Background: Diabetic Retinopathy (DR) is considered a pathology of retinal vascular complications, which stays in the top causes of vision impairment and blindness. Therefore, precisely inspecting its progression enables the ophthalmologists to set up appropriate next-visit schedule and cost-effective treatment plans. In the literature, existing work only makes use of numerical attributes in Electronic Medical Records (EMR) for acquiring such kind of DR-oriented knowledge through conventional machine learning techniques, which require an exhaustive job of engineering most impactful risk factors.

Objective: In this paper, an approach of deep bimodal learning is introduced to leverage the performance of DR risk progression identification.

Methods: In particular, we further involve valuable clinical information of fundus photography in addition to the aforementioned systemic attributes. Accordingly, a Trilogy of Skip-connection Deep Networks, namely Tri-SDN, is proposed to exhaustively exploit underlying relationships between the baseline and follow-up information of the fundus images and EMR-based attributes. Besides that, we adopt Skip-Connection Blocks as basis components of the Tri-SDN for making the end-to-end flow of signals more efficient during feedforward and backpropagation processes.

Results: Through a 10-fold cross validation strategy on a private dataset of 96 diabetic mellitus patients, the proposed method attains superior performance over the conventional EMR-modality learning approach in terms of Accuracy (90.6%), Sensitivity (96.5%), Precision (88.7%), Specificity (82.1%), and Area Under Receiver Operating Characteristics (88.8%).

Conclusions: The experimental results show that the proposed Tri-SDN can combine features of different modalities (i.e., fundus images and EMR-based numerical risk factors) smoothly and effectively during training and testing processes, respectively. As a consequence, with impressive performance of DR risk progression recognition, the proposed approach is able to help the ophthalmologists properly decide follow-up schedule and subsequent treatment plans.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijmedinf.2019.07.005DOI Listing

Publication Analysis

Top Keywords

risk progression
12
bimodal learning
8
trilogy skip-connection
8
skip-connection deep
8
deep networks
8
diabetic retinopathy
8
treatment plans
8
performance risk
8
fundus images
8
images emr-based
8

Similar Publications

Infertility is increasing globally, affecting one in six adults due to factors like delayed childbearing and lifestyle changes. Despite the recognition of the importance of increasing fertility awareness, levels remain low. This study evaluated the perceptions of 'FActs!', a serious game aimed at improving adolescents' fertility awareness.

View Article and Find Full Text PDF

Introduction: Immune-related adverse events (irAEs) induced by immune checkpoint inhibitors are difficult to predict and can lead to severe events. Although it is important to develop strategies for the early detection of severe irAEs, there is a lack of evidence on irAEs associated with ipilimumab plus nivolumab therapy for metastatic renal cell carcinoma (RCC). Therefore, this study aimed to investigate the association between eosinophil and severe irAEs in patients receiving ipilimumab plus nivolumab therapy for RCC.

View Article and Find Full Text PDF

Integrated single-cell and bulk transcriptome analysis of R-loop score-based signature with regard to immune microenvironment, lipid metabolism and prognosis in HCC.

Front Immunol

January 2025

National Key Laboratory of Draggability Evaluation and Systematic Translational Medicine, Tianjin's Clinical Research Center for Cancer, Department of Bone and Soft Tissue Tumors, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin, China.

Background: Hepatocellular carcinoma (HCC) is one of the most prevalent causes of cancer-related morbidity and mortality worldwide. Late-stage detection and the complex molecular mechanisms driving tumor progression contribute significantly to its poor prognosis. Dysregulated R-loops, three-stranded nucleic acid structures associated with genome instability, play a key role in the malignant characteristics of various tumors.

View Article and Find Full Text PDF

Background: Colon adenocarcinoma (COAD) is a malignancy with a high mortality rate and complex biological characteristics and heterogeneity, which poses challenges for clinical treatment. Anoikis is a type of programmed cell death that occurs when cells lose their attachment to the extracellular matrix (ECM), and it plays a crucial role in tumor metastasis. However, the specific biological link between anoikis and COAD, as well as its mechanisms in tumor progression, remains unclear, making it a potential new direction for therapeutic strategy research.

View Article and Find Full Text PDF

Introduction: The envelope proteins syncytin-1 and pHERV-W from the Human Endogenous Retroviral family 'W' (HERV-W) have been identified as potential risk factors in multiple sclerosis (MS). This study aims to evaluate both humoral and cell-mediated immune response to antigenic peptides derived from these proteins across different clinical forms and inflammatory phases of MS.

Methods: Indirect enzyme-linked immunosorbent assay (ELISA) was employed to measure immunoglobulin G (IgG) responses to syncytin-1 and pHERV-W peptides in MS patients.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!