Intraoperative neurophysiological monitoring (IOM) enables a function-preserving surgical strategy for surgeries of brain or spinal cord pathologies by neurophysiological measurements. However, the IOM data management at neurosurgical institutions are often either not digitized or inefficient in terms of collecting, storing and processing of IOM data. Here, we describe the development of a web application, called IOM-Manager, as a first step towards the complete digitization of the IOM workflow. The web application is used for structured protocoling based on standardized protocol entry catalog, data archiving, and data analysis. These functionalities are based on the results of the requirement engineering of a process analysis, a survey with potential users and a market analysis. A usability test with one IOM team indicated the IOM-Manager and its other components can in fact solve many problems of existing solutions.

Background:Intraoperative neurophysiological monitoring (IONM) guides the surgeon in ensuring motor pathway integrity during high-risk neurosurgical and orthopedic procedures. Although motor evoked potentials (MEPs) are valuable for predicting motor outcomes, the key features of predictive signals are not well understood, and standardized warning criteria are lacking. Objective:The objective of this study is to expand machine learning (ML) methods for muscle classification and test them in a bicentric setup. Further, we aim to identify key features of MEP signals that contribute to accurate muscle classification using explainable artificial intelligence (XAI) techniques. Methods:This study employed ML and deep learning models, specifically random forest (RF) classifiers and convolutional neural networks (CNNs), to classify MEP signals from two medical centers according to muscle identity. Depending on the algorithm, time-series, feature-engineered, and time-frequency representations of the MEP data were used. XAI techniques, specifically SHAP values and gradient class activation maps (Grad-CAM), were implemented to identify important signal features. Results:High classification accuracy was achieved with the RF classifier, reaching 87.9% accuracy on the validation set and 80.0% accuracy on the test set. The 1D- and 2D-CNNs demonstrated comparably strong performance. Our XAI findings indicate that frequency components and peak latencies are crucial for accurate MEP classification, providing insights that could inform intraoperative warning criteria. Conclusions:This study demonstrates the effectiveness of ML techniques and the importance of XAI in enhancing trust in and reliability of AI-driven IONM applications. Further it may help to identify new intrinsic features of MEP signals so far overlooked in conventional warning criteria.

Background Even for an experienced neurophysiologist, it is challenging to look at a single graph of an unlabeled motor evoked potential (MEP) and identify the corresponding muscle. We demonstrate that supervised machine learning (ML) can successfully perform this task. Methods Intraoperative MEP data from supratentorial surgery on 36 patients was included for the classification task with 4 muscles: Extensor digitorum (EXT), abductor pollicis brevis (APB), tibialis anterior (TA) and abductor hallucis (AH). Three different supervised ML classifiers (random forest (RF), k-nearest neighbors (kNN) and logistic regression (LogReg)) were trained and tested on either raw or compressed data. Patient data was classified considering either all 4 muscles simultaneously, 2 muscles within the same extremity (EXT versus APB), or 2 muscles from different extremities (EXT versus TA). Results In all cases, RF classifiers performed best and kNN second best. The highest performances were achieved on raw data (4 muscles 83%, EXT versus APB 89%, EXT versus TA 97% accuracy). Conclusions Standard ML methods show surprisingly high performance on a classification task with intraoperative MEP signals. This study illustrates the power and challenges of standard ML algorithms when handling intraoperative signals and may lead to intraoperative safety improvements.

In neurosurgery, intraoperative neurophysiological monitoring (IOM) with continuous measurements of neural electrical activity may reduce the risk of postoperative deficits. During an IOM, surgical information as well as neurophysiological, surgical and anesthesia events have to be recorded. So far, there is no common standard for this task available. In this paper, such a standardization with the aim of facilitating the data input and making the protocols data available for different sorts of analyses is described. We developed a protocol entry catalog with 200 standard expressions, which were divided into four categories: IOM, surgical procedure, anesthesia and others. An empirical assessment of the catalog by the IOM team showed the need for subcategories. In the final version of the catalog, the standard terms were grouped into 25 subcategories. The catalog is a first step to support systematic research into the occurrence of clinical events during the IOM and their association with postoperative neurological deficits that could enable improved surgical procedures in the future.

Background: We elucidate the decision making that lies behind artificial intelligence (AI) algorithms in the example of muscle classification in intraoperative neurophysiological monitoring (IONM). The goal is to uncover decisive parameters in motor evoked potentials (MEP) to understand intraoperative changes and optimize AI decision making. Methods: We classified MEP in supratentorial surgery in a bi-centric setup, training on 160 patients from one center and validating on 50 patients from an independent center. We trained random forests (RF), and 1D and 2D convolutional neural nets (CNN) on a total of 37’000 MEPs and uncovered the decision making by looking into the feature importance and gradient class activation maps (Grad-CAM). Results: The RF achieved 89% test accuracy and 80% accuracy on the validation dataset from the independent center, whereas the 1D CNN achieved 85% test and 76% validation accuracy. Finally, the 2D CNN achieved 86% test and 81% valication accuracy. Inspecting the RF feature importance reveals that the algorithm focuses on the time interval where the potential has highest amplitude. On the other hand, the grad-CAM reveals that the CNNs might be focusing on the biggest slope of the potential. Conclusions: Analyzing the decision making of artificial intelligence algorithms is an essential part of ensuring the quality and evidence behind the good performances of these methods. Understanding this rationale will be crucial when improving intraoperative MEP alarm criteria. We showed the key features during identification of MEPs and validated the results in a bicentric setup. To our knowledge, it is the first time an IONM machine learning classification task has been implemented in a multicenter set-up.