0
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Development and validation of a deep-learning model to predict 10-year atherosclerotic cardiovascular disease risk from retinal images using the UK Biobank and EyePACS 10K datasets

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Atherosclerotic cardiovascular disease (ASCVD) is a leading cause of death globally, and early detection of high-risk individuals is essential for initiating timely interventions. The authors aimed to develop and validate a deep learning (DL) model to predict an individual’s elevated 10-year ASCVD risk score based on retinal images and limited demographic data.

          Methods

          The study used 89,894 retinal fundus images from 44,176 UK Biobank participants (96% non-Hispanic White, 5% diabetic) to train and test the DL model. The DL model was developed using retinal images plus age, race/ethnicity, and sex at birth to predict an individual’s 10-year ASCVD risk score using the pooled cohort equation (PCE) as the ground truth. This model was then tested on the US EyePACS 10K dataset (5.8% non-Hispanic White, 99.9% diabetic), composed of 18,900 images from 8969 diabetic individuals. Elevated ASCVD risk was defined as a PCE score of ≥7.5%.

          Results

          In the UK Biobank internal validation dataset, the DL model achieved an area under the receiver operating characteristic curve of 0.89, sensitivity 84%, and specificity 90%, for detecting individuals with elevated ASCVD risk scores. In the EyePACS 10K and with the addition of a regression-derived diabetes modifier, it achieved sensitivity 94%, specificity 72%, mean error -0.2%, and mean absolute error 3.1%.

          Conclusion

          This study demonstrates that DL models using retinal images can provide an additional approach to estimating ASCVD risk, as well as the value of applying DL models to different external datasets and opportunities about ASCVD risk assessment in patients living with diabetes.

          Related collections

          Most cited references30

          • Record: found
          • Abstract: not found
          • Article: not found

          2018 AHA/ACC/AACVPR/AAPA/ABC/ACPM/ADA/AGS/APhA/ASPC/NLA/PCNA Guideline on the Management of Blood Cholesterol

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            2013 ACC/AHA Guideline on the Assessment of Cardiovascular Risk

            Supplemental Digital Content is available in the text.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning

              Traditionally, medical discoveries are made by observing associations, making hypotheses from them and then designing and running experiments to test the hypotheses. However, with medical images, observing and quantifying associations can often be difficult because of the wide variety of features, patterns, colours, values and shapes that are present in real data. Here, we show that deep learning can extract new knowledge from retinal fundus images. Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age (mean absolute error within 3.26 years), gender (area under the receiver operating characteristic curve (AUC) = 0.97), smoking status (AUC = 0.71), systolic blood pressure (mean absolute error within 11.23 mmHg) and major adverse cardiac events (AUC = 0.70). We also show that the trained deep-learning models used anatomical features, such as the optic disc or blood vessels, to generate each prediction.
                Bookmark

                Author and article information

                Contributors
                Journal
                Cardiovasc Digit Health J
                Cardiovasc Digit Health J
                Cardiovascular Digital Health Journal
                Elsevier
                2666-6936
                09 January 2024
                April 2024
                09 January 2024
                : 5
                : 2
                : 59-69
                Affiliations
                []Toku Eyes, Auckland, New Zealand
                []Topcon Healthcare, Oakland, New Jersey
                []Institute of Ophthalmology, University College of London, London, United Kingdom
                [§ ]San Mateo Medical Center, San Mateo, California
                []Division of Cardiovascular Medicine, Stanford University School of Medicine, Stanford, California
                []Department of Medicine, Lundquist Institute at Harbor-UCLA Medical Center, Torrance, California
                Author notes
                [] Address reprint requests and correspondence: Dr Ehsan Vaghefi, Toku Eyes, 6 Clayton St, New Market, Auckland, New Zealand, 1023. e.vaghefi@ 123456auckland.ac.nz
                Article
                S2666-6936(24)00001-X
                10.1016/j.cvdhj.2023.12.004
                11096659
                c5fba86b-673b-4b99-92ec-9b45b147f6f8
                © 2024 Heart Rhythm Society.

                This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

                History
                Categories
                Original Article

                cardiovascular disease risk,pooled cohort equation,retinal imaging,artificial intelligence

                Comments

                Comment on this article