Diabetic retinopathy risk prediction for fundus examination using sparse learning

A cross-sectional study

Ein Oh, Tae Keun Yoo, Euncheol Park

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Background: Blindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients. Methods. Health records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR. Results: Considering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation. Conclusion: The sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

Original languageEnglish
Article number106
JournalBMC Medical Informatics and Decision Making
Volume13
Issue number1
DOIs
Publication statusPublished - 2013 Sep 17

Fingerprint

Diabetic Retinopathy
Cross-Sectional Studies
Learning
Nutrition Surveys
Korea
Area Under Curve
Electronic Health Records
Health
Blindness
ROC Curve

All Science Journal Classification (ASJC) codes

  • Health Policy
  • Health Informatics

Cite this

@article{6dbe5a9720284b72a5f5e7f686f34dea,
title = "Diabetic retinopathy risk prediction for fundus examination using sparse learning: A cross-sectional study",
abstract = "Background: Blindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients. Methods. Health records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR. Results: Considering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6{\%} in the internal validation, and an AUC of 0.82 and an accuracy of 75.2{\%} in the external validation. Conclusion: The sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.",
author = "Ein Oh and Yoo, {Tae Keun} and Euncheol Park",
year = "2013",
month = "9",
day = "17",
doi = "10.1186/1472-6947-13-106",
language = "English",
volume = "13",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "BioMed Central",
number = "1",

}

Diabetic retinopathy risk prediction for fundus examination using sparse learning : A cross-sectional study. / Oh, Ein; Yoo, Tae Keun; Park, Euncheol.

In: BMC Medical Informatics and Decision Making, Vol. 13, No. 1, 106, 17.09.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Diabetic retinopathy risk prediction for fundus examination using sparse learning

T2 - A cross-sectional study

AU - Oh, Ein

AU - Yoo, Tae Keun

AU - Park, Euncheol

PY - 2013/9/17

Y1 - 2013/9/17

N2 - Background: Blindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients. Methods. Health records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR. Results: Considering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation. Conclusion: The sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

AB - Background: Blindness due to diabetic retinopathy (DR) is the major disability in diabetic patients. Although early management has shown to prevent vision loss, diabetic patients have a low rate of routine ophthalmologic examination. Hence, we developed and validated sparse learning models with the aim of identifying the risk of DR in diabetic patients. Methods. Health records from the Korea National Health and Nutrition Examination Surveys (KNHANES) V-1 were used. The prediction models for DR were constructed using data from 327 diabetic patients, and were validated internally on 163 patients in the KNHANES V-1. External validation was performed using 562 diabetic patients in the KNHANES V-2. The learning models, including ridge, elastic net, and LASSO, were compared to the traditional indicators of DR. Results: Considering the Bayesian information criterion, LASSO predicted DR most efficiently. In the internal and external validation, LASSO was significantly superior to the traditional indicators by calculating the area under the curve (AUC) of the receiver operating characteristic. LASSO showed an AUC of 0.81 and an accuracy of 73.6% in the internal validation, and an AUC of 0.82 and an accuracy of 75.2% in the external validation. Conclusion: The sparse learning model using LASSO was effective in analyzing the epidemiological underlying patterns of DR. This is the first study to develop a machine learning model to predict DR risk using health records. LASSO can be an excellent choice when both discriminative power and variable selection are important in the analysis of high-dimensional electronic health records.

UR - http://www.scopus.com/inward/record.url?scp=84883719704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883719704&partnerID=8YFLogxK

U2 - 10.1186/1472-6947-13-106

DO - 10.1186/1472-6947-13-106

M3 - Article

VL - 13

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

SN - 1472-6947

IS - 1

M1 - 106

ER -