Utility of Machine learning in the Management of Normal Pressure Hydrocephalus (NPH): A Systematic Review.

Researchers

Journal

Modalities

Models

Abstract

In the past decade many machine learning (ML) models have been utilized in the management of normal pressure hydrocephalus (NPH). This study aims at systematically reviewing those ML models.Pubmed, EMBASE and Web of Science databases were searched for studies reporting applications of ML in NPH. Quality assessment was performed using PROBAST and TRIPOD adherence reporting guidelines and statistical analysis was performed with level of significance <0.05.A total of 22 studies with 53 models were included in the review of which convolutional neural network (CNN) was the most utilized model. Inputs used to train various models included clinical features, CT scan, MRI, intracranial pulse waveform characteristics and perfusion infusion. The overall mean accuracy of the models was 77% (highest for CNN, 98% while lowest for Decision tree (DT), 55% p=0.176). There was a statistically significant difference in the accuracy and AUC of diagnostic and interventional models (accuracy; 83.4% vs 69.4%, AUC; 0.882 vs 0.729, p <0.001). Overall, 59.09% (n = 13) and 81.82% (n = 18) of the studies had high-risk bias and high-applicability, respectively, on PROBAST assessment; however only 55.15% of the studies adhered to the TRIPOD statement.Though highly accurate, there are many challenges to current ML models necessitating the need to standardize the ML models to enable comparison across the studies and enhance the NPH decision making and care.Copyright © 2023 Elsevier Inc. All rights reserved.