Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes
Abstract Background Prior studies have demonstrated an association between retinal vascular features and cardiovascular disease (CVD), however most studies have only evaluated a few simple parameters at a time. Our aim was to determine whether a deep-learning artificial intelligence (AI) model could...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | Cardiovascular Diabetology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12933-024-02564-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559897214287872 |
|---|---|
| author | Mohammad Ghouse Syed Emanuele Trucco Muthu R. K. Mookiah Chim C. Lang Rory J. McCrimmon Colin N. A. Palmer Ewan R. Pearson Alex S. F. Doney Ify R. Mordi |
| author_facet | Mohammad Ghouse Syed Emanuele Trucco Muthu R. K. Mookiah Chim C. Lang Rory J. McCrimmon Colin N. A. Palmer Ewan R. Pearson Alex S. F. Doney Ify R. Mordi |
| author_sort | Mohammad Ghouse Syed |
| collection | DOAJ |
| description | Abstract Background Prior studies have demonstrated an association between retinal vascular features and cardiovascular disease (CVD), however most studies have only evaluated a few simple parameters at a time. Our aim was to determine whether a deep-learning artificial intelligence (AI) model could be used to predict CVD outcomes from routinely obtained diabetic retinal screening photographs and to compare its performance to a traditional clinical CVD risk score. Methods We included 6127 individuals with type 2 diabetes without myocardial infarction or stroke prior to study entry. The cohort was divided into training (70%), validation (10%) and testing (20%) cohorts. Clinical 10-year CVD risk was calculated using the pooled cohort equation (PCE) risk score. A polygenic risk score (PRS) for coronary heart disease was also obtained. Retinal images were analysed using an EfficientNet-B2 network to predict 10-year CVD risk. The primary outcome was time to first major adverse CV event (MACE) including CV death, myocardial infarction or stroke. Results 1241 individuals were included in the test cohort (mean PCE 10-year CVD risk 35%). There was a strong correlation between retinal predicted CVD risk and the PCE risk score (r = 0.66) but not the polygenic risk score (r = 0.05). There were 288 MACE events. Higher retina-predicted risk was significantly associated with increased 10-year risk of MACE (HR 1.05 per 1% increase; 95% CI 1.04–1.06, p < 0.001) and remained so after adjustment for the PCE and polygenic risk score (HR 1.03; 95% CI 1.02–1.04, p < 0.001). The retinal risk score had similar performance to the PCE (both AUC 0.697) and when combined with the PCE and polygenic risk score had significantly improved performance compared to the PCE alone (AUC 0.728). An increase in retinal-predicted risk within 3 years was associated with subsequent increased MACE likelihood. Conclusions A deep-learning AI model could accurately predict MACE from routine retinal screening photographs with a comparable performance to traditional clinical risk assessment in a diabetic cohort. Combining the AI-derived retinal risk prediction with a coronary heart disease polygenic risk score improved risk prediction. AI retinal assessment might allow a one-stop CVD risk assessment at routine retinal screening. Graphical abstract |
| format | Article |
| id | doaj-art-97b14b9e369543ada30d48e5e68cc8c7 |
| institution | Kabale University |
| issn | 1475-2840 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Cardiovascular Diabetology |
| spelling | doaj-art-97b14b9e369543ada30d48e5e68cc8c72025-01-05T12:07:53ZengBMCCardiovascular Diabetology1475-28402025-01-0124111110.1186/s12933-024-02564-wDeep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetesMohammad Ghouse Syed0Emanuele Trucco1Muthu R. K. Mookiah2Chim C. Lang3Rory J. McCrimmon4Colin N. A. Palmer5Ewan R. Pearson6Alex S. F. Doney7Ify R. Mordi8VAMPIRE project, Computing, School of Science and Engineering, University of DundeeVAMPIRE project, Computing, School of Science and Engineering, University of DundeeVAMPIRE project, Computing, School of Science and Engineering, University of DundeeDivision of Cardiovascular Research, School of Medicine, University of DundeeDivision of Systems Medicine, School of Medicine, University of DundeeDivision of Population Health and Genomics, School of Medicine, University of DundeeDivision of Population Health and Genomics, School of Medicine, University of DundeeDivision of Cardiovascular Research, School of Medicine, University of DundeeDivision of Cardiovascular Research, School of Medicine, University of DundeeAbstract Background Prior studies have demonstrated an association between retinal vascular features and cardiovascular disease (CVD), however most studies have only evaluated a few simple parameters at a time. Our aim was to determine whether a deep-learning artificial intelligence (AI) model could be used to predict CVD outcomes from routinely obtained diabetic retinal screening photographs and to compare its performance to a traditional clinical CVD risk score. Methods We included 6127 individuals with type 2 diabetes without myocardial infarction or stroke prior to study entry. The cohort was divided into training (70%), validation (10%) and testing (20%) cohorts. Clinical 10-year CVD risk was calculated using the pooled cohort equation (PCE) risk score. A polygenic risk score (PRS) for coronary heart disease was also obtained. Retinal images were analysed using an EfficientNet-B2 network to predict 10-year CVD risk. The primary outcome was time to first major adverse CV event (MACE) including CV death, myocardial infarction or stroke. Results 1241 individuals were included in the test cohort (mean PCE 10-year CVD risk 35%). There was a strong correlation between retinal predicted CVD risk and the PCE risk score (r = 0.66) but not the polygenic risk score (r = 0.05). There were 288 MACE events. Higher retina-predicted risk was significantly associated with increased 10-year risk of MACE (HR 1.05 per 1% increase; 95% CI 1.04–1.06, p < 0.001) and remained so after adjustment for the PCE and polygenic risk score (HR 1.03; 95% CI 1.02–1.04, p < 0.001). The retinal risk score had similar performance to the PCE (both AUC 0.697) and when combined with the PCE and polygenic risk score had significantly improved performance compared to the PCE alone (AUC 0.728). An increase in retinal-predicted risk within 3 years was associated with subsequent increased MACE likelihood. Conclusions A deep-learning AI model could accurately predict MACE from routine retinal screening photographs with a comparable performance to traditional clinical risk assessment in a diabetic cohort. Combining the AI-derived retinal risk prediction with a coronary heart disease polygenic risk score improved risk prediction. AI retinal assessment might allow a one-stop CVD risk assessment at routine retinal screening. Graphical abstracthttps://doi.org/10.1186/s12933-024-02564-wArtificial intelligenceRetinaCardiovascular riskDiabetes |
| spellingShingle | Mohammad Ghouse Syed Emanuele Trucco Muthu R. K. Mookiah Chim C. Lang Rory J. McCrimmon Colin N. A. Palmer Ewan R. Pearson Alex S. F. Doney Ify R. Mordi Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes Cardiovascular Diabetology Artificial intelligence Retina Cardiovascular risk Diabetes |
| title | Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes |
| title_full | Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes |
| title_fullStr | Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes |
| title_full_unstemmed | Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes |
| title_short | Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes |
| title_sort | deep learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes |
| topic | Artificial intelligence Retina Cardiovascular risk Diabetes |
| url | https://doi.org/10.1186/s12933-024-02564-w |
| work_keys_str_mv | AT mohammadghousesyed deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT emanueletrucco deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT muthurkmookiah deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT chimclang deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT roryjmccrimmon deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT colinnapalmer deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT ewanrpearson deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT alexsfdoney deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes AT ifyrmordi deeplearningpredictionofcardiovascularoutcomesfromroutineretinalimagesinindividualswithtype2diabetes |