Facial AI Shows Promise for BP Screening - Scorecard - MDSpire

Facial AI Shows Promise for BP Screening

Deep learning model identifies hypertension from facial images with 83% accuracy, with zygomatic and cheek regions performing nearly as well as whole-face analysis

  • By

  • Mouj Hijazi

  • January 14, 2026

  • 3 min

Share

Clinical Scorecard: Facial AI Shows Promise for BP Screening

At a Glance

CategoryDetail
ConditionHypertension
Key MechanismsDeep learning analysis of facial images focusing on zygomatic and cheek regions.
Target PopulationPatients with hypertension and normotensive controls.
Care SettingEveryday environments using standard cameras.

Key Highlights

  • Achieved 83% accuracy in identifying hypertension.
  • Zygomatic and cheek regions showed comparable performance to full-face analysis.
  • Method addresses barriers in hypertension detection such as low screening adherence.
  • Utilizes standard cameras, making it a scalable and non-invasive tool.
  • Study involved 375 patients with hypertension and 131 normotensive controls.

Guideline-Based Recommendations

Diagnosis

  • Use facial image analysis as an initial screening tool for hypertension.

Management

  • Consider facial AI screening as a complementary tool alongside traditional blood pressure measurements.

Monitoring & Follow-up

  • Further research needed to validate findings across larger and more diverse populations.

Risks

  • Small sample size may limit generalizability of results.

Patient & Prescribing Data

Patients with systolic BP ≥ 140 mmHg or diastolic BP ≥ 90 mmHg.

Facial AI screening can help identify hypertension in asymptomatic patients.

Clinical Best Practices

  • Incorporate facial AI as a supplementary screening method in clinical practice.
  • Ensure standardized lighting and imaging conditions for facial image capture.

References

Original Source(s)

Facial AI Shows Promise for BP Screening

  • by Mouj Hijazi

  • January 14, 2026

Related Content

Interruption of the right middle and lower lobe pulmonary arteries combined with arterial aneurysm formation at the origin of the right subclavian artery branch: a case report

Non-Invasive Techniques In Pediatric Dyslipidemia

Damon B. Dixon, MD, at Phoenix Children’s Cardiology, is the author to this EndoText chapter. Dr. Dixon brings nationally recognized expertise in pediatric cardiovascular risk assessment and non?invasive vascular imaging.

  • by

  • May 15, 2026

  • 1 min
Serum uric acid levels and cardiorenal complication prevalence in hypertensive patients before and after the COVID-19 pandemic: a retrospective cross-sectional study from a tertiary traditional Chinese medicine hospital