Remote Photoplethysmography Technology for Blood Pressure and Hemoglobin Level Assessment in the Preoperative Assessment Setting: Algorithm Development Study
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".