayed median daily CSF output of 275.1 mL/day and 193.4 mL/day, respectively (P = .0005). ROC curve for CSF drainage for the two groups showed an area under the curve (AUC) of 0.71 with a 95% confidence interval (CI) 0.65 to 0.77. Qualitative analysis of CSF characteristics revealed that the shunt-dependent group had more proteinaceous, darker red color, and greater proportion of red blood cells (RBCs) although not statistically significant.

CONCLUSIONS

Determinants of prolonged CSF drainage requirements in patients with high grade aSAH are not fully elucidated to this date and there is no standardized protocol for CSF diversion. Our study revealed potential markers that can be used in the assessment for the need for long term CSF diversion. Our limited sample size necessitates further research to establish clear correlations and cutoffs of these parameters in predicting long term CSF diversion requirements.

Prediction and Risk Assessment Models for Subarachnoid Hemorrhage: A Systematic Review on Case Studies

Subarachnoid hemorrhage (SAH) is one of the major health issues known to society and has a higher mortality rate. The clinical factors with computed tomography (CT), magnetic resonance image (MRI), and electroencephalography (EEG) data were used to evaluate the performance of the developed method. In this paper, various methods such as statistical analysis, logistic regression, machine learning, and deep learning methods were used in the prediction and detection of SAH which are reviewed. The advantages and limitations of SAH prediction and risk assessment methods are also being reviewed. Most of the existing methods were evaluated on the collected dataset for the SAH prediction. In some researches, deep learning methods were applied, which resulted in higher performance in the prediction process. EEG data were applied in the existing methods for the prediction process, and these methods demonstrated higher performance. However, the existing methods have the limitations of overfitting problems, imbalance data problems, and lower efficiency in feature analysis. The artificial neural network (ANN) and support vector machine (SVM) methods have been applied for the prediction process, and considerably higher performance is achieved by using this method.

Subarachnoid Hemorrhage and Hydrocephalus

BACKGROUND

Hydrocephalus associated with subarachnoid hemorrhage is a common neurosurgical problem, the management of which is tailor-made to the patient. It is usually seen with an aneurysmal bleed and is independent of the primary modality of treatment.

AIM

This study aimed to provide a comprehensive overview of this important association and discuss the various available treatment modalities.

MATERIALS AND METHODS

A detailed review of the literature was done on the risk factors, pathogenesis, and treatment of hydrocephalus in the setting of subarachnoid hemorrhage.

RESULTS

Hydrocephalus occurs in 6% to 67% of subarachnoid hemorrhage (SAH). It may present as acute, subacute, or chronic at the time of presentation. Diagnosis is made with a plain computed tomography scan of the brain, and the treatment is observant, temporary, or permanent cerebrospinal fluid diversion.

CONCLUSION

Hydrocephalus associated with SAH interferes with the outcome of SAH. It prolongs the hospital stay, besides causing additional morbidity. The various risk factors, if present, should warn us to be vigilant, and management is definitely not uniform and is custom made to the patients' needs.

Ventriculoatrial shunt as a feasible regimen for certain patients of hydrocephalus: clinical features and surgical management

Ventriculoatrial (VA) shunt is one of the most commonly used solutions for hydrocephalus. In recent years, the number of VA shunt has decreased worldwide, given the perceived technical challenges and the potentially serious complications associated with VA shunt. However, VA shunt remains as a viable treatment option for hydrocephalus in selected patients. Novel placement strategies and monitoring methods have been developed to reduce complications following VA shunt. In this article, we reported that seven consecutive cases who received a VA shunt. VA shunts were applied in seven hydrocephalic patients who experienced previous ventriculoperitoneal (VP) shunt failures or had contraindications to abdominal catheter placement. The insertion of VA shunt catheters was guided with the aid of intraoperative electromagnetic neuronavigation and electrocardiographic technique. There were three female and four male patients with a mean age of 46 years (range 22-68 years) received VA shunts under the guidance of electromagnetic neuronavigation and electrocardiographic method intraoperatively. In all cases, postoperative cranial CT scans and chest radiography demonstrated appropriate positioning of the catheter tips. And no postoperative complications occurred during the follow-up period of 3-26 months. VA shunts are potential favorable alternatives for patients who cannot tolerate VP shunts. It is noteworthy that VA is not free of complications. Intraoperative application of electromagnetic neuronavigation and electrocardiographic technique contributes to safe and optimal catheter placement of VA shunts.

Development of machine learning models to prognosticate chronic shunt-dependent hydrocephalus after aneurysmal subarachnoid hemorrhage

BACKGROUND

Shunt-dependent hydrocephalus significantly complicates subarachnoid hemorrhage (SAH), and reliable prognosis methods have been sought in recent years to reduce morbidity and costs associated with delayed treatment or neglected onset. Machine learning (ML) defines modern data analysis techniques allowing accurate subject-based risk stratifications. We aimed at developing and testing different ML models to predict shunt-dependent hydrocephalus after aneurysmal SAH.

