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 10.6-second pulse rate (vs EKG) and 60-second waveform analysis (vs BP).

Organization: Presage Technologies

Model date: 2026-07-03

Model version: f6d705f0

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 10.6s 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 10.6s 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 118 subjects, 420 videos
Camera (videos) e-con See3CAM CU27: 114, Logitech C920: 113, Samsung S24 Rear 24mm (tripod): 101, Samsung S24 Front 27mm (handheld): 92
Sex (subjects) Female: 63, Male: 55
Age Group (subjects) 18-25: 34, 26-35: 39, 36-45: 17, 46-55: 15, 56-65: 10, 65+: 2
Fitzpatrick (subjects) Type 1: 21, Type 2: 12, Type 3: 13, Type 4: 24, Type 5: 33, Type 6: 15
BMI (subjects) Mean: 27.9, Range: 16.5–54.3, N=118
Lighting (videos) Ring Light: 133, Lamp: 132, Window: 101

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 >= 97)

  1. MAE: 0.41 BPM
  2. RMSE: 0.66 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 1.17 3.34 0.967 100.0 8631
10 1.11 3.17 0.970 99.5 8588
20 1.08 3.07 0.972 99.3 8568
30 1.05 3.01 0.973 98.9 8533
40 0.99 2.80 0.977 98.2 8472
50 0.89 2.50 0.981 97.0 8376
60 0.79 2.17 0.986 95.6 8255
65 0.74 2.01 0.988 94.9 8193
70 0.70 1.91 0.989 94.0 8109
75 0.64 1.63 0.992 92.9 8018
80 0.59 1.42 0.994 91.8 7920
85 0.52 1.10 0.996 90.2 7785
90 0.49 0.93 0.997 88.3 7625
95 0.44 0.74 0.998 83.8 7229
96 0.42 0.70 0.999 81.8 7060
97 0.41 0.66 0.999 80.0 6789
98 0.39 0.62 0.999 73.1 6311
99 0.37 0.61 0.999 63.0 5441

Performance

(at 80% Return Rate, Confidence >= 97)

By Camera Type

Camera Type N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Samsung S24 Rear 24mm (tripod) 1994 84.7 0.42 0.76 0.998
Samsung S24 Front 27mm (handheld) 881 68.0 0.47 0.83 0.998
e-con See3CAM CU27 1952 78.1 0.41 0.58 0.999
Logitech C920 1962 79.0 0.37 0.53 0.999

By Fitzpatrick Skin Type

Fitzpatrick N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Type I 1341 94.5 0.39 0.60 0.999
Type II 756 84.8 0.32 0.49 0.999
Type III 793 91.0 0.49 0.95 0.998
Type IV 1657 87.2 0.37 0.55 0.999
Type V 1831 74.6 0.41 0.57 0.999
Type VI 411 37.5 0.61 1.11 0.996
Fitzpatrick Type VI: Breakdown by Lighting Condition
Ring Light 166 47.4 0.44 0.60 0.997
Window 86 26.1 0.65 0.94 0.999
Lamp 119 32.2 0.79 1.67 0.966

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 3437 80.7 0.38 0.64 0.999
Female 3352 76.7 0.43 0.68 0.999

By Age Group

Age Group N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
18-25 2026 81.1 0.49 0.79 0.998
26-35 2161 76.5 0.41 0.58 0.999
36-45 872 77.3 0.43 0.71 0.999
46-55 950 85.2 0.26 0.37 1.000
56-65 696 79.9 0.29 0.39 0.999
65+ 42 30.2 0.59 0.86 0.999

By Lighting Type

Lighting N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Lamp 1967 74.9 0.45 0.83 0.998
Ring Light 2303 82.8 0.38 0.53 0.999
Window 1420 71.0 0.42 0.66 0.998

Confidence vs Waveform Correlation

Confidence >= Waveform Pearson r Return Rate (%) N (videos)
0 0.621 100.0 372
10 0.621 100.0 372
20 0.621 100.0 372
30 0.621 100.0 372
40 0.623 99.5 370
50 0.629 98.1 365
60 0.631 96.8 360
65 0.636 94.6 352
70 0.642 91.7 341
75 0.643 91.1 339
80 0.649 89.0 331
85 0.653 86.0 320
90 0.660 82.3 306
95 0.661 77.7 289
96 0.662 74.5 277
97 0.660 70.2 261
98 0.667 63.2 235
99 0.666 50.3 187

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