Machine Learning-Driven Threat Detection in Healthcare: A Cloud-Native Framework Using AWS Services DOI Open Access

Venkata Jagadeesh Reddy Kopparthi

International Journal of Scientific Research in Computer Science Engineering and Information Technology, Journal Year: 2024, Volume and Issue: 10(6), P. 1585 - 1595

Published: Dec. 12, 2024

This article presents a comprehensive framework for implementing machine learning-based threat detection in healthcare organizations using AWS cloud services. The increasing sophistication of cyber threats environments and stringent regulatory requirements protecting patient data necessitate more advanced security solutions. proposes an intelligent system that leverages services, including Amazon SageMaker, GuardDuty, Macie, integrated with custom learning models anomaly predictive analysis. implements real-time monitoring capabilities electronic health records (EHR), connected medical devices, network activities while ensuring HIPAA compliance. results demonstrate significant improvements accuracy, reduced false positives, enhanced response times compared to traditional approaches. system's ability continuously learn from new patterns adapt emerging showcases its effectiveness maintaining robust cybersecurity. contributes the growing body knowledge provides practical insights seeking implement cloud-based solutions proactive detection.

Language: Английский

Deep Reinforced Cognitive Analytics Algorithm (DRCAM): An Advanced Method to early detection of Cognitive skill impairment using Deep Learning and Reinforcement Learning DOI Creative Commons
Sunita Patil,

Shaveta Malik

MethodsX, Journal Year: 2025, Volume and Issue: unknown, P. 103277 - 103277

Published: March 1, 2025

Language: Английский

Citations

0
A State-of-the-Art Review of Artificial Intelligence (AI) Applications in Healthcare: Advances in Diabetes, Cancer, Epidemiology, and Mortality Prediction DOI Creative Commons
Mariano Vargas-Santiago, Diana A. León-Velasco, Christian E. Maldonado-Sifuentes

et al.

Computers, Journal Year: 2025, Volume and Issue: 14(4), P. 143 - 143

Published: April 10, 2025

Artificial Intelligence (AI) methodologies have profoundly influenced healthcare research, particularly in chronic disease management and public health. This paper provides a comprehensive state-of-the-art review of AI’s applications across diabetes, cancer, epidemiology, mortality prediction. The analysis highlights advancements machine learning (ML), deep (DL), natural language processing (NLP) that enable robust predictive models decision support systems, leading to significant clinical health outcomes. study examines modeling, pattern recognition, applications, addressing their respective challenges potential real-world settings. Emphasis is placed on the emerging role explainable AI (XAI), multimodal data fusion, privacy-preserving techniques such as federated learning, which aim enhance interpretability, robustness, ethical compliance. underscores vital interdisciplinary collaboration adaptive systems creating resilient, scalable, patient-centric solutions.

Language: Английский

Citations

0
Exploring the potential and limitations of deep learning and explainable AI for longitudinal life course analysis DOI Creative Commons
Helen Coupland, Neil Scheidwasser-Clow, Alexandros Katsiferis

et al.

BMC Public Health, Journal Year: 2025, Volume and Issue: 25(1)

Published: April 24, 2025

Abstract Background Understanding the complex interplay between life course exposures, such as adverse childhood experiences and environmental factors, disease risk is essential for developing effective public health interventions. Traditional epidemiological methods, regression models scoring, are limited in their ability to capture non-linear temporally dynamic nature of these relationships. Deep learning (DL) explainable artificial intelligence (XAI) increasingly applied within healthcare settings identify influential factors enable personalised However, significant gaps remain understanding utility limitations, especially sparse longitudinal data how patterns identified using explainability linked underlying causal mechanisms. Methods We conducted a controlled simulation study assess performance various state-of-the-art DL architectures including CNNs (attention-based) RNNs against XGBoost logistic regression. Input was simulated reflect generic generalisable scenario with different rules used generate multiple realistic outcomes based upon concepts. Multiple metrics were model presence class imbalance SHAP values calculated. Results find that methods can accurately detect relationships baseline linear tree-based cannot. there no one consistently outperforms others across all scenarios. further superior handling feature availability over time compared traditional machine approaches. Additionally, we examine interpretability provided by values, demonstrating explanations often misalign relationships, despite excellent predictive calibrative performance. Conclusions These insights provide foundation future research applying XAI data, highlighting challenges associated critical need advancing frameworks health.

Language: Английский

Citations

0
The Role of AI-Based Chatbots in Public Health Emergencies: A Narrative Review DOI Creative Commons
Francesco Branda, Massimo Stella, C. Ceccarelli

et al.

Future Internet, Journal Year: 2025, Volume and Issue: 17(4), P. 145 - 145

Published: March 26, 2025

The rapid emergence of infectious disease outbreaks has underscored the urgent need for effective communication tools to manage public health crises. Artificial Intelligence (AI)-based chatbots have become increasingly important in these situations, serving as critical resources provide immediate and reliable information. This review examines role AI-based emergencies, particularly during outbreaks. By providing real-time responses inquiries, help disseminate accurate information, correct misinformation, reduce anxiety. Furthermore, AI play a vital supporting healthcare systems by triaging offering guidance on symptoms preventive measures, directing users appropriate services. not only enhances access information but also helps alleviate workload professionals, allowing them focus more complex tasks. However, implementation is without challenges. Issues such accuracy user trust, ethical considerations regarding data privacy are factors that be addressed optimize their effectiveness. Additionally, adaptability rapidly evolving scenarios essential sustained relevance. Despite challenges, potential AI-driven transform emergencies significant. highlights importance continuous development integration into strategies enhance preparedness response efforts Their accessible, accurate, timely makes indispensable modern emergency management.

Language: Английский

Citations

0
Pregnant women’s lifestyles and exposure to endocrine-disrupting chemicals: a machine learning approach DOI
Surabhi Shah, Jongmin Oh, Yoorim Bang

et al.

Environmental Pollution, Journal Year: 2024, Volume and Issue: unknown, P. 125309 - 125309

Published: Nov. 1, 2024

Language: Английский

Citations

1
Machine Learning-Driven Threat Detection in Healthcare: A Cloud-Native Framework Using AWS Services DOI Open Access

Venkata Jagadeesh Reddy Kopparthi

International Journal of Scientific Research in Computer Science Engineering and Information Technology, Journal Year: 2024, Volume and Issue: 10(6), P. 1585 - 1595

Published: Dec. 12, 2024

This article presents a comprehensive framework for implementing machine learning-based threat detection in healthcare organizations using AWS cloud services. The increasing sophistication of cyber threats environments and stringent regulatory requirements protecting patient data necessitate more advanced security solutions. proposes an intelligent system that leverages services, including Amazon SageMaker, GuardDuty, Macie, integrated with custom learning models anomaly predictive analysis. implements real-time monitoring capabilities electronic health records (EHR), connected medical devices, network activities while ensuring HIPAA compliance. results demonstrate significant improvements accuracy, reduced false positives, enhanced response times compared to traditional approaches. system's ability continuously learn from new patterns adapt emerging showcases its effectiveness maintaining robust cybersecurity. contributes the growing body knowledge provides practical insights seeking implement cloud-based solutions proactive detection.

Language: Английский

Citations

0