ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data

Bhagawati, Mrinalini; Paul, Sudip; Mantella, Laura; Johri, Amer M.; Gupta, Siddharth; Laird, John R.; Singh, Inder M.; Khanna, Narendra N.; Al-Maini, Mustafa; Isenovic, Esma R.; Tiwari, Ekta; Singh, Rajesh; Nicolaides, Andrew; Saba, Luca; Anand, Vinod; Suri, Jasjit S.*
Diagnostics2024-9DOI: 10.3390/diagnostics14171894
1被引2阅读
引用收藏
分享

摘要

Background: The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge (TM) 3.0(HDL) (AtheroPoint (TM), Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms. Methodology: 500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge (TM) 3.0(HDL) was scientifically validated using seen and unseen datasets while the reliability and statistical tests were conducted using CST along with p-value significance. The performance of AtheroEdge (TM) 3.0(HDL) was evaluated by measuring the p-value and area-under-the-curve for both seen and unseen data. Results: The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the seen datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge (TM) 3.0(HDL) showed less than 1% (p-value < 0.001) difference between seen and unseen data, complying with regulatory standards. Conclusions: The hypothesis for AtheroEdge (TM) 3.0(HDL) was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.<br />

学科与关键词

关键词
cardiovascular disease riskmachine learning feature extractionhybrid deep learningscientific validationperformance evaluationreliabilityand stability
相关
加载中…
  • Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort
    Bhagawati, Mrinalini; Paul, Sudip; Mantella, Laura; Johri, Amer M.; Laird, John R.; Singh, Inder M.; Singh, Rajesh; Garg, Deepak; Fouda, Mostafa M.; Khanna, Narendra N.; Cau, Riccardo; Abraham, Ajith; Al-Maini, Mostafa; Isenovic, Esma R.; Sharma, Aditya M.; Fernandes, Jose Fernandes E.; Chaturvedi, Seemant; Karla, Mannudeep K.; Nicolaides, Andrew; Saba, Luca; Suri, Jasjit S.*International Journal of Cardiovascular Imaging, 2024, 40(6): 1283-1303.被引 1
  • Cardiovascular disease/stroke risk stratification in deep learning framework: a review
    Bhagawati, Mrinalini; Paul, Sudip; Agarwal, Sushant; Protogeron, Athanasios; Sfikakis, Petros P.; Kitas, George D.; Khanna, Narendra N.; Ruzsa, Zoltan; Sharma, Aditya M.; Tomazu, Omerzu; Turk, Monika; Faa, Gavino; Tsoulfas, George; Laird, John R.; Rathore, Vijay; Johri, Amer M.; Viskovic, Klaudija; Kalra, Manudeep; Balestrieri, Antonella; Nicolaides, Andrew; Singh, Inder M.; Chaturvedi, Seemant; Paraskevas, Kosmas I.; Fouda, Mostafa M.; Saba, Luca; Suri, Jasjit S.*Cardiovascular Diagnosis and Therapy, 2023, 13(3).被引 7
  • Cardiovascular/Stroke Risk Assessment in Patients with Erectile Dysfunction-A Role of Carotid Wall Arterial Imaging and Plaque Tissue Characterization Using Artificial Intelligence Paradigm: A Narrative Review
    Khanna, Narendra N.; Maindarkar, Mahesh; Saxena, Ajit; Ahluwalia, Puneet; Paul, Sudip; Srivastava, Saurabh K.; Cuadrado-Godia, Elisa; Sharma, Aditya; Omerzu, Tomaz; Saba, Luca; Mavrogeni, Sophie; Turk, Monika; Laird, John R.; Kitas, George D.; Fatemi, Mostafa; Barqawi, Al Baha; Miner, Martin; Singh, Inder M.; Johri, Amer; Kalra, Mannudeep M.; Agarwal, Vikas; Paraskevas, Kosmas, I; Teji, Jagjit S.; Fouda, Mostafa M.; Pareek, Gyan; Suri, Jasjit S.*Diagnostics, 2022, 12(5): 1249.被引 12
查看全部 →

发表信息

论文状态
公开发表
期刊
Diagnostics
发表日期
2024-09
卷期
第 14 卷, 第 17 期
页码
1894
DOI
10.3390/diagnostics14171894
成果收录
SCIE

作者

  • B

    Bhagawati, Mrinalini (第一作者)

  • P

    Paul, Sudip

查看全部 16 位作者收起作者
  • M

    Mantella, Laura

  • J

    Johri, Amer M.

  • G

    Gupta, Siddharth

  • L

    Laird, John R.

  • S

    Singh, Inder M.

  • K

    Khanna, Narendra N.

  • A

    Al-Maini, Mustafa

  • I

    Isenovic, Esma R.

  • T

    Tiwari, Ekta

  • S

    Singh, Rajesh

  • N

    Nicolaides, Andrew

  • S

    Saba, Luca

  • A

    Anand, Vinod

  • S

    Suri, Jasjit S. (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417