A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging

Stroke is a leading cause of death and disability in developed countries. We validated an AI-based prediction model for incident stroke using sensors such as fundus cameras and ophthalmoscopes for retinal images, along with socio-demographic data and traditional risk factors. The model was trained o...

Full description

Saved in:
Bibliographic Details
Main Authors: Arun Govindaiah, Tasin Bhuiyan, R. Theodore Smith, Mandip S. Dhamoon, Alauddin Bhuiyan
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/6/1917
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849340339671793664
author Arun Govindaiah
Tasin Bhuiyan
R. Theodore Smith
Mandip S. Dhamoon
Alauddin Bhuiyan
author_facet Arun Govindaiah
Tasin Bhuiyan
R. Theodore Smith
Mandip S. Dhamoon
Alauddin Bhuiyan
author_sort Arun Govindaiah
collection DOAJ
description Stroke is a leading cause of death and disability in developed countries. We validated an AI-based prediction model for incident stroke using sensors such as fundus cameras and ophthalmoscopes for retinal images, along with socio-demographic data and traditional risk factors. The model was trained on a proprietary dataset of over 6500 participants, including 171 with 5-year incident strokes and 242 with 10-year incident strokes. The model provides separate 5-year and 10-year risk scores. The model was externally validated on the UK Biobank dataset (3000 subjects with 5-year incident strokes). Using retinal imaging, our models identified individuals with 5-year incident strokes with 80% sensitivity, 82% specificity, and an AUC of 0.83, and predicted 10-year incidents with 72% sensitivity, 78% specificity, and an AUC of 0.79. In comparison, for the 10-year model, the AUC for the Framingham score was 0.73, and the CHADS2 score was 0.74. On the Biobank external dataset, our 5-year model (without retinal features) demonstrated moderate but lower sensitivity (69.3%) and specificity (66.4%) compared to its performance on the proprietary dataset (with retinal features). Using a multi-ethnic dataset, we developed and validated a prediction model that improves stroke risk identification for 5-year and 10-year incidences by incorporating retinal features.
format Article
id doaj-art-573cf3b49bdb4a0181eb36a7ddfb3237
institution Kabale University
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-573cf3b49bdb4a0181eb36a7ddfb32372025-08-20T03:43:56ZengMDPI AGSensors1424-82202025-03-01256191710.3390/s25061917A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal ImagingArun Govindaiah0Tasin Bhuiyan1R. Theodore Smith2Mandip S. Dhamoon3Alauddin Bhuiyan4iHealthScreen Inc., Richmond Hill, NY 11418, USAiHealthScreen Inc., Richmond Hill, NY 11418, USABiomolecular Retinal Imaging, Department of Ophthalmology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USADepartment of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USAiHealthScreen Inc., Richmond Hill, NY 11418, USAStroke is a leading cause of death and disability in developed countries. We validated an AI-based prediction model for incident stroke using sensors such as fundus cameras and ophthalmoscopes for retinal images, along with socio-demographic data and traditional risk factors. The model was trained on a proprietary dataset of over 6500 participants, including 171 with 5-year incident strokes and 242 with 10-year incident strokes. The model provides separate 5-year and 10-year risk scores. The model was externally validated on the UK Biobank dataset (3000 subjects with 5-year incident strokes). Using retinal imaging, our models identified individuals with 5-year incident strokes with 80% sensitivity, 82% specificity, and an AUC of 0.83, and predicted 10-year incidents with 72% sensitivity, 78% specificity, and an AUC of 0.79. In comparison, for the 10-year model, the AUC for the Framingham score was 0.73, and the CHADS2 score was 0.74. On the Biobank external dataset, our 5-year model (without retinal features) demonstrated moderate but lower sensitivity (69.3%) and specificity (66.4%) compared to its performance on the proprietary dataset (with retinal features). Using a multi-ethnic dataset, we developed and validated a prediction model that improves stroke risk identification for 5-year and 10-year incidences by incorporating retinal features.https://www.mdpi.com/1424-8220/25/6/1917strokerisk scoremachine learningAI in medicine
spellingShingle Arun Govindaiah
Tasin Bhuiyan
R. Theodore Smith
Mandip S. Dhamoon
Alauddin Bhuiyan
A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging
Sensors
stroke
risk score
machine learning
AI in medicine
title A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging
title_full A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging
title_fullStr A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging
title_full_unstemmed A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging
title_short A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging
title_sort machine learning prediction model to identify individuals at risk of 5 year incident stroke based on retinal imaging
topic stroke
risk score
machine learning
AI in medicine
url https://www.mdpi.com/1424-8220/25/6/1917
work_keys_str_mv AT arungovindaiah amachinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT tasinbhuiyan amachinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT rtheodoresmith amachinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT mandipsdhamoon amachinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT alauddinbhuiyan amachinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT arungovindaiah machinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT tasinbhuiyan machinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT rtheodoresmith machinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT mandipsdhamoon machinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging
AT alauddinbhuiyan machinelearningpredictionmodeltoidentifyindividualsatriskof5yearincidentstrokebasedonretinalimaging