Impact of multimodal intraoperative neurophysiological monitoring of the spinal cord during spine and spinal cord surgeries

Elwakil, W.; Imam, Mohamed Hassan; Hassan, Mohamed; El-Saadany, Waleed F.; Gaber, Osama

doi:10.1186/s43166-023-00201-0

Cited by 4 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, volatile anesthetics can affect SSEP signal amplitude and latency, prompting the need for multi-modal IONM techniques [15,18,19]. The integration of combined SSEP, TcMEPs, and EMG provides a more accurate and multi-angle viewpoint of the functional integrity of the spinal cord, which can enhance surgical precision and reduce the risk of neurological injury [20][21][22][23]. Nonetheless, the massive amount of data generated from multi-modal monitoring makes it difficult to quantify the range of variability seen from these waveforms.…”

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning Strategies to Model the Effects of Sevoflurane on Somatosensory-Evoked Potentials during Spine Surgery

Wilson,

Kumbhare,

Ronkon

et al. 2023

Diagnostics

View full text Add to dashboard Cite

In this study, a small sample of patients’ neuromonitoring data was analyzed using machine learning (ML) tools to provide proof of concept for quantifying complex signals. Intraoperative neurophysiological monitoring (IONM) is a valuable asset for monitoring the neurological status of a patient during spine surgery. Notably, this technology, when operated by neurophysiologists and surgeons familiar with proper alarm criteria, is capable of detecting neurological deficits. However, non-surgical factors, such as volatile anesthetics like sevoflurane, can negatively influence robust IONM signal generation. While sevoflurane has been shown to affect the latency and amplitude of somatosensory evoked potential (SSEP), a more complex and nuanced analysis of the SSEP waveform has not been performed. In this study, signal processing and machine learning techniques were used to more intricately characterize and predict SSEP waveform changes as a function of varying end-tidal sevoflurane concentration. With data from ten patients who underwent spinal procedures, features describing the SSEP waveforms were generated using principal component analysis (PCA), phase space curves (PSC), and time-frequency analysis (TFA). A minimum redundancy maximum relevance (MRMR) feature selection technique was then used to identify the most important SSEP features associated with changing sevoflurane concentrations. Once the features carrying the maximum amount of information about the majority of signal waveform variability were identified, ML models were used to predict future changes in SSEP waveforms. Linear regression, regression trees, support vector machines, and neural network ML models were then selected for testing. Using SSEP data from eight patients, the models were trained using a range of features selected during MRMR calculations. During the training phase of model development, the highest performing models were identified as support vector machines and regression trees. After identifying the highest performing models for each nerve group, we tested these models using the remaining two patients’ data. We compared the models’ performance metrics using the root mean square error values (RMSEs). The feasibility of the methodology described provides a general framework for the applications of machine learning strategies to further delineate the effects of surgical and non-surgical factors affecting IONM signals.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Machine Learning Strategies to Model the Effects of Sevoflurane on Somatosensory-Evoked Potentials during Spine Surgery

Wilson,

Kumbhare,

Ronkon

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

Electrodiagnostic testing in dogs with disorders of the spinal cord or cauda equina

Lewis

2024

The Veterinary Journal

View full text Add to dashboard Cite

Diagnostic Accuracy of Somatosensory Evoked Potential and Transcranial Motor Evoked Potential in Detection of Neurological Injury in Intradural Extramedullary Spinal Cord Tumor Surgeries: A Short-Term Follow-Up Prospective Interventional Study Experience from Tertiary Care Center of India

Mishra,

Pandey,

Sharma

et al. 2024

Asian J Neurosurg

View full text Add to dashboard Cite

Objectives Intraoperative neuromonitoring (IONM) is an acknowledged tool for real-time neuraxis assessment during surgery. Somatosensory evoked potential (SSEP) and transcranial motor evoked potential (MEP) are commonest deployed modalities of IONM. Role of SSEP and MEP in intradural extramedullary spinal cord tumor (IDEMSCT) surgery is not well established. The aim of this study was to evaluate sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of SSEP and transcranial MEP, in detection of intraoperative neurological injury in IDEMSCT patients as well as their postoperative limb-specific neurological improvement assessment at fixed intervals till 30 days. Materials and Methods Symptomatic patients with IDEMSCTs were selected according to the inclusion criteria of study protocol. On modified McCormick (mMC) scale, their sensory-motor deficit was assessed both preoperatively and postoperatively. Surgery was done under SSEP and MEP (transcranial) monitoring using appropriate anesthetic agents. Gross total/subtotal resection of tumor was achieved as per IONM warning alarms. Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of SSEP and MEP were calculated considering postoperative neurological changes as “reference standard.” Patients were followed up at postoperative day (POD) 0, 1, 7, and 30 for convalescence. Statistical Analysis With appropriate tests of significance, statistical analysis was carried out. Receiver-operating characteristic curve was used to find cutoff point of mMC for SSEP being recordable in patients with higher neurological deficit along with calculation of sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of SSEP and MEP for prediction of intraoperative neurological injury. Results Study included 32 patients. Baseline mean mMC value was 2.59. Under neuromonitoring, gross total resection of IDEMSCT was achieved in 87.5% patients. SSEP was recordable in subset of patients with mMC value less than or equal to 2 with diagnostic accuracy of 100%. MEP was recordable in all patients and it had 96.88% diagnostic accuracy. Statistically significant neurological improvement was noted at POD-7 and POD-30 follow-up. Conclusion SSEP and MEP individually carry high diagnostic accuracy in detection of intraoperative neurological injuries in patients undergoing IDEMSCT surgery. MEP continues to monitor the neuraxis, even in those subsets of patients where SSEP fails to record.

show abstract

Impact of multimodal intraoperative neurophysiological monitoring of the spinal cord during spine and spinal cord surgeries

Cited by 4 publications

References 39 publications

Application of Machine Learning Strategies to Model the Effects of Sevoflurane on Somatosensory-Evoked Potentials during Spine Surgery

Application of Machine Learning Strategies to Model the Effects of Sevoflurane on Somatosensory-Evoked Potentials during Spine Surgery

Electrodiagnostic testing in dogs with disorders of the spinal cord or cauda equina

Diagnostic Accuracy of Somatosensory Evoked Potential and Transcranial Motor Evoked Potential in Detection of Neurological Injury in Intradural Extramedullary Spinal Cord Tumor Surgeries: A Short-Term Follow-Up Prospective Interventional Study Experience from Tertiary Care Center of India

Contact Info

Product

Resources

About