Identifying Airway Obstructions Using Photoplethysmography (PPG)

Objective. Central and obstructive apneas are sources of morbidity and mortality associated with primary patient conditions as well as secondary to medical care such as sedation/analgesia in post-operative patients. This research investigates the predictive value of the respirophasic variation in the noninvasive photoplethysmography (PPG) waveform signal in detecting airway obstruction. Methods. PPG data from 20 consenting healthy adults (12 male, 8 female) undergoing anesthesia were collected directly after surgery and before transfer to the Post Anesthesia Care Unit (PACU). Features of the PPG waveform were calculated and used in a neural network to classify normal and obstructive events. Results. During the postoperative period studied, the neural network classifier yielded an average (±standard deviation) 75.4 (±3.7)% sensitivity, 91.6 (±2.3)% specificity, 84.7 (±3.5)% positive predictive value, 85.9 (±1.8)% negative predictive value, and an overall accuracy of 85.4 (±2.0)%. Conclusions. The accuracy of this method shows promise for use in real-time monitoring situations.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Welcome Guimera,et al.  Practice Guidelines for Sedation and Analgesia by Non- Anesthesiologists , 2005 .

[3]  J. N. Watson,et al.  An Algorithm for the Detection of Individual Breaths from the Pulse Oximeter Waveform , 2004, Journal of clinical monitoring and computing.

[4]  W S May,et al.  Respiratory Monitoring , 1986, International anesthesiology clinics.

[5]  H F Mahieu,et al.  Photoelectric plethysmography--some fundamental aspects of the reflection and transmission method. , 1981, Clinical physics and physiological measurement : an official journal of the Hospital Physicists' Association, Deutsche Gesellschaft fur Medizinische Physik and the European Federation of Organisations for Medical Physics.

[6]  K. Bloch,et al.  Monitoring of ventilation during exercise by a portable respiratory inductive plethysmograph. , 2005, Chest.

[7]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[8]  K. Nakajima,et al.  Monitoring of heart and respiratory rates by photoplethysmography using a digital filtering technique. , 1996, Medical engineering & physics.

[9]  C. Blitt.  Monitoring in anesthesia and critical care medicine , 1987 .

[10]  A. Johansson.  Neural network for photoplethysmographic respiratory rate monitoring , 2003, Medical and Biological Engineering and Computing.

[11]  James S Hagood,et al.  Estimation of airway obstruction using oximeter plethysmograph waveform data , 2005, Respiratory research.

[12]  C. Patterson.  Joint Commission on Accreditation of Healthcare Organizations , 1995, Infection Control & Hospital Epidemiology.

[13]  Xu-Sheng Zhang,et al.  Modeling for neuromonitoring depth of anesthesia. , 2002, Critical reviews in biomedical engineering.

[14]  Amparo Alonso-Betanzos,et al.  A new method for sleep apnea classification using wavelets and feedforward neural networks , 2005, Artif. Intell. Medicine.

[15]  Z H Khan,et al.  Artificial neural network and medicine. , 1998, Indian journal of physiology and pharmacology.

[16]  Zoltán Benyó,et al.  Detection of airway obstructions and sleep apnea by analyzing the phase relation of respiration movement signals , 2003, IEEE Trans. Instrum. Meas..

[17]  A P Wheeler,et al.  Use of pulse oximetry to recognize severity of airflow obstruction in obstructive airway disease: correlation with pulsus paradoxus. , 1999, Chest.

[18]  C. Eswaran,et al.  Automated Detection of Anesthetic Depth Levels Using Chaotic Features with Artificial Neural Networks , 2007, Journal of Medical Systems.

[19]  B Hök,et al.  Postanesthesia monitoring revisited: frequency of true and false alarms from different monitoring devices. , 1994, Journal of clinical anesthesia.

[20]  G B Drummond,et al.  Thoracic impedance used for measuring chest wall movement in postoperative patients. , 1996, British journal of anaesthesia.

[21]  T. Strömberg,et al.  Influence of Tidal Volume and THoraco-abdominal Separation on the Respiratory Induced Variation of the Photoplethysmogram , 2004, Journal of clinical monitoring and computing.

[22]  A. Aarabi,et al.  A multistage knowledge-based system for EEG seizure detection in newborn infants , 2007, Clinical Neurophysiology.

[23]  Carol L. Lake,et al.  Clinical Monitoring: Practical Applications for Anesthesia and Critical Care , 2001 .

[24]  A. Walden,et al.  Spectral analysis for physical applications : multitaper and conventional univariate techniques , 1996 .

[25]  Metin Akay,et al.  Biomedical Signal Processing , 2020, Series in BioEngineering.

[26]  L. Nilsson,et al.  Respiration can be monitored by photoplethysmography with high sensitivity and specificity regardless of anaesthesia and ventilatory mode , 2005, Acta anaesthesiologica Scandinavica.

[27]  G. S. Makin,et al.  Velocity of Blood Flow in Normal Human Venae Cavae , 1968 .

[28]  Donna L. Hudson,et al.  Neural networks and artificial intelligence for biomedical engineering , 1999 .