Prediction of Diabetic Retinopathy Using Longitudinal Electronic Health Records

Chen, Suhao; Wang, Zekai; Yao, Bing; Liu, Tieming

doi:10.1109/case49997.2022.9926605

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few decades, deep learning or deep neural network (DNN) has emerged as a powerful tool for pattern recognition that can learn the abstracted features from complex data and yield state-of-the-art predictions ( Mousavi et al, 2019 ; Xie and Yao, 2022a ; Xie and Yao, 2022b ; Chen et al, 2022 ; Wang et al, 2022 ). As opposed to traditional machine learning, deep learning presents strong robustness and fault tolerance to uncertain factors, which makes it suitable for beat and rhythm classification from ECGs ( Tutuko et al, 2021 ).…”

Section: Research Backgroundmentioning

confidence: 99%

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet

Xie,

Stavrakis,

Yao

2024

Front. Physiol.

Self Cite

View full text Add to dashboard Cite

Introduction: Atrial fibrillation (AF) is the most common cardiac arrhythmia, which is clinically identified with irregular and rapid heartbeat rhythm. AF puts a patient at risk of forming blood clots, which can eventually lead to heart failure, stroke, or even sudden death. Electrocardiography (ECG), which involves acquiring bioelectrical signals from the body surface to reflect heart activity, is a standard procedure for detecting AF. However, the occurrence of AF is often intermittent, costing a significant amount of time and effort from medical doctors to identify AF episodes. Moreover, human error is inevitable, as even experienced medical professionals can overlook or misinterpret subtle signs of AF. As such, it is of critical importance to develop an advanced analytical model that can automatically interpret ECG signals and provide decision support for AF diagnostics.Methods: In this paper, we propose an innovative deep-learning method for automated AF identification using single-lead ECGs. We first extract time-frequency features from ECG signals using continuous wavelet transform (CWT). Second, the convolutional neural networks enhanced with residual learning (ReNet) are employed as the functional approximator to interpret the time-frequency features extracted by CWT. Third, we propose to incorporate a multi-branching structure into the ResNet to address the issue of class imbalance, where normal ECGs significantly outnumber instances of AF in ECG datasets.Results and Discussion: We evaluate the proposed Multi-branching Resnet with CWT (CWT-MB-Resnet) with two ECG datasets, i.e., PhysioNet/CinC challenge 2017 and ECGs obtained from the University of Oklahoma Health Sciences Center (OUHSC). The proposed CWT-MB-Resnet demonstrates robust prediction performance, achieving an F1 score of 0.8865 for the PhysioNet dataset and 0.7369 for the OUHSC dataset. The experimental results signify the model’s superior capability in balancing precision and recall, which is a desired attribute for ensuring reliable medical diagnoses.

show abstract

Section: Research Backgroundmentioning

confidence: 99%

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet

Xie,

Stavrakis,

Yao

2024

Front. Physiol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, many of the methods, e.g., decision trees-based models and gradient boosting-based models lack the ability to model the dynamical trajectory of the DR disease. Our prior work [3] has shown that the longitudinal information of the disease dynamics is conducive for data-driven disease prediction. Note that Cox proportional hazard models generally assume there is a linear relationship between the medical variables and proportional hazard [34].…”

Section: Research Background and Literature Reviewmentioning

confidence: 99%

“…The dataset we use in this study is obtained from the 2018 Cerner Health Facts ® data warehouse, one of the largest Health Insurance Portability and Accountability Act (HIPAA)-compliant databases in the U.S. storing de-identified clinical data of more than 63 million patients [3]. This database contains comprehensive clinical information including patient demographics, hospital visits, diagnoses, procedures, medication prescriptions, vital signs, lab tests, etc., providing an unprecedented opportunity for data-driven diagnosis of DR.…”

Section: A Data Source and Data Extractionmentioning

confidence: 99%

“…Unfortunately, many diabetic patients are unaware of their potential risk of DR because DR is asymptomatic at the early stage. Thus, they missed the most effective time window to halt the progression of DR, because vision loss or blindness is inevitable [3]. Additionally, although ADA suggests ophthalmic examinations in the annual DR screening guidelines, the compliance rates are below expectation, which results in 19% of DR patients being undiagnosed [1], [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Branching Temporal Convolutional Network With Tensor Data Completion for Diabetic Retinopathy Prediction

Wang,

Chen,

Liu

et al. 2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Diabetic retinopathy (DR), caused by damage to the blood vessels in the tissue of the retina, is a microvascular complication of diabetes. DR is the leading cause of vision loss among working-aged adults. However, due to the low compliance rate of DR screening and expensive medical devices for ophthalmic exams, many DR patients did not seek proper medical attention until DR develops to irreversible stages (i.e., vision loss). Fortunately, the widely available electronic health record (EHR) databases provide an unprecedented opportunity to develop cost-effective machine-learning tools for DR detection. This paper proposes a Multi-branching Temporal Convolutional Network with Tensor Data Completion (MB-TCN-TC) model to analyze the longitudinal EHRs collected from diabetic patients for DR prediction. Experimental results demonstrate that the proposed MB-TCN-TC model not only effectively copes with the imbalanced data and missing value issues commonly seen in EHR datasets but also captures the temporal correlation and complicated interactions among medical variables in the longitudinal clinical records, yielding superior prediction performance compared to existing methods.

show abstract

Hierarchical active learning for defect localization in 3D systems

Xie

Yao

2023

IISE Transactions on Healthcare Systems Engineering

View full text Add to dashboard Cite

Prediction of Diabetic Retinopathy Using Longitudinal Electronic Health Records

Cited by 5 publications

References 0 publications

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet

Multi-Branching Temporal Convolutional Network With Tensor Data Completion for Diabetic Retinopathy Prediction

Hierarchical active learning for defect localization in 3D systems

Contact Info

Product

Resources

About