AUTOMATED CARDIAC DISEASE PREDICTION AND SEVERITY DETECTION USING IMAGE SEGMENTATION AND DEEP LEARNING DOI

Bhawna Verma,

Anupama Anupama, G. Gaurav

et al.

International Journal of Research -GRANTHAALAYAH, Journal Year: 2024, Volume and Issue: 12(8)

Published: Aug. 31, 2024

Cardiovascular disease remains a leading cause of mortality worldwide, necessitating accurate and early diagnosis. Cardiac imaging, combined with advanced computational techniques, plays vital role in identifying assessing heart conditions. This project explores the application deep learning—particularly Convolutional Neural Networks (CNNs)—in analyzing multimodal cardiac images to improve diagnostic accuracy efficiency. The proposed system focuses on disease-specific regions CT by employing CNN-based image representation segmentation. A K-Nearest Neighbor (KNN) classifier is used segment into three based color, isolating both affected unaffected areas. By calculating percentage pixels, model estimates severity disease, enabling more informed timely treatment decisions. approach demonstrates potential AI-driven tools enhance noninvasive diagnostics cardiology while minimizing procedural risks costs.

Language: Английский

ENNigma: A framework for Private Neural Networks DOI Creative Commons
Pedro Barbosa, Ivone Amorim, Eva Maia

et al.

Future Generation Computer Systems, Journal Year: 2025, Volume and Issue: unknown, P. 107719 - 107719

Published: Jan. 1, 2025

Language: Английский

Citations

0
Exploration and comparison of the effectiveness of swarm intelligence algorithm in early identification of cardiovascular disease DOI Creative Commons

Tiantian Bai,

Mengru Xu,

Taotao Zhang

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 7, 2025

Due to the aging of global population and lifestyle changes, cardiovascular disease has become leading cause death worldwide, causing serious public health problems economic pressures. Early accurate prediction is crucial reducing morbidity mortality, but traditional methods often lack robustness. This study focuses on integrating swarm intelligence feature selection algorithms (including whale optimization algorithm, cuckoo search flower pollination Harris hawk particle genetic algorithm) with machine learning technology improve early diagnosis disease. systematically evaluated performance each algorithm under different sizes, specifically by comparing their average running time objective function values identify optimal subset. Subsequently, selected subsets were integrated into ten classification models, a comprehensive weighted evaluation was performed based accuracy, precision, recall, F1 score, AUC value model determine configuration. The results showed that random forest, extreme gradient boosting, adaptive boosting k-nearest neighbor models best combined dataset (weighted score 1), where set consisted 9 key features when size 25; while Framingham dataset, 0.92), its derived from 10 50. this show can effectively screen informative sets, significantly provide strong support for diseases.

Language: Английский

Citations

0
HealthEdgeAI: GAI and XAI Based Healthcare System for Sustainable Edge AI and Cloud Computing Environments DOI

Han Wang,

Balaji Muthurathinam Panneer Chelvan,

Muhammed Golec

et al.

Concurrency and Computation Practice and Experience, Journal Year: 2025, Volume and Issue: 37(9-11)

Published: April 10, 2025

ABSTRACT Coronary heart disease is a leading cause of mortality worldwide. Although no cure exists for this condition, appropriate treatment and timely intervention can effectively manage its symptoms reduce the risk complications such as attacks. Prior studies have mostly relied on limited dataset from UC Irvine Machine Learning Repository, predominantly focusing (ML) models without incorporating Explainable Artificial Intelligence (XAI) or Generative (GAI) techniques enhancement. While some research has explored cloud‐based deployments, implementation edge AI in domain remains largely under‐explored. Therefore, paper proposes HealthEdgeAI , sustainable approach to prediction that enhances XAI through GAI‐driven data augmentation. In our research, we assessed multiple by evaluating accuracy, precision, recall, F1‐score, area under curve (AUC). We also developed web application using Streamlit demonstrate methods employed FastAPI serve optimal model an API. Additionally, examined performance these cloud computing settings comparing key Quality Service (QoS) parameters, average response rate throughput. To highlight potential computing, tested devices with both low‐ high‐end configurations illustrate differences QoS. Ultimately, study identifies current limitations outlines prospective directions future AI‐based environments.

Language: Английский

Citations

0
Identification and diagnosis of chronic heart disease: A deep learning-based hybrid approach DOI
Hazrat Bilal, Yar Muhammad, Inam Ullah

et al.

Alexandria Engineering Journal, Journal Year: 2025, Volume and Issue: 124, P. 470 - 483

Published: April 11, 2025

Language: Английский

Citations

0
Optimized convolutional neural network using grasshopper optimization technique for enhanced heart disease prediction DOI Creative Commons
Sanjeeva Polepaka, R. P. Ram Kumar,

Deepthi Palakurthy

et al.

