{"id":1087,"date":"2025-07-20T00:09:29","date_gmt":"2025-07-20T00:09:29","guid":{"rendered":"https:\/\/mediwhale.stage.studio-jt.co.kr\/kr\/?post_type=publication&#038;p=1087"},"modified":"2025-07-20T00:09:29","modified_gmt":"2025-07-20T00:09:29","slug":"diabetes-prediction-without-blood-tests-the-role-of-retinal-imaging-and-artificial-intelligence","status":"publish","type":"publication","link":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/publication\/diabetes-prediction-without-blood-tests-the-role-of-retinal-imaging-and-artificial-intelligence\/","title":{"rendered":"Diabetes Prediction without Blood Tests\u2014The Role of Retinal Imaging and Artificial Intelligence"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\"><strong>Introduction and Objective:<\/strong>\u00a0<\/h4>\n\n\n\n<p>This study evaluates a non-invasive method for diabetes prediction using retinal imaging features\u2014Reti-DR (probability of diabetic retinopathy) and Reti-HbA1c (probability of HbA1c > 6.5)\u2014alongside demographic and clinical data. The objective was to determine the predictive accuracy of this approach without blood-based tests.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Methods:<\/strong>\u00a0<\/h4>\n\n\n\n<p>Cross-sectional data from 1,191 CMERC-HI participants (732 non-diabetic, 459 diabetic), a cohort at high risk of cardiovascular events, were analyzed. Independent variables included Reti-DR, Reti-HbA1c, age, gender, and BMI. Scores were averaged across fundus images. Reti-DR and Reti-HbA1c models were pre-trained on ~0.2M and 325,177 fundus images, respectively, from a health screening dataset. Data were split into training (80%, n=952) and testing (20%, n=239) sets. Features were standardized, and logistic regression was evaluated using AUC and positive predictive value (PPV)\/sensitivity at the optimal threshold.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Results:<\/strong>\u00a0<\/h4>\n\n\n\n<p>The model achieved an AUC of 0.81. At an optimal threshold of 0.33, PPV was 0.58, and sensitivity was 0.80. Odds ratios showed Reti-HbA1c (2.24) and Reti-DR (1.75) as the strongest predictors.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Conclusion:<\/strong>\u00a0<\/h4>\n\n\n\n<p>This study demonstrates a feasible, non-invasive method for detecting diabetes, including in individuals on medications. Integrating Reti-DR and Reti-HbA1c into models offers an alternative to blood tests.<\/p>\n","protected":false},"template":"","publication_type_categories":[12],"publication_categories":[21],"class_list":["post-1087","publication","type-publication","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/publication\/1087","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/types\/publication"}],"version-history":[{"count":1,"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/publication\/1087\/revisions"}],"predecessor-version":[{"id":1088,"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/publication\/1087\/revisions\/1088"}],"wp:attachment":[{"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/media?parent=1087"}],"wp:term":[{"taxonomy":"publication_type_categories","embeddable":true,"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/publication_type_categories?post=1087"},{"taxonomy":"publication_categories","embeddable":true,"href":"https:\/\/mediwhale.stage.studio-jt.co.kr\/ko\/wp-json\/wp\/v2\/publication_categories?post=1087"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}