Presage Arterial Pressure Waveform and Pulse Rate Model Card

THE FOLLOWING INFORMATION, AND PRESAGE'S SDK AND APP, ARE OFFERED FOR GENERAL WELLNESS AND INFORMATIONAL PURPOSES ONLY. NEITHER HAVE BEEN CLEARED BY THE FDA AND NEITHER MAY BE USED FOR MEDICAL DIAGNOSIS OR TREATMENT.

1. Model Details

Basic info: Presage vitals by video analysis generates a relative arterial pressure waveform and pulse rate from a video of a subject. This card covers 8-second pulse rate (vs EKG) and 60-second waveform analysis (vs BP).

Organization: Presage Technologies

Model date: 2026-03-18

Model version: 3.0.0-rc.8

Model type: A proprietary computer vision and signal processing pipeline extracts a relative arterial pressure waveform and pulse rate from video of a subject. Pulse rate is compared against EKG at 8s windows. The waveform is z-score normalized and compared against the Biopac BP reference at 60s windows.

License: The algorithm is currently proprietary, and licenses are granted with predefined agreement.

Contact: Questions can be sent to: support@presagetech.com

2. Intended Use

Model Uses

This model was intended for use in the analysis and non-diagnostic utility of arterial pressure waveform morphology and pulse rate. Requires a stationary device and video of a subject acquired at 25+ fps. Pulse rate range: 40-180 BPM.

Out-of-Scope Uses

As noted above. Not intended for diagnostic blood pressure measurement. Does not provide absolute systolic, diastolic, or MAP values in mmHg. Not an arrhythmia detection or monitoring device.

3. Validation

Reference Standard: Biopac MP160 3-lead ECG (for pulse rate comparison at 8s windows) and Biopac continuous blood pressure monitor (for waveform correlation at 60s windows). Waveforms z-score normalized before comparison.

Comparison Methodology: Arterial Pressure Waveform measurements from the camera-based system were compared against time-aligned reference measurements. Ground truth signals were checked for quality using labeled signal annotations; segments with poor signal quality were excluded from analysis.

4. Data Demographics

Category Distribution
Total 119 subjects, 429 videos
Camera (videos) Logitech C920: 117, e-con See3CAM CU27: 114, Samsung S24 Rear 24mm (tripod): 102, Samsung S24 Front 27mm (handheld): 96
Sex (subjects) Female: 63, Male: 56
Age Group (subjects) 18-25: 38, 26-35: 35, 36-45: 18, 46-55: 15, 56-65: 10, 65+: 2
Fitzpatrick (subjects) Type 1: 21, Type 2: 13, Type 3: 13, Type 4: 24, Type 5: 33, Type 6: 15
BMI (subjects) Mean: 27.9, Range: 16.5–54.3, N=119
Lighting (videos) Lamp: 136, Ring Light: 133, Window: 103

Reference standard: Biopac EKG and continuous blood pressure monitor.

5. Data Provenance

Reference Instrumentation: Biopac research-grade physiological sensors: 3-lead ECG (for pulse rate ground truth), continuous blood pressure monitor (for waveform correlation ground truth).

Camera Devices Tested: Samsung S24 Rear 24mm (tripod), Samsung S24 Front 27mm (handheld), e-con See3CAM CU27 (USB), Logitech C920 (tripod).

Average Camera Distance: Samsung S24/e-con/Logitech: 26", Samsung S24 handheld: 10"

Data Handling: All subject data is de-identified. Derived metrics and anonymized identifiers are retained. Data is securely stored with access restricted to trained researchers.

6. Factors

The arterial pressure model requires face detection and high-quality photoplethysmographic signal extraction.


