Predicting hypoxic hypoxia using machine learning and wearable sensors

Snider, Dallas; Linnville, Steven; Phillips, Jeffrey B.; Rice, G Merrill

doi:10.1016/j.bspc.2021.103110

Cited by 8 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tong et al 46 computed the Shannon entropy (SE) on the EEG signal before and after hypoxic–ischemic brain injury, obtaining lower SE values in the delta and theta bands immediately after the hypoxia compared to the baseline (i.e., before the hypoxic state). Modulation in theta spectral power during cerebral hypoxia has been widely demonstrated in several studies 47–50 . In particular, the slowing of the EEG signal, namely the increase in theta rhythm amplitude, has been associated with the reduction in cerebral blood flow, the consequent vasoconstriction, and the decrease in oxygen supply within the cerebral cortex.…”

Section: Discussionmentioning

confidence: 98%

“…Modulation in theta spectral power during cerebral hypoxia has been widely demonstrated in several studies. [47][48][49][50] T A B L E 1 Significant p values obtained with false discovery rate (FDR) correction and corresponding Cohen's effect size values reported for each electrode in both the entire EEG spectrum and theta frequency bands. In particular, the slowing of the EEG signal, namely the increase in theta rhythm amplitude, has been associated with the reduction in cerebral blood flow, the consequent vasoconstriction, and the decrease in oxygen supply within the cerebral cortex.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Complexity analysis from EEG data in congestive heart failure: A study via approximate entropy

et al. 2023

View full text Add to dashboard Cite

Aim Congestive heart failure (CHF) is a very complex clinical syndrome that may lead to ischemic cerebral hypoxia condition. The aim of the present study is to analyze the effects of CHF on brain activity through electroencephalographic (EEG) complexity measures, like approximate entropy (ApEn). Methods Twenty patients with CHF and 18 healthy elderly people were recruited. ApEn values were evaluated in the total spectrum (0.2–47 Hz) and main EEG frequency bands: delta (2–4 Hz), theta (4–8 Hz), alpha 1 (8–11 Hz), alpha 2 (11–13 Hz), beta 1 (13–20 Hz), beta 2 (20–30 Hz), and gamma (30–45 Hz) to identify differences between CHF group and control. Moreover, a correlation analysis was performed between ApEn parameters and clinical data (i.e., B‐type natriuretic peptides (BNP), New York Heart Association (NYHA), and systolic blood pressure (SBP)) within the CHF group. Results Statistical topographic maps showed statistically significant differences between the two groups in the total spectrum and theta frequency band. Within the CHF group, significant negative correlations were found between total ApEn and BNP in O2 channel and between theta ApEn and NYHA scores in Fp1, Fp2, and Fz channels; instead, a significant positive correlation was found between theta ApEn and SBP in C3 channel and a nearly significant positive correlation was obtained between theta ApEn and SBP in F4 channel. Conclusion EEG abnormalities in CHF are very similar to those observed in cognitive‐impaired patients, suggesting analogies between the effects of neurodegeneration and brain chronic hypovolaemia due to heart disorder and underlying high brain sensitivity to CHF.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Discussionmentioning

confidence: 99%

Complexity analysis from EEG data in congestive heart failure: A study via approximate entropy

et al. 2023

View full text Add to dashboard Cite

show abstract

Section: Neurological Signalsmentioning

confidence: 99%

“…EEG has been found to be an informative signal for both physical and psychological health. Recent work with EEG has looked at monitoring or predicting a variety of conditions; Snider et al [111] for instance used a commercial EEG headset and multiple machine learning models to predict hypoxia in pilots. The device and associated models were evaluated on military pilots and piloting students in a flight simulator using a mask capable of placing the subjects in a hypoxic state.…”

Section: Physical and Psychological Health Monitoringmentioning

confidence: 99%

Advances in Biosignal Sensing and Signal Processing Methods with Wearable Devices

