Predicting Shunt Dependency from the Effect of Cerebrospinal Fluid Drainage on Ventricular Size

Abstract

Background: Prolonged external ventricular drainage (EVD) in patients with subarachnoid hemorrhage (SAH) leads to morbidity, whereas early removal can have untoward effects related to recurrent hydrocephalus. A metric to help determine the optimal time for EVD removal or ventriculoperitoneal shunt (VPS) placement would be beneficial in preventing the prolonged, unnecessary use of EVD. This study aimed to identify whether dynamics of cerebrospinal fluid (CSF) biometrics can temporally predict VPS dependency after SAH.

Methods: This was a retrospective analysis of a prospective, single-center, observational study of patients with aneurysmal SAH who required EVD placement for hydrocephalus. Patients were divided into VPS-dependent (VPS+) and non-VPS dependent groups. We measured the bicaudate index (BCI) on all available computed tomography scans and calculated the change over time (ΔBCI). We analyzed the relationship of ΔBCI with CSF output by using Pearson's correlation. A k-nearest neighbor model of the relationship between ΔBCI and CSF output was computed to classify VPS.

Results: Fifty-eight patients met inclusion criteria. CSF output was significantly higher in the VPS+ group in the 7 days post EVD placement. There was a negative correlation between delta BCI and CSF output in the VPS+ group (negative delta BCI means ventricles become smaller) and a positive correlation in the VPS- group starting from days four to six after EVD placement (p < 0.05). A weighted k-nearest neighbor model for classification had a sensitivity of 0.75, a specificity of 0.70, and an area under the receiver operating characteristic curve of 0.80.

Conclusions: The correlation of ΔBCI and CSF output is a reliable intraindividual biometric for VPS dependency after SAH as early as days four to six after EVD placement. Our machine learning model leverages this relationship between ΔBCI and cumulative CSF output to predict VPS dependency. Early knowledge of VPS dependency could be studied to reduce EVD duration in many centers (intensive care unit length of stay).

Keywords: Cerebral spinal fluid dynamics; External ventricular drain; Hydrocephalus; Machine learning; Shunt dependency; Subarachnoid.

Figure 1.. Correlation coefficient between delta bicaudate index and Cerebrospinal fluid output.

Horizontal lines are lines of best fit based on Pearson correlation coefficient on days one to seven (A to G, respectively) and H) change in correlation over the period of seven days. BCI=bicaudate index; CSF=cerebrospinal fluid; VP=ventriculoperitoneal

Figure 2.. Correlation coefficient between average bicaudate index and cerebrospinal fluid output.

Horizontal lines are lines of best fit based on Pearson correlation coefficient on days one to seven (A to G, respectively) and H) change in correlation over the period of seven days. BCI=bicaudate index; CSF=cerebrospinal fluid; VP=ventriculoperitoneal

Figure 3.. Values during the seven days for average bicaudate index, delta bicaudate index, cerebrospinal fluid output

Visual plot of all data during the seven days of external ventricular drain placement. A) average BCI, B) delta BCI, C) cerebrospinal fluid output. BCI=bicaudate index; CSF=cerebrospinal fluid; VP=ventriculoperitoneal

Figure 4.. Weighted k-nearest neighbor analysis

Showing receiver operating characteristic curve for ventriculoperitoneal shunt dependency based on A) delta BCI model, B) average BCI model, and confusion matrices for C) delta BCI model and D) average BCI model. Other features that were used as inputs were cumulative CSF output, age, Hunt and Hess score, Fisher score, and gender. BCI=bicaudate index.; KNN=k-nearest neighbor; VPS=ventriculoperitoneal shunt.