CARES健康促進聯盟 | CARES Health Promotion Allianc

From Health Check-up toward New Era of Health Management

ntuhcaresgroup — Sat, 24 May 2025 09:33:33 +0000

This video features Dr. Chiu, the founder of the CARES team and Director at National Taiwan University Hospital, sharing his insights and practices on the evolution from health check-ups to a new era of health management. Dr. Chiu reviews the 20-year development of the Health Management Center at NTU Hospital, emphasizing that modern medicine should not focus solely on disease screening. Instead, the emphasis should shift to the prevention of chronic non-communicable diseases and the overall enhancement of health among the sub-healthy population.

Facing the challenges of an aging population and declining birth rates, health management must incorporate new technologies such as digital tools, artificial intelligence (AI), and the Internet of Things (IoT) to create more personalized and forward-looking health promotion strategies. Dr. Chiu stresses that active participation from the public and the cultivation of healthy lifestyle habits are key to successful health management. He also cites both domestic and international examples, such as the successful reduction of stroke rates in Nagano Prefecture, Japan, and the emerging involvement of the insurance industry in health management.

In addition, he highlights the importance of addressing often overlooked yet serious health threats like obstructive sleep apnea. Looking ahead, health management will place greater focus on quality of life, aiming to achieve a win–win situation through the integration of medical care and technology for early disease prevention and health promotion.

Key Highlights

The NTU Health Management Center celebrates its 20th anniversary, shifting from health check-ups to comprehensive health management.
Chronic non-communicable diseases (such as cardiovascular diseases, diabetes, and cancer) are leading causes of death in developed countries, making prevention essential.
The sub-healthy population constitutes the majority; only about 10% of people are truly healthy, and health management should target improvements in this group.
The adoption of digital technology, AI, and IoT enhances screening efficiency and health monitoring.
Changing lifestyle habits is challenging; fun and incentive-based approaches are needed to sustain behavioral change.
Emphasizes the role of community and home-based healthcare, with hospitals potentially shifting their functions toward community integration.
Insurance companies are beginning to engage in health management by incorporating lifestyle factors into premium adjustment models.

Speaker

The post From Health Check-up toward New Era of Health Management first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Precision Health: Big Data and Disease Risk Prediction

ntuhcaresgroup — Sat, 24 May 2025 08:35:35 +0000

Dr. Hung-Ju Lin of the CARES team, with a background in cardiology and internal medicine, approached the topic from the perspectives of preventive medicine and epidemiology, offering an in-depth explanation of how big data is applied in disease risk prediction and precision health. He emphasized that as life expectancy in Taiwan continues to rise, the urgent challenge lies in extending “healthy life expectancy.” Disease risk prediction can help identify high-risk populations early—particularly in the early stages of chronic diseases such as the susceptibility phase and preclinical stage—allowing interventions in lifestyle habits to delay or even reverse disease progression.

Dr. Lin introduced the five key characteristics of big data—Volume, Variety, Velocity, Veracity, and Value—and explained how integrating diverse types of medical data (such as clinical records, lab indicators, sleep data, and genetic testing) can improve predictive accuracy.

He further elaborated on using a Holmes-style reasoning approach combined with scientific validation methods, along with artificial intelligence and machine learning models (such as Random Forest, Neural Network, and XGBoost) to build a risk prediction model for prediabetes. These models help identify critical predictive features and enhance interpretability and stability. Dr. Lin particularly noted the trade-off between model complexity and prediction error, emphasizing the need to strike the right balance.

Ultimately, he proposed a shift from “Big Data” to “Smart Data,” stressing that precise data organization, verification, and dynamic updating are key to improving prediction quality. Taiwan has already laid a foundation for smart medical databases and alignment with international data standards, making the growth of the precision health industry an inevitable trend.

He also called on the medical community to continue leveraging big data to strengthen disease risk prediction, in tandem with health behavior interventions (such as exercise and diet), to collectively advance toward a new paradigm of personalized precision health.

Key Highlights

While healthy life expectancy in Taiwan has increased, years lived with disability remain high; extending healthy years of life is critical.
The five major characteristics of big data (Volume, Variety, Velocity, Veracity, and Value) open new opportunities for disease risk prediction.
Early prediction of disease risk allows for preventive measures during the susceptibility stage to slow disease progression.
Machine learning and AI technologies improve the accuracy and efficiency of predictive models.
There is a trade-off between model complexity and prediction error; striking the optimal balance is essential.
Taiwan already has long-term patient databases, keeping pace with international research standards.
The shift from big data to smart data—and alignment with global standards and collaborations—is key to future development.

