Identifying Airway Obstructions Using Photoplethysmography (PPG)

Knorr-Chung, Bethany R.; McGrath, Susan; Blike, George T.

doi:10.1007/s10877-008-9110-7

Cited by 14 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In patients with obstructive sleep apnea, the size of these inspiratory swings in pulse transit time correlates well with the degree of inspiratory effort. 38 This lack of sensitivity is a major limitation in a clinical setting. 37 In a pilot study, a neural network signal analysis reached a sensitivity of 75% and specificity of 85% in detecting airway obstruction by PPG.…”

Section: Obstructive Apneamentioning

confidence: 99%

Respiration Signals from Photoplethysmography

Nilsson

2013

Anesthesia &Amp; Analgesia

106

View full text Add to dashboard Cite

Pulse oximetry is based on the technique of photoplethysmography (PPG) wherein light transmitted through tissues is modulated by the pulse. In addition to variations in light modulation by the cardiac cycle, the PPG signal contains a respiratory modulation and variations associated with changing tissue blood volume of other origins. Cardiovascular, respiratory, and neural fluctuations in the PPG signal are of different frequencies and can all be characterized according to their sinusoidal components. PPG was described in 1937 to measure blood volume changes. The technique is today increasingly used, in part because of developments in semiconductor technology during recent decades that have resulted in considerable advances in PPG probe design. Artificial neural networks help to detect complex nonlinear relationships and are extensively used in electronic signal analysis, including PPG. Patient and/or probe-tissue movement artifacts are sources of signal interference. Physiologic variations such as vasoconstriction, a deep gasp, or yawn also affect the signal. Monitoring respiratory rates from PPG are often based on respiratory-induced intensity variations (RIIVs) contained in the baseline of the PPG signal. Qualitative RIIV signals may be used for monitoring purposes regardless of age, gender, anesthesia, and mode of ventilation. Detection of breaths in adult volunteers had a maximal error of 8%, and in infants the rates of overdetected and missed breaths using PPG were 1.5% and 2.7%, respectively. During central apnea, the rhythmic RIIV signals caused by variations in intrathoracic pressure disappear. PPG has been evaluated for detecting airway obstruction with a sensitivity of 75% and a specificity of 85%. The RIIV and the pulse synchronous PPG waveform are sensitive for detecting hypovolemia. The respiratory synchronous variation of the PPG pulse amplitude is an accurate predictor of fluid responsiveness. Pleth variability index is a continuous measure of the respiratory modulation of the pulse oximeter waveform and has been shown to predict fluid responsiveness in mechanically ventilated patients including infants. The pleth variability index value depends on the size of the tidal volume and on positive end-expiratory pressure. In conclusion, the respiration modulation of the PPG signal can be used to monitor respiratory rate. It is probable that improvements in neural network technology will increase sensitivity and specificity for detecting both central and obstructive apnea. The size of the PPG respiration variation can predict fluid responsiveness in mechanically ventilated patients.

show abstract

Section: Obstructive Apneamentioning

confidence: 99%

Respiration Signals from Photoplethysmography

Nilsson

2013

Anesthesia &Amp; Analgesia

106

View full text Add to dashboard Cite

show abstract

“…Nonetheless, research efforts to apply machine learning algorithms in monitoring continued, and some applications have shown promise in pediatric anesthesia. Knorr and colleagues used a neural network to identify airway obstructions in postoperative patients based on photoplethysmography . A reliable, accurate application of this technology could have tremendous utility in postoperative pediatric patients, as the majority of critical pediatric airway events occur in the postanesthesia care unit .…”

Section: Machine Learning In Monitoring Of the Pediatric Airwaymentioning

confidence: 99%

Artificial intelligence, machine learning and the pediatric airway

Matava

Pankiv

Ahumada

et al. 2020

Pediatric Anesthesia

View full text Add to dashboard Cite

Artificial intelligence and machine learning are rapidly expanding fields with increasing relevance in anesthesia and, in particular, airway management. The ability of artificial intelligence and machine learning algorithms to recognize patterns from large volumes of complex data makes them attractive for use in pediatric anesthesia airway management. The purpose of this review is to introduce artificial intelligence, machine learning, and deep learning to the pediatric anesthesiologist. Current evidence and developments in artificial intelligence, machine learning, and deep learning relevant to pediatric airway management are presented. We critically assess the current evidence on the use of artificial intelligence and machine learning in the assessment, diagnosis, monitoring, procedure assistance, and predicting outcomes during pediatric airway management. Further, we discuss the limitations of these technologies and offer areas for focused research that may bring pediatric airway management anesthesiology into the era of artificial intelligence and machine learning.

show abstract

“…In a pilot study using neural network signal analysis, airway obstruction was identified by PPG-derived signals (Nonin Medical, USA) in a sample of extubated surgical patients prior to PACU arrival (75% sensitivity and 91% specificity) (45). When AHI > 68%, Romem et al found that PPG demonstrated 70% sensitivity and 91% specificity compared to PSG (46).…”

Section: Ppg-derived Signal For Rrmentioning

confidence: 99%

“…At present, there are several studies about PPG for the evaluation of sleep apnea (48–50). However, there are limited reports of PPG as the special monitoring tool for postoperative OSA patients, although RR is regarded as a clinically important parameter for monitoring the respiratory condition (45, 51). …”

Section: Ppg-derived Signal For Rrmentioning

confidence: 99%

A Brief Review of Non-invasive Monitoring of Respiratory Condition for Extubated Patients with or at Risk for Obstructive Sleep Apnea after Surgery

et al. 2017

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA) is one of the important risk factors contributing to postoperative airway complications. OSA alters the respiratory physiology and increases the sensitivity of muscle tone of the upper airway after surgery to residual anesthetic medication. In addition, the prevalence of OSA was reported to be much higher among surgical patients than the general population. Therefore, appropriate monitoring to detect early respiratory impairment in postoperative extubated patients with possible OSA is challenging. Based on the comprehensive clinical observation, several equipment have been used for monitoring the respiratory conditions of OSA patients after surgery, including the continuous pulse oximetry, capnography, photoplethysmography (PPG), and respiratory volume monitor (RVM). To date, there has been no consensus on the most suitable device as a recommended standard of care. In this review, we describe the advantages and disadvantages of some possible monitoring strategies under certain clinical conditions. According to the literature, the continuous pulse oximetry, with its high sensitivity, is still the most widely used device. It is also cost-effective and convenient to use but has low specificity and does not reflect ventilation. Capnography is the most widely used device for detection of hypoventilation, but it may not provide reliable data for extubated patients. Even normal capnography cannot exclude the existence of hypoxia. PPG shows the state of both ventilation and oxygenation, but its sensitivity needs further improvement. RVM provides real-time detection of hypoventilation, quantitative precise demonstration of respiratory rate, tidal volume, and MV for extubated patients, but no reflection of oxygenation. Altogether, the sole use of any of these devices is not ideal for monitoring of extubated patients with or at risk for OSA after surgery. However, we expect that the combined use of continuous pulse oximetry and RVM may be promising for these patients due to their complementary function, which need further study.

show abstract

Identifying Airway Obstructions Using Photoplethysmography (PPG)

Abstract: The accuracy of this method shows promise for use in real-time monitoring situations.

Cited by 14 publications

References 22 publications

Respiration Signals from Photoplethysmography

Respiration Signals from Photoplethysmography

Artificial intelligence, machine learning and the pediatric airway

A Brief Review of Non-invasive Monitoring of Respiratory Condition for Extubated Patients with or at Risk for Obstructive Sleep Apnea after Surgery

Contact Info

Product

Resources

About