Monitoring Progression in Hypertensive Patients with Dyslipidemia Using Optical Coherence Tomography Angiography: Can A.I. Be Improved?
2024

Using A.I. to Monitor Eye Health in Hypertensive Patients

Sample size: 154 publication 10 minutes Evidence: moderate

Author Information

Author(s): Barca Irina Cristina, Potop Vasile, Arama Stefan Sorin

Primary Institution: “Carol Davila” University of Medicine and Pharmacy, Bucharest, Romania

Hypothesis

OCTA will show subclinical changes in retinal microvasculature in the superficial and deep plexi, i.e., changes related to secondary dyslipidemia and progression of hypertensive retinopathy.

Conclusion

Subjects with dyslipidemia and progressive hypertensive retinopathy had a reduction in microvascular density and vascular flow, which can be monitored using improved A.I. systems.

Supporting Evidence

  • Statistically significant correlations were found between total cholesterol and various OCTA parameters.
  • Participants with higher blood pressure showed increased avascular zones and reduced blood flow.
  • OCTA is a non-invasive method that allows for detailed imaging of retinal microvasculature.

Takeaway

This study looked at how high blood pressure and bad cholesterol affect the tiny blood vessels in the eyes, and how we can use smart computer programs to help doctors see these changes better.

Methodology

A prospective cohort study was conducted on 154 eyes of participants with dyslipidemia and hypertension, using OCTA to measure retinal vascular parameters.

Potential Biases

Potential bias due to the lack of randomization and the exclusion of certain patient groups.

Limitations

The study did not include a control group and had a small sample size of 77 participants.

Participant Demographics

Average age was 56.9 years, with 55.8% males; participants were from Eastern Europe.

Statistical Information

P-Value

p = 0.002 to p = 0.029 for various correlations

Confidence Interval

95% CI for various parameters

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.3390/jcm13247584

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication