Exploratory Study to Evaluate Respiratory Rate Using a Thermal Imaging Camera

Abstract

Background: Respiratory rate is a vital physiological measurement used in the immediate assessment of unwell children and adults. Convenient electronic devices exist for the measurement of pulse, blood pressure, oxygen saturation, and temperature. Although devices which measure respiratory rate exist, none have entered everyday clinical practice for acute assessment of children and adults. An accurate and practical device which has no physical contact with the patient is important to ensure readings are not affected by distress caused by the assessment method. Objective: The aim of this study was to evaluate the use of a thermal imaging method to monitor the respiratory rate in children and adults. Methods: Facial thermal images of adult volunteers and children undergoing elective polysomnography were included. Respiration was recorded for at least 2 min with the camera positioned 1 m from the subject’s face. Values obtained using the thermal imaging camera were compared with those obtained from contact methods such as the nasal thermistor, respiratory inductance plethysmography, nasal airflow, and end tidal CO₂. Results: A total of 61 subjects, including 41 adults (age range 27–46 years) and 20 children (age range 0.5–18 years) were enrolled. The correlation between the respiratory rate measured using thermal imaging and the contact method was r = 0.94. Sequential refinements to the thermal imaging algorithms resulted in the ability to perform real-time measurements and an improvement of the correlation to r = 0.995. Conclusion: This exploratory study shows that thermal imaging-derived respiratory rates in children and adults correlate closely with the best performing standard method. With further refinements, this method could be implemented in both acute and chronic care in children and adults.

A Review of the State of the Art in Non-Contact Sensing for COVID-19

“…The primary disadvantage of using this method is the cost of thermal and depth cameras and the camera operators. Although the price of these cameras is falling gradually, it remains substantially high [ 57 ]. The cost of the equipment is of course less expensive than methods such as CT and X-ray scanning, but still more expensive than other methods discussed further in this paper.…”

Non-contact thermography-based respiratory rate monitoring in a post-anesthetic care unit

“…Therefore, the classifier must be trained again using current data. A recent study [ 17 ] showed that adding automated thermal detection algorithms to contact methods improved RR detection compared with the contact method alone. However, the feasibility of the automated thermal model alone was not clarified.…”

A Broader Look: Camera-Based Vital Sign Estimation across the Spectrum

“…For example, 21 and 22 present results from a video dataset of 70 patients “during the immediate recovery after cardiac surgery” 21 with an average duration of 28.6 minutes. Elphick et al report results on 61 sleeping subjects (41 adults, 20 children) 23 . Although using healthy subjects under laboratory conditions, three published papers present results on more than 50 subjects, namely Fan and Li (65 subjects, one minute each) 24 , Cerina et al (60 subjects, five minutes each) 25 and Vieira Moco et al (54 subjects for model calibration, duration not reported) 26 .…”