Cogent Engineering, Journal Year: 2024, Volume and Issue: 11(1)

Published: Nov. 8, 2024

According to the World Health Organization (WHO), heart disease (HD) is a preeminent worldwide cause of mortality. Early prediction and diagnosis HDs becomes very crucial save human kind. This study presents novel approach by integrating machine learning (ML) technique, explicitly, convolutional neural network (CNN) model with grasshopper optimization (GHO) algorithm optimize performance conventional CNN, thereby, efficiency accuracy proposed HD (HDP) enhanced. While evaluating on Cleveland Dataset, hybridized optimized CNN using GHO demonstrated superior metrics, namely, classification 88.52%, precision 87.87%, recall 90.62% F1-score 89.23%. The results emphasize model's potential robustness for early diagnosis, contributing significant improvements than ML methods. Further, strengthens growing body artificial intelligence (AI)-driven healthcare solutions highlights significance hybrid models in domain.

Language: Английский

Citations

2
An Integrated Stacked Convolutional Neural Network and the Levy Flight-based Grasshopper Optimization Algorithm for Predicting Heart Disease DOI Creative Commons

Syed Muhammad Salman Bukhari,

Muhammad Hamza Zafar, Syed Kumayl Raza Moosavi

et al.

Healthcare Analytics, Journal Year: 2024, Volume and Issue: unknown, P. 100374 - 100374

Published: Dec. 1, 2024

Language: Английский

Citations

1
Mitigating Algorithmic Bias in AI-Driven Cardiovascular Imaging for Fairer Diagnostics DOI Creative Commons
Md Abu Sufian, Lujain Alsadder,

Wahiba Hamzi

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2675 - 2675

Published: Nov. 27, 2024

: The research addresses algorithmic bias in deep learning models for cardiovascular risk prediction, focusing on fairness across demographic and socioeconomic groups to mitigate health disparities. It integrates fairness-aware algorithms, susceptible carrier-infected-recovered (SCIR) models, interpretability frameworks combine with actionable AI insights supported by robust segmentation classification metrics.

Language: Английский

Citations

0
DEVELOPMENT OF AN AUTOMATED HOSPITAL MANAGEMENT SYSTEM FOR ENHANCED PATIENT CARE AND OPERATIONAL EFFICIENCY DOI

Bittu,

Megha Megha,

Anil Gangwar

et al.

International Journal of Research -GRANTHAALAYAH, Journal Year: 2024, Volume and Issue: 12(7)

Published: July 31, 2024

The Hospital Management System (HMS) is a robust, computerized solution designed to streamline and manage the daily operations of hospital. This system aims improve overall efficiency hospital activities, ranging from patient management billing, diagnosis, medical record maintenance. primary goal automate organize tasks such as managing inpatient outpatient data, processing treatments, storing diagnostic records, generating bills, tracking pharmacy laboratory activities. Additionally, ensures seamless access reports, allowing them retrieve their history test results anywhere in world, addressing prevalent issue delayed records after consultation.One major issues faced by hospitals inefficient information, which often recorded manually on paper, leading increased administrative workload risk errors. automates these manual processes, staff easily store data. It also facilitates creation digital maintains diagnosis tracks immunization details for children, offers centralized database various diseases treatment options.The eliminates need paper-based documentation, reducing burden staff, ensuring more accurate, up-to-date information. For doctors, it provides instant histories, chances missing important Overall, increase productivity, care, reduce errors consolidating all hospital-related data into one platform. smoother workflows, faster decision-making, better communication across departments, ultimately improved healthcare delivery.This project focuses automating digitizing key aspects operations, thereby creating comprehensive activities efficiently effectively.

Language: Английский

Citations

0
AUTOMATED CARDIAC DISEASE PREDICTION AND SEVERITY DETECTION USING IMAGE SEGMENTATION AND DEEP LEARNING DOI

Bhawna Verma,

Anupama Anupama, G. Gaurav

et al.

International Journal of Research -GRANTHAALAYAH, Journal Year: 2024, Volume and Issue: 12(8)

Published: Aug. 31, 2024

Cardiovascular disease remains a leading cause of mortality worldwide, necessitating accurate and early diagnosis. Cardiac imaging, combined with advanced computational techniques, plays vital role in identifying assessing heart conditions. This project explores the application deep learning—particularly Convolutional Neural Networks (CNNs)—in analyzing multimodal cardiac images to improve diagnostic accuracy efficiency. The proposed system focuses on disease-specific regions CT by employing CNN-based image representation segmentation. A K-Nearest Neighbor (KNN) classifier is used segment into three based color, isolating both affected unaffected areas. By calculating percentage pixels, model estimates severity disease, enabling more informed timely treatment decisions. approach demonstrates potential AI-driven tools enhance noninvasive diagnostics cardiology while minimizing procedural risks costs.

Language: Английский

Citations

0