Speaker

The post Precision Health: Big Data and Disease Risk Prediction first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

AI Application in Medicine

ntuhcaresgroup — Sat, 24 May 2025 07:36:56 +0000

Professor Lian-Yu Lin of the CARES team shared insights on the application and development of artificial intelligence (AI) in the medical field. Professor Lin explored AI’s real-world contributions to medical imaging diagnostics, highlighting its exceptional performance in areas such as skin cancer detection, fundus examinations, and cardiovascular disease—often surpassing the accuracy of specialist physicians. He emphasized how AI enhances physician productivity and reduces workload, using radiology as an example where AI significantly improves tasks like quantitative analysis, classification, and image reconstruction. Additionally, he introduced AI-based automatic image segmentation technology and its role in transforming medical data into valuable predictive tools—such as identifying early risks for fractures or cardiovascular events—thus supporting early clinical intervention.

Professor Lin also addressed the potential of AI assistants (like ChatGPT-4) in medical record summarization and patient history analysis. He discussed AI’s applications in cardiology, particularly in ECG and ultrasound diagnostics, underscoring how AI helps reduce physician burnout while improving diagnostic accuracy and medical efficiency. He further noted current limitations of AI, including the black-box nature of deep learning models, risks of misdiagnosis, legal liability concerns, and fairness challenges. Professor Lin asserted that AI should assist rather than replace physicians, and he expressed hope for the future development of “generalist medical AI” to promote human-AI collaboration and enhance the quality of healthcare services.

Key Highlights

AI represents a revolutionary breakthrough in medical image feature extraction, automating tasks that previously required time-consuming manual analysis.
AI improves diagnostic accuracy and has already outperformed specialists in certain areas.
AI reduces the workload of physicians, helping to prevent clinician burnout and improve patient care quality.
AI is widely applied in quantification and classification of X-rays, CT scans, and ultrasound images, supporting clinical decision-making.
AI aids in the identification of rare diseases and genetic syndromes, expanding the diagnostic frontier.
AI assistants (such as ChatGPT-4) streamline medical documentation and enhance administrative efficiency.
Risks such as the black-box problem, accountability issues, and fairness concerns highlight the need for responsible human-AI collaboration.

Speaker

The post AI Application in Medicine first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Challenge in Aging Society: Parkinson’s Disease

ntuhcaresgroup — Sat, 24 May 2025 06:39:09 +0000

This lecture, delivered by Professor Chin-Hsien Lin—a neurology expert from the CARES team—focused on the challenges and strategies related to neurodegenerative diseases in the context of Taiwan’s rapidly aging society. As the population structure shifts dramatically, the proportion of individuals aged 65 and older is expected to reach 25% within the next decade. This demographic change is making neurodegenerative diseases such as Alzheimer’s disease and Parkinson’s disease increasingly prevalent and urgent public health concerns.

The lecture provided an in-depth analysis of the pathogenesis, prodromal symptoms, and the latest diagnostic technologies and treatment trends for these two major conditions.

Professor Lin emphasized that these diseases do not occur suddenly, but rather develop gradually over many years before clinical symptoms become evident. Therefore, early identification and preventive intervention are crucial. She introduced a comprehensive screening approach that includes questionnaires, digital cognitive assessments, voice and motion analysis, advanced brain imaging techniques, and the use of biomarkers. These methods not only help accurately identify individuals at risk but also offer timely opportunities for mechanism-targeted therapeutic interventions.

In addition, Professor Lin shared the latest advances in gene therapy and monoclonal antibody treatments, highlighting that Taiwan’s neurology community has already implemented some of these therapies in clinical practice. This signifies a shift in the treatment of neurodegenerative diseases—from being untreatable to being manageable and capable of slowing disease progression.

She also called for greater attention to brain health, advocating for lifestyle modifications—including diet, exercise, and management of chronic conditions—to improve quality of life and delay neurodegeneration as part of a more holistic approach to health management.

