The Prediction of Shunt Response in Idiopathic Normal-Pressure Hydrocephalus Based on Intracranial Pressure Monitoring and Lumbar Infusion

k-Shape clustering for extracting macro-patterns in intracranial pressure signals

Background

Intracranial pressure (ICP) monitoring is a core component of neurosurgical diagnostics. With the introduction of telemetric monitoring devices in the last years, ICP monitoring has become feasible in a broader clinical setting including monitoring during full mobilization and at home, where a greater diversity of ICP waveforms are present. The need for identification of these variations, the so-called macro-patterns lasting seconds to minutes—emerges as a potential tool for better understanding the physiological underpinnings of patient symptoms.

Methods

We introduce a new methodology that serves as a foundation for future automatic macro-pattern identification in the ICP signal to comprehensively understand the appearance and distribution of these macro-patterns in the ICP signal and their clinical significance. Specifically, we describe an algorithm based on k-Shape clustering to build a standard library of such macro-patterns.

Results

In total, seven macro-patterns were extracted from the ICP signals. This macro-pattern library may be used as a basis for the classification of new ICP variation distributions based on clinical disease entities.

Conclusions

We provide the starting point for future researchers to use a computational approach to characterize ICP recordings from a wide cohort of disorders.

Prediction of Shunt Responsiveness in Suspected Patients With Normal Pressure Hydrocephalus Using the Lumbar Infusion Test: A Machine Learning Approach

BACKGROUND

Machine learning (ML) approaches can significantly improve the classical Rout-based evaluation of the lumbar infusion test (LIT) and the clinical management of the normal pressure hydrocephalus.

OBJECTIVE

To develop a ML model that accurately identifies patients as candidates for permanent cerebral spinal fluid shunt implantation using only intracranial pressure and electrocardiogram signals recorded throughout LIT.

METHODS

This was a single-center cohort study of prospectively collected data of 96 patients who underwent LIT and 5-day external lumbar cerebral spinal fluid drainage (external lumbar drainage) as a reference diagnostic method. A set of selected 48 intracranial pressure/electrocardiogram complex signal waveform features describing nonlinear behavior, wavelet transform spectral signatures, or recurrent map patterns were calculated for each patient. After applying a leave-one-out cross-validation training-testing split of the data set, we trained and evaluated the performance of various state-of-the-art ML algorithms.

RESULTS

The highest performing ML algorithm was the eXtreme Gradient Boosting. This model showed a good calibration and discrimination on the testing data, with an area under the receiver operating characteristic curve of 0.891 (accuracy: 82.3%, sensitivity: 86.1%, and specificity: 73.9%) obtained for 8 selected features. Our ML model clearly outperforms the classical Rout-based manual classification commonly used in clinical practice with an accuracy of 62.5%.

CONCLUSION

This study successfully used the ML approach to predict the outcome of a 5-day external lumbar drainage and hence which patients are likely to benefit from permanent shunt implantation. Our automated ML model thus enhances the diagnostic utility of LIT in management.

The Role of Machine Learning and Radiomics for Treatment Response Prediction in Idiopathic Normal Pressure Hydrocephalus

Introduction Ventricular shunting remains the standard of care for patients with idiopathic normal pressure hydrocephalus (iNPH); however, not all patients benefit from the shunting. Prediction of response in advance can result in improved patient selection for ventricular shunting. This study aims to develop a machine learning predictive model for treatment response after shunt placement using the clinical and radiomics features. Methods In this retrospective pilot study, the medical records of iNPH patients who underwent ventricular shunting were evaluated. In each patient, the "idiopathic normal pressure hydrocephalus grading scale" (iNPHGS) and a "Modified Rankin Scale" were calculated before and after surgery. The subsequent treatment response was calculated as the difference between the iNPHGS scores before and after surgery. iNPHGS score reduction of two or more than two were considered as treatment response. The presurgical MRI scans were evaluated by radiologists, the ventricular systems were segmented on the T2-weighted images, and the radiomics features were extracted from the segmented ventricular system. Using Orange data mining open-source platform, different machine learning models were then developed based on the presurgical clinical features and the selected radiomics features to predict treatment response after shunt placement. Results After the implementation of the inclusion criteria, 78 patients were included in this study. One hundred twenty radiomics features were extracted, and the 12 best predictive radiomics features were selected. Using only clinical data (iNPHGS and Modified Rankin Scale), the random forest model achieved the best performance in treatment prediction with an area under the curve (AUC) of 0.71. Adding the Radiomics analysis to the clinical data improved the prediction performance, with the support vector machine (SVM) achieving the highest rank in treatment prediction with an AUC of 0.8. Adding age and sex to the analysis did not improve the prediction. Conclusion Using machine learning models for treatment response prediction in patients with iNPH is feasible with acceptable accuracy. Adding the Radiomics analysis to the clinical features can further improve the predictive performance. SVM is likely the best model for this task.

B waves: a systematic review of terminology, characteristics, and analysis methods

Background

Although B waves were introduced as a concept in the analysis of intracranial pressure (ICP) recordings nearly 60 years ago, there is still a lack consensus on precise definitions, terminology, amplitude, frequency or origin. Several competing terms exist, addressing either their probable physiological origin or their physical characteristics. To better understand B wave characteristics and ease their detection, a literature review was carried out.

Methods

A systematic review protocol including search strategy and eligibility criteria was prepared in advance. A literature search was carried out using PubMed/MEDLINE, with the following search terms: B waves + review filter, slow waves + review filter, ICP B waves, slow ICP waves, slow vasogenic waves, Lundberg B waves, MOCAIP.

Results

In total, 19 different terms were found, B waves being the most common. These terminologies appear to be interchangeable and seem to be used indiscriminately, with some papers using more than five different terms. Definitions and etiologies are still unclear, which makes systematic and standardized detection difficult.

Conclusions

Two future lines of action are available for automating macro-pattern identification in ICP signals: achieving strict agreement on morphological characteristics of “traditional” B waveforms, or starting a new with a fresh computerized approach for recognition of new clinically relevant patterns.