Get API key

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: 2026-11-06

Model version: d205a6f0

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, 413 videos
Camera (videos) Logitech C920: 113, e-con See3CAM CU27: 111, Samsung S24 Rear 24mm (tripod): 99, Samsung S24 Front 27mm (handheld): 90
Sex (subjects) Female: 63, Male: 55
Age Group (subjects) 18-25: 33, 26-35: 39, 36-45: 18, 46-55: 13, 56-65: 12, 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: 131, Lamp: 130, Window: 98

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.

  • User: Face must be visible, illuminated, and still.
  • Environment: Stable lighting is critical for waveform quality.

These factors can affect model performance:

  • Lighting: Temporal lighting changes degrade waveform quality.
  • Motion: Any motion introduces artifacts in the pressure trace.
  • User: Demographics including skin tone may impact signal quality.
  • Chewing gum can degrade performance.

Lighting Conditions Tested:

  • Ring Light: Direct, front-facing illumination providing consistent lighting on the subject's face.
  • Window: Natural sunlight entering through a window that illuminates the subject's face from the side rather than directly head-on. Lighting intensity varies depending on weather conditions and the time of day when the measurement is collected.
  • Lamp: A room lighting lamp aimed at the ceiling and not directed at the participant, to mimic living room-like environments.

Other factors:

  • Instrumentation: Camera parameter locking (exposure, gain, white balance) is essential.

7. Metrics

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

  1. MAE: 0.37 BPM
  2. RMSE: 0.69 BPM

8. Quantitative Analysis

Computed vs Ground Truth at Confidence Thresholds

Pulse rate in 10.6-second windows, computed vs. ground truth, for the top 50%, the top 80% and all readings by confidence, colored by camera

Bland-Altman Plot

Pulse rate Bland-Altman plot at an 80% return rate: mean difference -0.08 BPM, limits of agreement 1.26 and -1.42 BPM

Confidence Lookup Table

Confidence >= MAE (BPM) RMSE (BPM) Pearson r Return Rate (%) N (samples)
0 0.93 2.96 0.974 100.0 24957
10 0.90 2.82 0.976 99.6 24869
20 0.88 2.74 0.978 99.4 24801
30 0.83 2.55 0.981 98.9 24675
40 0.79 2.39 0.983 98.2 24518
50 0.72 2.13 0.986 97.3 24290
60 0.64 1.81 0.990 96.1 23984
65 0.60 1.60 0.992 95.2 23770
70 0.56 1.42 0.994 94.4 23554
75 0.52 1.25 0.995 93.4 23322
80 0.49 1.08 0.996 92.5 23077
85 0.45 0.94 0.997 91.2 22751
90 0.42 0.81 0.998 89.3 22297
95 0.39 0.72 0.998 84.8 21172
96 0.38 0.70 0.998 82.8 20674
97 0.37 0.69 0.999 80.0 19919
98 0.35 0.64 0.999 74.3 18553
99 0.32 0.59 0.999 63.8 15930

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) 6028 85.5 0.43 0.91 0.998
Samsung S24 Front 27mm (handheld) 1242 62.3 0.36 0.52 0.999
e-con See3CAM CU27 6108 78.0 0.34 0.48 0.999
Logitech C920 6541 80.9 0.33 0.65 0.999

By Fitzpatrick Skin Type

Fitzpatrick N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Type I 4032 93.2 0.33 0.53 0.999
Type II 2368 89.6 0.27 0.39 1.000
Type III 2649 93.0 0.49 1.14 0.997
Type IV 4422 87.2 0.33 0.49 0.999
Type V 5031 72.6 0.37 0.72 0.998
Type VI 1417 45.1 0.49 0.78 0.998
Fitzpatrick Type VI: Breakdown by Lighting Condition
Ring Light 526 53.2 0.36 0.48 0.997
Window 327 34.2 0.55 0.78 0.999
Lamp 427 40.4 0.60 1.07 0.986

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 10045 82.7 0.35 0.70 0.999
Female 9874 77.1 0.38 0.68 0.998

By Age Group

Age Group N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
18-25 5497 82.1 0.46 0.90 0.997
26-35 6546 80.3 0.33 0.46 0.999
36-45 2790 74.0 0.38 0.63 0.999
46-55 2574 84.3 0.27 0.44 1.000
56-65 2271 85.4 0.26 0.35 0.999
65+ 65 16.4 1.80 4.64 0.971

By Lighting Type

Lighting N (samples) Return Rate (%) MAE (BPM) RMSE (BPM) Pearson r
Lamp 6059 77.2 0.43 0.98 0.996
Ring Light 6790 83.4 0.33 0.48 0.999
Window 4086 72.1 0.36 0.57 0.999

Confidence vs Waveform Correlation

Confidence >= Waveform Pearson r Return Rate (%) N (videos)
0 0.683 100.0 370
10 0.683 100.0 370
20 0.683 100.0 370
30 0.683 100.0 370
40 0.687 99.2 367
50 0.693 97.8 362
60 0.697 96.2 356
65 0.700 95.1 352
70 0.704 93.5 346
75 0.707 92.2 341
80 0.709 90.3 334
85 0.716 87.3 323
90 0.720 84.3 312
95 0.731 78.4 290
96 0.739 75.7 280
97 0.738 71.1 263
98 0.740 66.2 245
99 0.736 55.4 205

Waveform Example

Waveform example SF_0011_logi: the SDK arterial pressure waveform over 10 seconds against the Biopac blood pressure reference
Waveform example SF_0002_27mm_001, 15 seconds at high confidence: the SDK arterial pressure waveform against the Biopac blood pressure reference
Waveform example STLW_0594_27mm_002, 15 seconds at low confidence: the SDK arterial pressure waveform against the Biopac blood pressure reference

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

  • Provides relative waveform morphology, not absolute mmHg values
  • Works best in stationary conditions with locked camera parameters
  • Requires sufficient illumination for signal extraction

Download the full model card HTML, 7.1 MB