Key Highlights

Taiwan has entered a super-aged society; the proportion of individuals aged 65+ will reach 25% by 2030.
Alzheimer’s disease and Parkinson’s disease are the most common neurodegenerative diseases, typically beginning after age 60.
Neurodegeneration progresses gradually, with prodromal symptoms appearing up to 20 years before clinical onset.
Digital cognitive testing, as well as voice and motion analysis technologies, support early screening and monitoring.
Gene therapy and monoclonal antibody drugs have received FDA approval and are now in clinical use in Taiwan.
Biomarkers and brain imaging enhance diagnostic accuracy and support early detection.
Lifestyle interventions—such as diet, exercise, and chronic disease control—are key non-pharmacological strategies for slowing neurodegeneration.

Speaker

The post Challenge in Aging Society: Parkinson’s Disease first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Health Management 2.0 – Toward Intelligent Medicine

ntuhcaresgroup — Sat, 24 May 2025 05:46:57 +0000

This video features a keynote speech delivered by Mr. Allen Jong, President of Acer Gadget (a subsidiary of Acer Group). He shares insights and practical visions for the future of health management from the perspective of the technology industry. Mr. Zhong emphasizes that traditional health checkups are like periodic car maintenance—they can identify problems but fail to provide real-time alerts or promote long-term behavioral change. In response, he proposes a new concept of “daily health management” and advocates for the use of technology to empower individuals in managing their own health.

He showcases Acer Group’s innovative smart health devices, including a bidet toilet seat with integrated physiological monitoring, an exercise-powered workstation (“Küchi Desk”), and a connected health management app. These devices collect physiological data and upload it to the cloud, where AI-driven analysis can generate disease risk assessments and health recommendations.

Mr. Zhong also introduces three ongoing proof-of-concept (POC) projects focused on medical risk prediction, personalized health scoring, and smart retail integration. He stresses the importance of building a comprehensive health management platform that connects the medical, insurance, retail, and long-term care sectors—laying the foundation for a homegrown health-tech ecosystem in Taiwan. His ultimate vision is to use technology not just to serve the younger generation, but to improve the overall quality of life for all humanity, with the potential to scale Taiwan’s model internationally.

Key Highlights

Traditional health checkups resemble “overhauls” and should evolve toward daily monitoring and behavioral adjustment.
Acer promotes a “centralized health management” concept by integrating household devices for continuous physiological monitoring.
Smartphones serve as health data hubs, enabling AI-based risk analysis and health assessment.
Three key POC projects: medical risk prediction, health scoring, and precision marketing/exercise integration.
Cross-sector collaboration is encouraged—shifting from selling devices to building data platforms and health-promotion ecosystems.
Data security and privacy are critical; the use of blockchain and anonymization technologies is recommended to build trust.
Health promotion should incorporate gamification and social care elements to increase public engagement and acceptance.

Speaker

The post Health Management 2.0 – Toward Intelligent Medicine first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Virtual Module Platform System Development Plan

ntuhcaresgroup — Thu, 22 May 2025 01:04:00 +0000

Subproject Four: Virtual Module Platform System Development Plan

With the rapid advancement of digital healthcare, virtual health platforms are becoming essential tools for improving health management. This project focuses on developing a virtual platform system centered on personal-generated health data (PGHD). By integrating wearable devices and risk prediction models, it aims to provide real-time and precise health management services. The key achievements and applications are as follows:

1. PGHD Transmission Workflow

We have completed initial tests for the PGHD transmission workflow, successfully verifying the technical feasibility of data collection and management. The system imports data from Google Fit and Apple Health, temporarily stores it on AWS, and then integrates it into a backend management system for analysis. Current data sources include wearable devices and smartphones, primarily collecting heart rate, step count, and sleep duration. Due to the limitations of some devices in measuring electrocardiograms (ECG) and blood pressure, these are secondary data collection targets. This workflow establishes a solid foundation for the future expansion of health platforms by ensuring the seamless integration and flow of multi-device, multi-platform data.

2. Health Data Collection Platform

To further enhance data collection efficiency, we have developed a platform capable of automatically processing data from wearable devices. Users can synchronize their data to the platform through Google Fit or Apple Health authorization. Key data collected includes:

Heart Rate: Real-time monitoring of cardiac health.
Step Count: Reflecting daily activity levels.
Sleep Duration: Assessing individual rest quality.

