Contactless and Calibration-Free Blood Pressure and Pulse Rate Monitor for Screening and Monitoring of Hypertension: Cross-Sectional Validation Study
Bibliographic record
Abstract
BACKGROUND: The key to reducing the immense morbidity and mortality burdens of cardiovascular diseases is to help people keep their blood pressure (BP) at safe levels. This requires that more people with hypertension be identified, diagnosed, and given tools to lower their BP. BP monitors are critical to hypertension diagnosis and management. However, there are characteristics of conventional BP monitors (oscillometric cuff sphygmomanometers) that hinder rapid and effective hypertension diagnosis and management. Calibration-free, software-only BP monitors that operate on ubiquitous mobile devices can enable on-demand BP monitoring, overcoming the hardware barriers of conventional BP monitors. OBJECTIVE: This study aims to investigate the accuracy of a contactless BP monitor software app for classifying the full range of clinically relevant BPs as hypertensive or nonhypertensive and to evaluate its accuracy for measuring the pulse rate (PR) and BP of people with BPs relevant to stage-1 hypertension. METHODS: The software app, known commercially as Lifelight, was investigated following the data collection and data analysis methodology outlined in International Organization for Standardization (ISO) 81060-2:2018/AMD 1:2020 "Non-invasive Sphygmomanometers-Part 2: Clinical investigation of automated measurement type." This validation study was conducted by the independent laboratory Element Materials Technology Boulder (formerly Clinimark). The study generated data from 85 people aged 18-85 years with a wide-ranging distribution of BPs specified in ISO 81060-2:2018/AMD 1:2020. At least 20% were required to have Fitzpatrick scale skin tones of 5 or 6 (ie, dark skin tones). The accuracy of the app's BP measurements was assessed by comparing its BP measurements with measurements made by dual-observer manual auscultation using the same-arm sequential method specified in ISO 81060-2:2018/AMD 1:2020. The accuracy of the app's PR measurements was assessed by comparing its measurements with concurrent electroencephalography-derived heart rate values. RESULTS: The app measured PR with an accuracy root-mean-square of 1.3 beats per minute and mean absolute error of 1.1 (SD 0.8) beats per minute. The sensitivity and specificity with which it determined that BPs exceeded the in-clinic systolic threshold for hypertension diagnosis were 70.1% and 71.7%, respectively. These rates are consistent with those reported for conventional BP monitors in a literature review by The National Institute for Health and Care Excellence. The app's mean error for measuring BP in the range of normotension and stage-1 hypertension (ie, 65/85, 76% of participants) was 6.5 (SD 12.9) mm Hg for systolic BP and 0.4 (SD 10.6) mm Hg for diastolic BP. Mean absolute error was 11.3 (SD 10.0) mm Hg and 8.6 (SD 6.8) mm Hg, respectively. CONCLUSIONS: A calibration-free, software-only medical device was independently tested against ISO 81060-2:2018/AMD 1:2020. The safety and performance demonstrated in this study suggest that this technique could be a potential solution for rapid and scalable screening and management of hypertension.
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 | 0.009 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".