Multimodal deep learning of fundus abnormalities and traditional risk factors for cardiovascular risk prediction.

NPJ Digit Med

Department of Digital Health, Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Sungkyunkwan University, Samsung Medical Center, Seoul, Republic of Korea.

Published: February 2023

Cardiovascular disease (CVD), the leading cause of death globally, is associated with complicated underlying risk factors. We develop an artificial intelligence model to identify CVD using multimodal data, including clinical risk factors and fundus photographs from the Samsung Medical Center (SMC) for development and internal validation and from the UK Biobank for external validation. The multimodal model achieves an area under the receiver operating characteristic curve (AUROC) of 0.781 (95% confidence interval [CI] 0.766-0.798) in the SMC and 0.872 (95% CI 0.857-0.886) in the UK Biobank. We further observe a significant association between the incidence of CVD and the predicted risk from at-risk patients in the UK Biobank (hazard ratio [HR] 6.28, 95% CI 4.72-8.34). We visualize the importance of individual features in photography and traditional risk factors. The results highlight that non-invasive fundus photography can be a possible predictive marker for CVD.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9894867PMC
http://dx.doi.org/10.1038/s41746-023-00748-4DOI Listing

Publication Analysis

Top Keywords

risk factors
16
traditional risk
8
risk
6
multimodal deep
4
deep learning
4
learning fundus
4
fundus abnormalities
4
abnormalities traditional
4
factors
4
factors cardiovascular
4

Similar Publications

Patterns and determinants of serum amylase, lipase concentrations in Indian adolescents and youth with type 1 diabetes.

J Pediatr Endocrinol Metab

December 2024

Department of Growth and Pediatric Endocrinology, Hirabai Cowasji Jehangir Medical Research Institute, Jehangir Hospital, Pune, Maharashtra, India.

Objectives: Exocrine pancreatic insufficiency has been demonstrated in type 1 diabetes (T1D); lower concentrations of pancreatic enzymes have been associated with metabolic risk (MR). Influence of puberty and MR factors on serum concentrations of amylase and lipase remain unexplored in Indian youth with T1D. 1) To characterize and predict determinants of serum amylase and lipase concentrations in adolescents/youth with T1D.

View Article and Find Full Text PDF

Risk factors for postoperative recurrence after full-endoscopic microvascular decompression for trigeminal neuralgia: a retrospective study and predictive nomogram.

Eur J Med Res

December 2024

Department of Neurosurgery, Neuromedicine Center, Beijing Shijitan Hospital, Capital Medical University, No. 10, Tieyi Road, Yangfangdian, Haidian District, Beijing, 100038, People's Republic of China.

Background: Full-endoscopic microvascular decompression (fE-MVD) is an emerging treatment option for trigeminal neuralgia (TN). However, the risk factors associated with postoperative recurrence of TN after fE-MVD procedure remain controversial. The aim of the present study was to summarize the surgical technique of fE-MVD for the treatment of TN and to develop a predictive model for recurrence at 1 year postoperatively based on independent risk factors.

View Article and Find Full Text PDF

Objective: To determine which parameters, including femur morphology, proximal femur bone mineral density, or patient characteristics, are associated with bisphosphonate-related atypical femur fractures (AFFs) and to investigate the relationships between AFF location and these parameters.

Materials And Methods: Sixteen females with a history of bisphosphonate use who presented with AFFs and 38 females without AFFs, even those with long-term bisphosphonate use of > 5 years, were compared. Patient characteristics; physique, gait ability, and history of pain and medication, were recorded.

View Article and Find Full Text PDF

The potential impact of inflammation on the lipid paradox in patients with acute myocardial infarction: a multicenter study.

BMC Med

December 2024

National Clinical Research Center for Cardiovascular Diseases, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 167, Beilishi Rd, Beijing, 100037, Xicheng District, China.

Background: Low-density lipoprotein cholesterol (LDL-C) is a well-recognized risk factor for cardiovascular diseases. However, several clinical studies demonstrated an inverse association between LDL-C and mortality risk in patients with acute myocardial infarction (AMI), known as the lipid paradox. This study aims to investigate the potential impact of inflammation on the association between LDL-C levels and mortality risks.

View Article and Find Full Text PDF

Introduction: Chronic alcohol consumption and tobacco usage are major risk factors for esophageal squamous cell carcinoma (ESCC). Excessive tobacco and alcohol consumption lead to oxidative stress and the generation of reactive carbonyl species (RCS) which induce DNA damage and cell apoptosis. This phenomenon contributes to cell damage and carcinogenesis in various organs including ESCC.

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!