Future developments will expand the collection to additional physiological indicators, such as blood pressure and ECG, to provide more comprehensive health data.

3. Chronic Disease Risk Prediction Model Platform

Building on previously developed chronic disease risk models, we have established a risk prediction platform. Users can input their personal health data to predict their risk of developing diseases within the next five years. The platform currently supports risk assessments for diabetes and chronic obstructive pulmonary disease (COPD):

Diabetes Risk Platform: Users can understand their likelihood of developing diabetes and receive professional advice, such as dietary adjustments or exercise plans.
COPD Risk Platform: This feature provides predictions about lung function status, enabling early treatment or health interventions.

These functionalities not only enhance the convenience of individual health management but also support healthcare institutions in delivering more precise disease prevention.

Applications and Future Prospects

The virtual module platform integrates PGHD technologies and risk prediction models, effectively facilitating the integration of health data while offering personalized health management solutions. In the future, we plan to further expand the platform’s features by introducing additional disease models and advanced data analysis technologies. By improving data collection and prediction accuracy, we aim to ensure that every user can enjoy efficient and accessible health services.

The post Virtual Module Platform System Development Plan first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Development of Chronic Disease Risk Prediction Models

ntuhcaresgroup — Tue, 20 May 2025 07:30:58 +0000

Subproject One: Development of Chronic Disease Risk Prediction Models

Chronic diseases such as diabetes, chronic lung disease, cardiovascular disease, Parkinson’s disease, and liver diseases are significant challenges in modern healthcare. This project leverages health check-up data and artificial intelligence (AI) technologies to develop various risk prediction models, facilitating early screening and personalized health management. Below are the key research achievements and applications:

1. Diabetes Risk Prediction Model

We developed a 5-year diabetes risk prediction model targeting prediabetic and non-diabetic populations. Using machine learning algorithms such as XGBoost, the model achieved over 80% accuracy. The three most critical predictors identified are glycated hemoglobin (HbA1c), fasting blood glucose, and postprandial blood glucose. This model enables healthcare teams to identify high-risk individuals early, offering lifestyle recommendations and medical interventions.

2. Chronic Lung Disease Risk Prediction Model

Based on long-term lung function data from non-smokers, we developed a risk prediction model for chronic obstructive pulmonary disease (COPD). Key risk factors include total cholesterol, low-density lipoprotein (LDL), and lung function metrics such as FEV1/FVC. With an accuracy rate of 85%, the model provides early diagnosis and preventive strategies, enhancing patient quality of life.

3. Coronary Artery Disease Risk Prediction Model

By analyzing coronary artery calcium (CAC) scores, we created a model to predict cardiovascular hospitalization risk. Age, hypertension, and CAC scores emerged as key factors. The model, with an accuracy of 83%, aids healthcare professionals in formulating treatment plans for high-risk patients, preventing severe cardiovascular events.

4. Parkinson’s Disease Risk Prediction Model

Utilizing smartphone-recorded voice and facial expression data, we integrated biological features to perform early screening for Parkinson’s disease. Key indicators include speech characteristics (e.g., speed and pitch) and facial movement patterns (e.g., mouth and eye dynamics). The model achieved 90% accuracy and has been validated with international datasets, marking a breakthrough in the early detection of neurodegenerative diseases.

5. Liver Disease Risk Prediction Model

Focusing on high-risk factors for liver cancer, such as fatty liver and liver fibrosis, we developed risk screening models using health check-up data. The models achieved over 85% accuracy. Key predictors include BMI, triglycerides (TG), and liver function markers such as ALT. These models assist in early intervention for high-risk individuals, reducing the risk of disease progression.

6. HBV and HCC-Related Research

For chronic hepatits B (HBV) patients, we developed a risk assessment system based on HBcrAg to predict liver cancer (HCC) risk. The model achieved an AUC exceeding 0.90, significantly outperforming traditional risk scoring systems. This tool helps identify high-risk patients and prioritize antiviral treatments, effectively lowering HCC incidence rates.

Applications and Future Prospects

These risk prediction models provide scientific support for the early screening and management of chronic diseases. They not only assist medical professionals in diagnosis but also empower individuals to understand their health risks through check-up data and take preventive measures. Looking ahead, we aim to enhance the accuracy of these models and expand their adoption in more healthcare facilities, advancing preventive medicine and benefiting broader populations.

