Prediction of Diabetic Retinopathy Among Type Ii Diabetic Patients Using Data Mining Techniques

Khairudin, Zuraida; Razak, Nurfatin Adila Abdul; Rahman, Hezlin Aryani Abd; Kamaruddin, Norbaizura; Aziz, Nor Azimah Abd

doi:10.24191/mjoc.v5i2.10554

Cited by 6 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different diagnostic criteria make it challenging to ascertain the true prevalence of diabetes, however various studies exhibited the incidence between 5 and 7 percent in Pakistan 13 . Similar to this, it has been projected that 12% of diabetes individuals in Pakistan may develop diabetic retinopathy (DR), however other sources have stated incidences as high as 15% to 19.9% [14][15] . One of the main contributing factors to blindness is DR among diabetic patients [16][17] .…”

Section: Discussionmentioning

confidence: 84%

Incidence of Retinopathy in Newly Diagnosed Patients with Type-II Diabetes Mellitus

Bhatti¹,

Ahmad²,

Khan³

et al. 2023

PJMHS

View full text Add to dashboard Cite

Aim: To determine the incidence of retinopathy in patients newly diagnosed with type-II diabetes mellitus. Place and Duration: Alshifa Trust Eye Hospital, Rawalpindi and Ophthalmology Department, CMH, Lahore for six-months duration from January 2022 to June 2022. Methods: The study included 200 individuals with type 2 diabetes mellitus diagnosed within the previous two months and selected with non-probability consecutive sampling technique. Diabetes was diagnosed on the basis of two consecutive values of random blood glucose (RBS), fasting blood glucose (FBS) and glycosylated hemoglobin (HBA1c)> 200 mg / dL according to the following criteria defined by the World Organization (WHO) which was revised in 1999 and 2006. All patients underwent detailed examination of the retina for diabetic retinopathy evaluation using biomicroscopic slit lamp and +90 Diopter lens. SPSS-21.0 was used for the data analysis. For each variable, descriptive statistics were calculated. Results: 200 patients in total were enrolled in this study. The participants ranged in age from 31 to 60 years, with the majority were in the 4th decade (mean age: 51.50 ± 9.02). 30 individuals (15%) with newly diagnosed type 2 diabetes had diabetic retinopathy. From 30 patients of newly diagnosed type 2 diabetes mellitus; the background retinopathy was seen in 18 (60%) of patients, pre proliferative retinopathy was observed in 8 (26.7%) of patients and proliferative retinopathy was seen in 3 (13.3%). Patients with diabetic retinopathy had a HbA1C (%) of 9.8± 1.2, while those without the diabetic retinopathy had HbA1c of 7.1 ± 2.2. Conclusions: We found that the incidence of retinopathy in patients with newly diagnosed type 2 diabetes is 15%, which underlines the value of a comprehensive ophthalmological assessment of all diabetic patients at diagnosis. Keywords: Retinopathy, Type-II diabetes mellitus and incidence.

show abstract

Section: Discussionmentioning

confidence: 84%

Incidence of Retinopathy in Newly Diagnosed Patients with Type-II Diabetes Mellitus

Bhatti¹,

Ahmad²,

Khan³

et al. 2023

PJMHS

View full text Add to dashboard Cite

show abstract

“…4 In addition, this study uses clinical audit datasets, where the samples were randomly selected from all T2D patients receiving treatment in public health clinics based on a predefined protocol. 3 Compared to other previous studies done in Malaysia, which used samples randomly selected from a clinic, 7 or following a cohort of patients from two tertiary hospitals, 8 our study utilises a method that can better represent T2D patients in Malaysian population.…”

Section: Discussionmentioning

confidence: 99%

“…6 However, there is a lack of studies on developing prediction models for diabetes complications in Malaysia, with previous studies using only a small sample size, limiting generalizability. 7,8 Therefore, this study aims to use ML techniques to develop predictive models for T2D complications using data acquired from the MNDR. By leveraging the ML technique and the large dataset, this study may overcome the limitations of non-ML models in capturing the complexity of the data, and small sample sizes encountered in previous studies, especially in Malaysia.…”

