TY  - JOUR
AU  - Tan, Selene Y L
AU  - Chai, Jia Xin
AU  - Choi, Minwoo
AU  - Javaid, Umair
AU  - Tan, Brenda Pei Yi
AU  - Chow, Belinda Si Ying
AU  - Abdullah, Hairil Rizal
PY  - 2025
DA  - 2025/6/6
TI  - Remote Photoplethysmography Technology for Blood Pressure and Hemoglobin Level Assessment in the Preoperative Assessment Setting: Algorithm Development Study
JO  - JMIR Form Res
SP  - e60455
VL  - 9
KW  - blood pressure
KW  - hemoglobin
KW  - noninvasive
KW  - telehealth
KW  - remote photoplethysmography
KW  - smartphone
KW  - hypertension
KW  - anemia
KW  - mHealth
KW  - mobile health
KW  - development
KW  - validation
KW  - hypertensive
KW  - systolic
KW  - diastolic
KW  - physiological
AB  - Background: Blood pressure (BP) and hemoglobin concentration measurements are essential components of preoperative anesthetic evaluation. Remote photoplethysmography (rPPG) is an emerging technology that may be used to measure BP and hemoglobin concentration noninvasively with just a consumer-grade smartphone, replacing traditional in-person measurements. However, there is limited data regarding the use of this technology in patients with diverse skin tones and medical comorbidities. Hence, widespread applicability is yet to be achieved. The potential benefits of achieving this would be immense, allowing for greater convenience, accessibility, and reduction in labor and resources. Objective: Our study aims to be the first to develop an algorithm for noninvasive rPPG-based BP and hemoglobin concentration measurement that can be used for preoperative evaluation of patients in real-world clinical practice settings. Methods: We conducted the study at Singapore General Hospital from March 1, 2023, to June 28, 2024. A total of 200 patients were recruited. Our primary analysis compared the accuracy of rPPG-based systolic and diastolic BP measurements against measurements taken with automated BP measuring devices. Our secondary analysis compared the accuracy of rPPG-based hemoglobin concentration measurement against traditional blood sampling. Results: Our model performed best with diastolic BP predictions, with a mean absolute percentage error of 7.52% and a mean difference of 0.16 mm Hg (SD 3.22 mm Hg) between reference and measured readings. The 95% CI for the mean difference between predicted and measured diastolic BP was ±0.57 (−0.41 to 0.73) mm Hg. Systolic BP predictions yielded a mean absolute percentage error of 9.52% and a mean difference of 2.69 mm Hg (SD 7.86 mm Hg). The 95% CI for the mean difference between predicted and measured systolic BP was ±1.14 (−1.54 to −3.83) mm Hg. Hemoglobin concentration predictions had a mean absolute percentage error of 8.52%, with a mean difference of 0.23 g/dL (SD 0.67 g/dL). The 95% CI for the mean difference between predicted and reference measured hemoglobin concentration was ±0.10 (95% CI 0.13‐0.33) g/dL. Conclusions: Noninvasive rPPG-based measurement of BP and hemoglobin concentration at the preoperative evaluation setting has great potential for improving convenience, improving efficiency, and conserving resources for patients and health care providers. Our model was able to accurately predict diastolic BP in patients with diverse skin tones and medical comorbidities. The findings of this study serve as a basis for further studies to develop and validate the model for noninvasive rPPG-based BP and hemoglobin concentration measurement. Trial Registration: ClinicalTrials.gov NCT06320847; https://clinicaltrials.gov/study/NCT06320847 
SN  - 2561-326X
UR  - https://formative.jmir.org/2025/1/e60455
UR  - https://doi.org/10.2196/60455
DO  - 10.2196/60455
ID  - info:doi/10.2196/60455
ER  -