The post Development of Chronic Disease Risk Prediction Models first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Development of Health Behavior Promotion Modules

admin — Mon, 19 May 2025 04:03:05 +0000

Subproject Two: Development of Health Behavior Promotion Modules

Modern medicine increasingly emphasizes the prevention of chronic diseases through changes in health behavior. This project focuses on the impact of exercise interventions and sleep quality on health, developing practical behavior promotion modules to help individuals improve their health management capabilities. The key research highlights and findings are as follows:

1. The Impact of Exercise on Metabolic Diseases and Colorectal Tumor Risk

Studies have shown that maintaining regular exercise habits after colorectal polyp removal significantly reduces the risk of metachronous advanced colorectal neoplasms (meta-ACRN). Further analysis revealed that this protective effect is more pronounced in patients with metabolic diseases, while the impact on metabolically healthy individuals is minimal. This finding underscores the importance of exercise for individuals with metabolic disorders. It provides a scientific foundation for designing tailored exercise programs, helping reduce tumor recurrence risk.

2. Health Improvements Through Exercise Interventions in Workplace Employees

We conducted an exercise intervention study with 29 workplace employees. Observations revealed a general reduction in total cholesterol and body weight, alongside a significant improvement in cardiorespiratory endurance. These results demonstrate that exercise interventions not only enhance physical fitness but also help prevent chronic diseases. This study provides empirical support for promoting workplace wellness programs, further enhancing employee well-being.

3. The Relationship Between Neurodegenerative Diseases and Sleep Quality

Neurodegenerative diseases, such as dementia and Parkinson’s disease, are becoming increasingly common among older adults. Using long-term data from individuals aged 50 and above at health management centers, we found a strong correlation between poor sleep quality and the onset of these diseases. Individuals with lower sleep quality scores (higher PSQI scores) were at significantly higher risk of developing neurodegenerative conditions. Even after adjusting for traditional risk factors, poor sleep remained an independent risk factor. This research highlights the importance of improving sleep habits in preventing neurodegenerative diseases and provides specific directions for health education.

Future Prospects

This subproject aims to assist the public in preventing chronic and neurodegenerative diseases through simple and effective health behavior promotion modules. We will continue to refine these models, incorporating big data analytics and personalized recommendations to benefit individuals and guide them toward healthier lives.

The post Development of Health Behavior Promotion Modules first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.

Chip Development Project

admin — Sun, 18 May 2025 02:51:24 +0000

Subproject Three: Chip Development Project

Modern healthcare is rapidly evolving with the miniaturization and smartification of devices, transforming health management methods. This project focuses on the development of wearable sensing technologies and ion sensing models to provide precise and real-time health monitoring tools, enhancing disease diagnosis and recovery efficiency. The key highlights of the research are as follows:

1. Wearable Pressure Sensing Module

We are developing a low-power, high-performance wearable pressure sensing module. The core technology combines liquid metal with biomimetic shark skin structures, forming a highly sensitive and stable self-powered sensing system. This module can instantly capture and analyze gait data, which is crucial for diagnosing neuromuscular diseases and tracking post-operative recovery.
Preliminary studies indicate that the system can accurately distinguish between normal and pathological gaits, providing clinicians with valuable data for disease classification and treatment evaluation. Moreover, gait recovery data collected by the system show a strong correlation with MRI results, particularly in patients with herniated intervertebral discs (HIVD) and anterior cruciate ligament (ACL) tears. This confirms its significant potential for clinical applications. In the future, this technology will integrate real-time data transmission and remote monitoring capabilities to offer more convenient recovery assessments for post-surgical patients.

2. Ion Sensing Model Development

The project has established a comprehensive ion sensing processing workflow, aligning with the development timeline of biomedical signal sensors. Based on existing research, the team optimizes AI algorithms to enhance the precision and stability of the sensing model. This technology is expected to be applicable in various biomedical monitoring scenarios in the future.

Applications and Future Prospects

The development of these technologies will significantly improve the precision and convenience of medical devices, enabling real-time health monitoring, remote data analysis, and personalized health management. In the future, we aim to further integrate multiple sensing technologies, creating a more intelligent medical system that enhances patient treatment outcomes and quality of life.

The post Chip Development Project first appeared on CARES健康促進聯盟 | CARES Health Promotion Allianc.