2022

View full text Add to dashboard Cite

Analysis & Sensing www.analysis-sensing.org Review doi.org/10.1002/anse.202200062Wearable devices have received significant attention recently for their ability to monitor critical physiological signals noninvasively, such as electrocardiography, electroencephalography, electromyography, and photoplethysmography. These biointegrated wearable systems can potentially fill gaps in conventional clinical practice by providing highly cost-effective health characterization and portable continuous health monitoring. Further, the physiological signals measured by wearables require post-processing to derive meaningful values, such as heart rate or blood oxygen saturation. This requirement, in conjunction with the smaller form factor and limited sensor count of the miniaturized systems, often necessitates robust signal processing and data analysis to approach the stringent performance specifications of conventional medical devices, and machine learning techniques have found success in filling this analytical role for their ability to learn complex functional relationships. Thus, this review outlines a systematic summary of the latest research on various wearable devices and their biosignal sensing and signal processing methods, emphasizing machine learning. We also discuss the developmental challenges and advantages of current machine-learning methods, while suggesting research directions for future studies.

show abstract

“…In the clinical setting, EEG signals combined with machine learning have recently been used for identifying sleep disorders, epilepsy, strokes, and other neurological disorders [ 44 ]. To date, we have found only a flight hypoxia detection system designed to classify normal from hypoxic instances using the transformed EEG data, which were processed on the naïve Bayes, decision tree, random forest, and neural network algorithms, with sensitivity and specificity ranging from 0.83~1.00 and 0.91~1.00, respectively [ 45 ]. From a neuro-cognitive perspective, Knudsen’s attentional model proposed that inhibition of task-irrelevant processes played a vital role in sustained attention tasks [ 46 , 47 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based on Event-Related EEG of Sustained Attention Differentiates Adults with Chronic High-Altitude Exposure from Healthy Controls

et al. 2022

View full text Add to dashboard Cite

(1) Objective: The aim of this study was to examine the effect of high altitude on inhibitory control processes that underlie sustained attention in the neural correlates of EEG data, and explore whether the EEG data reflecting inhibitory control contain valuable information to classify high-altitude chronic hypoxia and plain controls. (2) Methods: 35 chronic high-altitude hypoxic adults and 32 matched controls were recruited. They were required to perform the go/no-go sustained attention task (GSAT) using event-related potentials. Three machine learning algorithms, namely a support vector machine (SVM), logistic regression (LR), and a decision tree (DT), were trained based on the related ERP components and neural oscillations to build a dichotomous classification model. (3) Results: Behaviorally, we found that the high altitude (HA) group had lower omission error rates during all observation periods than the low altitude (LA) group. Meanwhile, the ERP results showed that the HA participants had significantly shorter latency than the LAs for sustained potential (SP), indicating vigilance to response-related conflict. Meanwhile, event-related spectral perturbation (ERSP) analysis suggested that lowlander immigrants exposed to high altitudes may have compensatory activated prefrontal cortexes (PFC), as reflected by slow alpha, beta, and theta frequency-band neural oscillations. Finally, the machine learning results showed that the SVM achieved the optimal classification F1 score in the later stage of sustained attention, with an F1 score of 0.93, accuracy of 92.54%, sensitivity of 91.43%, specificity of 93.75%, and area under ROC curve (AUC) of 0.97. The results proved that SVM classification algorithms could be applied to identify chronic high-altitude hypoxia. (4) Conclusions: Compared with other methods, the SVM leads to a good overall performance that increases with the time spent on task, illustrating that the ERPs and neural oscillations may provide neuroelectrophysiological markers for identifying chronic plateau hypoxia.

show abstract

Predicting hypoxic hypoxia using machine learning and wearable sensors

Cited by 8 publications

References 16 publications

Complexity analysis from EEG data in congestive heart failure: A study via approximate entropy

Complexity analysis from EEG data in congestive heart failure: A study via approximate entropy

Advances in Biosignal Sensing and Signal Processing Methods with Wearable Devices

Machine Learning Based on Event-Related EEG of Sustained Attention Differentiates Adults with Chronic High-Altitude Exposure from Healthy Controls

Contact Info

Product

Resources

About