Some cool considerations of external lumbar drainage during its widespread application in neurosurgical practice: a long way to go

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Background

Lumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.

Methods

We utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.

Results

In the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.

Conclusions

The RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

Lumbar drains: Practical understanding and application for the otolaryngologist

INTRODUCTION

Lumbar drains are frequently used in patients with otolaryngologic concerns. These can be used therapeutically or prophylactically with the primary purpose being to modulate CSF pressure. Within otolaryngology, lumbar drains are most frequently used for cerebrospinal fluid leaks - either due to cerebrospinal fluid fistulas or in skull base surgery as these allow for potential healing of the defect. While not typically placed by otolaryngologists, a basic understanding of lumbar drains is beneficial in the context of patient management.

MANAGEMENT

A lumbar drain is inserted into the intrathecal space in a patient's lumbar spine. Though considered to be a benign procedure, complications are relatively frequent, and adjustment or replacement of the drain may be required. Complications include infection, epidural bleeding, retained hardware, sequelae of relative immobility, or may relate to over-drainage, ranging from mild headache to cranial neuropathies, altered mental status, pneumocephalus, intracranial hemorrhage, and death. While in place, neurologic exams should be performed routinely and should include motor and sensory exams of the lower extremities. A patient should be monitored for fevers, nuchal rigidity, and other signs of infection or meningitis. The CSF fluid should be grossly examined to identify changes, but routine laboratory tests are not typically run on the fluid itself. Drainage rates will vary usually between 5 and 20 mL per hour and must be frequently reassessed and adjusted based upon signs of intracranial hypotension. Drains should be removed when appropriate and should not be left in more than 5 days due to the increased infectious risk.

CONCLUSION

Lumbar drains are important tools used in patients with otolaryngologic pathologies. Otolaryngologists and otolaryngology residents should be familiar with these catheters to determine if they are working correctly and to identify adverse effects as early as possible.