From COVID-19 to monkeypox: a novel predictive model for emerging infectious diseases DOI Creative Commons

Deren Xu,

Weng Howe Chan, Habibollah Haron

и другие.

BioData Mining, Год журнала: 2024, Номер 17(1)

Опубликована: Окт. 22, 2024

The outbreak of emerging infectious diseases poses significant challenges to global public health. Accurate early forecasting is crucial for effective resource allocation and emergency response planning. This study aims develop a comprehensive predictive model diseases, integrating the blending framework, transfer learning, incremental biological feature Rt increase prediction accuracy practicality. By transferring features from COVID-19 dataset monkeypox introducing dynamically updated learning techniques, model's capability in data-scarce scenarios was significantly improved. research findings demonstrate that framework performs exceptionally well short-term (7-day) predictions. Furthermore, combination techniques enhanced adaptability precision, with 91.41% improvement RMSE an 89.13% MAE. In particular, inclusion enabled more accurately reflect dynamics disease spread, further improving by 1.91% MAE 2.17%. underscores application potential multimodel fusion real-time data updates prediction, offering new theoretical perspectives technical support. not only enriches foundation models but also provides reliable support health responses. Future should continue explore multiple sources enhancing generalization capabilities enhance practicality reliability tools.

Язык: Английский

Artificial intelligence in diabetes management: transformative potential, challenges, and opportunities in healthcare DOI

Arnabjyoti Deva Sarma,

Moitrayee Devi

HORMONES, Год журнала: 2025, Номер unknown

Опубликована: Март 21, 2025

Язык: Английский

Процитировано

0
Beyond the Pain Management Clinic: The Role of AI-Integrated Remote Patient Monitoring in Chronic Disease Management – A Narrative Review DOI Creative Commons
Prachi Patel, Maja Green,

Jennifer Tram

и другие.

Journal of Pain Research, Год журнала: 2024, Номер Volume 17, С. 4223 - 4237

Опубликована: Дек. 1, 2024

Remote Patient Monitoring (RPM) stands as a pivotal advancement in patient-centered care, offering substantial improvements the diagnosis, management, and outcomes of chronic conditions. Through utilization advanced digital technologies, RPM facilitates real-time collection transmission critical health data, enabling clinicians to make prompt, informed decisions that enhance patient safety particularly within home environments. This narrative review synthesizes evidence from peer-reviewed studies evaluate transformative role RPM, its integration with Artificial Intelligence (AI), managing conditions such heart failure, diabetes, pain. By highlighting advancements disease-specific applications, underscores RPM's versatility ability empower patients through education, shared decision-making, adherence therapeutic regimens. The COVID-19 pandemic further emphasized importance ensuring healthcare continuity during systemic disruptions. AI has refined these capabilities, personalized, data analysis. While pain management serves focal area, also examines AI-enhanced applications cardiology diabetes. AI-driven systems, NXTSTIM EcoAI™, are highlighted for their potential revolutionize treatment approaches continuous monitoring, timely interventions, improved outcomes. progression basic wearable devices sophisticated, systems redefine delivery, reduce system burdens, quality life across multiple Looking forward, AI-integrated is expected refine disease strategies by more personalized effective treatments. broader implications, including applicability cardiology, showcase capacity deliver automated, data-driven thereby reducing burdens while enhancing life.

Язык: Английский

Процитировано

4
AI-Driven Management of Type 2 Diabetes in China: Opportunities and Challenges DOI Creative Commons
Zhifang He, Wenyu Li

Diabetes Metabolic Syndrome and Obesity, Год журнала: 2025, Номер Volume 18, С. 85 - 92

Опубликована: Янв. 1, 2025

With the aging of China's population and lifestyle changes, number patients with type 2 diabetes (T2D) has surged, posing a significant challenge to public health system. This study explores application effectiveness artificial intelligence (AI) technology in T2D management from Chinese perspective. AI demonstrates substantial potential personalized treatment planning, real-time monitoring early warning, telemedicine, management. It not only enhances precision convenience but also aids preventing managing complications. Despite challenges data privacy, popularization, standardization, regulation, technology's continuous maturation expanded suggest its increasingly pivotal role In future, through interdepartmental collaboration, policy support, cultural adaptation, is poised bring revolutionary changes China globally.

Язык: Английский

Процитировано

0
Intelligent visual analytics for food safety: A comprehensive review DOI
Qinghui Zhang, Yi Chen, Liang Xue

и другие.

Computer Science Review, Год журнала: 2025, Номер 57, С. 100739 - 100739

Опубликована: Март 6, 2025

Язык: Английский

Процитировано

0
From COVID-19 to monkeypox: a novel predictive model for emerging infectious diseases DOI Creative Commons

Deren Xu,

Weng Howe Chan, Habibollah Haron

и другие.

BioData Mining, Год журнала: 2024, Номер 17(1)

Опубликована: Окт. 22, 2024

The outbreak of emerging infectious diseases poses significant challenges to global public health. Accurate early forecasting is crucial for effective resource allocation and emergency response planning. This study aims develop a comprehensive predictive model diseases, integrating the blending framework, transfer learning, incremental biological feature Rt increase prediction accuracy practicality. By transferring features from COVID-19 dataset monkeypox introducing dynamically updated learning techniques, model's capability in data-scarce scenarios was significantly improved. research findings demonstrate that framework performs exceptionally well short-term (7-day) predictions. Furthermore, combination techniques enhanced adaptability precision, with 91.41% improvement RMSE an 89.13% MAE. In particular, inclusion enabled more accurately reflect dynamics disease spread, further improving by 1.91% MAE 2.17%. underscores application potential multimodel fusion real-time data updates prediction, offering new theoretical perspectives technical support. not only enriches foundation models but also provides reliable support health responses. Future should continue explore multiple sources enhancing generalization capabilities enhance practicality reliability tools.

Язык: Английский

Процитировано

0