These factors can affect model performance:


Lighting Conditions Tested:


Other factors:

7. Metrics

(at 80% Return Rate, Confidence >= 19)

  1. MAE: 1.13 BPM
  2. RMSE: 2.25 BPM

8. Quantitative Analysis

Computed vs Ground Truth at Confidence Thresholds

Bland-Altman Plot

Confidence Lookup Table

Confidence >= MAE (BPM) RMSE (BPM) Pearson r Return Rate (%) N (samples)
0 1.64 4.01 0.953 100.0 100721
10 1.21 2.49 0.981 88.9 89574
19 1.13 2.25 0.984 80.0 80736
20 1.12 2.21 0.984 78.9 79515
30 1.04 1.89 0.986 67.4 67840
40 0.95 1.59 0.990 57.8 58198
50 0.89 1.39 0.992 48.3 48619
60 0.84 1.29 0.993 39.2 39444
65 0.82 1.24 0.994 34.8 35045
70 0.79 1.17 0.995 30.3 30566
75 0.76 1.11 0.995 26.1 26326
80 0.74 1.06 0.996 22.0 22167
85 0.72 1.01 0.996 18.1 18265
90 0.69 0.96 0.997 14.6 14728
95 0.68 0.93 0.997 11.3 11402

Performance

(at 80% Return Rate, Confidence >= 19)

By Camera Type

Camera Type N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Samsung S24 Rear 24mm (tripod) 22546 80.6 1.10 2.09 0.986
Samsung S24 Front 27mm (handheld) 6158 77.3 1.42 3.52 0.961
e-con See3CAM CU27 25888 80.1 1.09 1.86 0.988
Logitech C920 26144 80.6 1.13 2.35 0.982

By Fitzpatrick Skin Type

Fitzpatrick N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Type I 12621 73.9 1.05 1.54 0.991
Type II 9017 84.3 1.13 2.11 0.988
Type III 9937 86.6 1.23 2.73 0.983
Type IV 17022 81.7 0.99 1.55 0.991
Type V 23711 83.4 1.10 2.43 0.978
Type VI 8428 69.0 1.48 3.13 0.969
Fitzpatrick Type VI: Breakdown by Lighting Condition
Ring Light 3016 76.7 1.04 1.79 0.970
Window 2104 63.1 1.46 3.40 0.986
Lamp 2752 63.4 2.05 4.16 0.776

Note: Types I-V are composites across all lighting conditions (Ring Light, Window, Lamp).

By Sex

Sex N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Male 38188 78.8 1.10 2.06 0.987
Female 42548 81.4 1.16 2.40 0.980

By Age Group

Age Group N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
18-25 25455 77.7 1.27 2.33 0.981
26-35 22489 76.5 1.21 2.18 0.979
36-45 11340 78.4 1.32 2.70 0.982
46-55 11970 94.0 0.67 1.33 0.996
56-65 7982 88.3 0.68 1.14 0.993
65+ 568 41.5 3.77 8.81 0.916

By Lighting Type

Lighting N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Lamp 23630 75.7 1.34 3.06 0.964
Ring Light 27060 86.3 1.01 1.59 0.991
Window 19791 82.8 1.06 2.03 0.985

Confidence vs Waveform Correlation

Confidence >= Waveform Pearson r Return Rate (%) N (videos)
0 0.678 100.0 383
10 0.692 96.6 370
20 0.705 88.0 337
30 0.707 74.2 284
40 0.714 62.7 240
50 0.720 47.5 182
60 0.734 36.6 140
65 0.735 29.2 112
70 0.730 23.8 91
75 0.719 17.2 66
80 0.725 13.1 50
85 0.747 8.6 33
90 0.735 6.0 23
95 0.739 2.3 9

Waveform Example

9. Fairness & Equity

Bias Assessment Methodology: Performance is stratified by Fitzpatrick skin type (I-VI), sex, camera type, and age group. Per-group metrics and Confidence averages are reported in the Quantitative Analysis tables above.

10. Ethical Considerations

As a remote sensing device, the risks posed to the subjects in the trial are minimal, including the association of each subject with corresponding biometric data. Mitigation of these risks include de-identifying all subject data, including videos, prior to saving it. Additionally, all data is securely stored with access to a select number of trained researchers.

The model is not intended for human life-critical decisions, diagnostics or prognostication.

11. Limitations and Tradeoffs