METHODS

We consulted electronic records of patients with aneurysmal SAH treated at our institution between January 2013 and March 2019. We selected variables for the models according to the results of the previous works on this topic. We trained and tested four ML algorithms on three datasets: one containing binary variables, one considering variables associated with shunt-dependency after an explorative analysis, and one including all variables. For each model, we calculated AUROC, specificity, sensitivity, accuracy, PPV, and also, on the validation set, the NPV and the Matthews correlation coefficient (ϕ).

RESULTS

Three hundred eighty-six patients were included. Fifty patients (12.9%) developed shunt-dependency after a mean follow-up of 19.7 (± 12.6) months. Complete information was retrieved for 32 variables, used to train the models. The best models were selected based on the performances on the validation set and were achieved with a distributed random forest model considering 21 variables, with a ϕ = 0.59, AUC = 0.88; sensitivity and specificity of 0.73 (C.I.: 0.39-0.94) and 0.92 (C.I.: 0.84-0.97), respectively; PPV = 0.59 (0.38-0.77); and NPV = 0.96 (0.90-0.98). Accuracy was 0.90 (0.82-0.95).

CONCLUSIONS

Machine learning prognostic models allow accurate predictions with a large number of variables and a more subject-oriented prognosis. We identified a single best distributed random forest model, with an excellent prognostic capacity (ϕ = 0.58), which could be especially helpful in identifying low-risk patients for shunt-dependency.

Thromboembolic infarction caused by an unknown patent foramen ovale 30 years after VA shunt insertion: a case report and review of the literature

BACKGROUND

Ventriculoatrial shunt (VA) insertion is one of the possible surgical procedures to treat hydrocephalus. However, it is also associated with several complications such as obstruction and shunt infection as well as life-threatening complications like intraatrial thrombus or thrombosis on the distal catheter. In this case report, we share a rare case of a patient with a VA shunt, who was admitted to our hospital with a stroke.

CASE DESCRIPTION

A 56-year-old female patient with suspected acute stroke was admitted to the stroke unit. CT and MRI scans showed multiple cerebral infarctions in both hemispheres. The transesophageal echocardiography (TEE) showed at the tip of the VA shunt catheter, which was implanted about 30 years ago due to aqueduct stenosis, also a thrombotic formation as the reason of stroke. Interestingly, the tip of the catheter was not in the right atrium as expected, but in the left atrium. Further evaluation showed a patent foramen ovale (PFO), through which the catheter migrated from the right to the left side. At first, conservative treatment with anticoagulation was started with the aim to dissolve the thrombotic formation; however, a control TEE showed an unchanged mass at the catheter tip. Therefore, a ventriculoperitoneal shunt was implanted and the proximal shunt catheter was removed with an additional closure of the PFO by our heart surgeons. Postoperatively, the patient was discharged 10 days later in good condition to a rehabilitation center.

CONCLUSIONS

Thromboembolic events due to a PFO are rare but possible life-threatening complication after VA shunt insertion. Therefore, preoperative cardiac diagnostic might be clinically relevant prior to a VA shunt implantation to avoid such complications.

Prognostic Model for Chronic Shunt-Dependent Hydrocephalus After Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

Patients with aneurysmal subarachnoid hemorrhage (aSAH) are at risk of the development of chronic shunt-dependent hydrocephalus. However, identification of shunt-dependent patients remains challenging. We sought to develop a prognostic model to identify patients with aSAH at risk of chronic shunt-dependent hydrocephalus. In addition to the well-known prognostic variables, blood clearance in the cerebrospinal fluid (CSF) spaces was considered.

METHODS

We retrospectively analyzed the data from 227 patients treated at our institution from January 2012 to January 2016. The outcome was ventriculoperitoneal shunt placement within 30 days after aSAH. The candidate prognostic variables were patient age, World Federation of Neurological Surgeons grade and Fisher grade, external ventricular drainage, ventricular and intracerebral hemorrhage, and interval to blood clearance in the peripheral/basal CSF spaces. Adjustment for multiple testing was performed. Multivariable logistic regression analysis was used for model development. Bootstrapping was applied for internal validation. The model performance measures included indexes for explained variance (R²), calibration (graphic plot, Hosmer-Lemeshow test), and discrimination (c-statistic).

RESULTS

Of the 227 patients, 90 (39.6%) required a ventriculoperitoneal shunt. The constructed prognostic model combined external ventricular drainage placement, the presence of ventricular blood, and the duration of blood clearance in the basal cisterns. The model performance was promising, with an R² of 33% (20% after bootstrapping), the calibration plot was adequate, the Hosmer-Lemeshow test result was not significant, and the c-statistic was 0.85 (0.84 as assessed after bootstrapping) indicating a good discriminating prognostic model.

CONCLUSIONS

Our prognostic model could help identify patients requiring permanent CSF diversion after aSAH, although additional modification and external validation are needed. Interventions aimed at accelerating the clearance of blood in the basal cisterns might have the potential to prevent the development of chronic hydrocephalus after aSAH.