Investigation of data-driven optical neuromonitoring approach during general anesthesia with sevoflurane

Abstract

Anesthesia monitoring currently needs a reliable method to evaluate the effects of the anesthetics on its primary target, the brain. This study focuses on investigating the clinical usability of a functional near-infrared spectroscopy (fNIRS)-derived machine learning classifier to perform automated and real-time classification of maintenance and emergence states during sevoflurane anesthesia. For 19 surgical procedures, we examine the entire continuum of the maintenance-transition-emergence phases and evaluate the predictive capability of a support vector machine (SVM) classifier during these phases. We demonstrate the robustness of the predictions made by the SVM classifier and compare its performance with that of minimum alveolar concentration (MAC) and bispectral (BIS) index-based predictions. The fNIRS-SVM investigated in this study provides evidence to the usability of the fNIRS signal for anesthesia monitoring. The method presented enables classification of the signal as maintenance or emergence automatically as well as in real-time with high accuracy, sensitivity, and specificity. The features local mean HbTotal, std [Formula: see text], local min Hb and [Formula: see text], and range Hb and [Formula: see text] were found to be robust biomarkers of this binary classification task. Furthermore, fNIRS-SVM was capable of identifying emergence before movement in a larger number of patients than BIS and MAC.

Assessment of Flourishing Levels of Individuals by Using Resting State fNIRS with Different Functional Connectivity Measures

“…In contrast to conventional approach that uses ΔHbO for FC analysis, we also used ΔHb due to previous evidence that suggests both hemoglobin concentrations should be analyzed for sparse networks (Montero-Hernandez et al, 2018b). In addition to this, there are several fNIRS based ML studies that focuses on classification of several psychiatric disorders also uses ΔHb (Cheng et al, 2019; Crippa et al, 2017; Hernandez-Meza et al, 2018; Hernandez-Meza et al, 2017; J. Li et al, 2016; Rosas-Romero et al, 2019; Sirpal et al, 2019; Sutoko et al, 2019) and for some cases ΔHb based features might also show higher accuracy results compared to ΔHbO based ones (Crippa et al, 2017).…”

Near Infrared Spectroscopy for High-Temporal Resolution Cerebral Physiome Characterization in TBI: A Narrative Review of Techniques, Applications, and Future Directions

“…Taking this concept further, Hernandez-Meza et al developed a functional NIRS based machine learning classifier to classify, in real-time, maintenance and emergence states in 19 patients undergoing various surgical procedures with sevoflurane anesthetic. They found that their NIRS based system was able tot detect emergence prior to bispectral index (BIS; Hernandez-Meza et al, 2017). These studies point to a possible role for NIRS in the tailored titration of sedation in the acute setting.…”

Diagnostic Machine Learning Applications on Clinical Populations using Functional Near Infrared Spectroscopy: A Review

“…Two studies were reported to classify the anesthesia phases. In the first study, fNIRS data collected under different anesthesia conditions from 19 patients under surgery was used for analysis (Hernandez-Meza et al, 2017). In this study, anesthesia conditions were identified as maintenance (MC) and emergence (EC).…”

“…SVM is a robust supervised learning algorithm that aims to discriminate the input data by creating a hyperplane with maximum margin according to their previously defined labels as we addressed in the section 5.1 (Vapnik, 1995). It was the most preferred classifier among fNIRS studies (Abtahi et al, 2020; Al-Shargie et al, 2017b; Cheng et al, 2019; Crippa et al, 2017; Dadgostar et al, 2018; Einalou et al, 2016; Eken et al, 2019; Fernandez Rojas et al, 2017, 2019; Gokcay et al, 2019; Gu et al, 2018; Guevara et al, 2020; Hernandez-Meza et al, 2018; Hernandez-Meza et al, 2017; Hosseini et al, 2018; Ichikawa et al, 2014; Karamzadeh et al, 2016; J. Li et al, 2016; Z.…”

“…However, notable number studies also considers about ΔHb as a critical feature source (Cheng et al, 2019; Chiarelli et al, 2021; Cicalese et al, 2020; Crippa et al, 2017; Y. Fukuda et al, 2014; Guevara et al, 2020; Hernandez-Meza et al, 2018; Hernandez-Meza et al, 2017; Koike et al, 2017; J. Li et al, 2016; Parent et al, 2019; Rosas-Romero et al, 2019; Sato et al, 2013; Sirpal et al, 2019; Song et al, 2017; Sutoko et al, 2019; Xu et al, 2019; Xu, Hua, et al, 2020; Xu, Liu, et al, 2020; Xu et al, 2021; Yang et al, 2019; D.…”