Section: Introductionmentioning

confidence: 99%

Machine learning based predictive model of Type 2 diabetes complications using Malaysian National Diabetes Registry: A study protocol

Abas,

Li,

Hairi

et al. 2024

Journal of Public Health Research

View full text Add to dashboard Cite

Background: The prevalence of diabetes in Malaysia is increasing, and identifying patients with higher risk of complications is crucial for effective management. The use of machine learning (ML) to develop prediction models has been shown to outperform non-ML models. This study aims to develop predictive models for Type 2 Diabetes (T2D) complications in Malaysia using ML techniques. Design and methods: This 10-year retrospective cohort study uses clinical audit datasets from Malaysian National Diabetes Registry from 2011 to 2021. T2D patients who received treatment in public health clinics in the southern region of Malaysia with at least two data points in 10 years are included. Patients with diabetes complications at baseline are excluded to ensure temporality between predictors and the target variable. Appropriate methods are used to address issues related to data cleaning, missing data imputation, data splitting, feature selection, and class imbalance. The study uses 7 ML algorithms, including logistic regression, support vector machine, k-nearest neighbours, decision tree, random forest, extreme gradient boosting, and light gradient boosting machine, to develop predictive models for four target variables: nephropathy, retinopathy, ischaemic heart disease, and stroke. Hyperparameter tuning is performed for each algorithm. The model training is performed using a stratified k-fold cross-validation technique. The best model for each algorithm is evaluated on a hold-out dataset using multiple metrics. Expected impact of the study on public health: The prediction model may be a valuable tool for diabetes management and secondary prevention by enabling earlier interventions and optimal resource allocation, leading to better health outcomes.

show abstract

“…The LR, Decision Tree, and ANN data mining models were chosen for this investigation. The ophthalmology Treatment center, UiTM Medical Specialist Centre, selected 361 Type II diabetic patients between January 2014 and December 2018, and the dataset contains 17 variables (Khairudin et al, 2020). There are two steps to classification:…”

Section: Role Of Data Miningmentioning

confidence: 99%

Prediction of Diabetic Retinopathy Using Health Records With Machine Learning Classifiers and Data Science

Sumathy¹,

Chakrabarty

Gupta

et al. 2022

International Journal of Reliable and Quality E-Healthcare

View full text Add to dashboard Cite

Diabetes is a rapidly spreading disease. When the pancreas produces insufficient insulin or the body cannot utilise it effectively. Diabetic Retinopathy (DR) and blindness are two major issues for diabetics. Diabetes patients increase the amount of data collected about DR. To extract important information and undiscovered knowledge from data, data mining techniques are required. DM is necessary in DR to improve society's health. Our study focuses on the early detection of Diabetic Retinopathy using patient information. DM approaches are used to extract information from these numeric records. The dataset was used to forecast DR using logistic regression, KNN, SVM, bagged tree, and boosted tree classifiers. Two cross-validations are used to find the best features and avoid overfitting. Our dataset includes 900 diabetes patients. The boosted tree produced the best classification accuracy (90.1%) with 10% hold-out validation. KNN also achieved 88.9% accuracy, which is impressive. As a result, our research suggests that bagged trees and KNN are good classifiers for DR.

show abstract

Prediction of Diabetic Retinopathy Among Type Ii Diabetic Patients Using Data Mining Techniques

Cited by 6 publications

References 26 publications

Incidence of Retinopathy in Newly Diagnosed Patients with Type-II Diabetes Mellitus

Incidence of Retinopathy in Newly Diagnosed Patients with Type-II Diabetes Mellitus

Machine learning based predictive model of Type 2 diabetes complications using Malaysian National Diabetes Registry: A study protocol

Prediction of Diabetic Retinopathy Using Health Records With Machine Learning Classifiers and Data Science

Contact Info

Product

Resources

About