Sahlgrenska Global Health Hackathon - Spain > Challenge 3 - Forever vital

Challenge 3 - Forever vital: innovating solutions for healthy aging

How can we leverage personalized medicine and AI to enhance chronic disease management and support healthy aging in a rapidly growing elderly population?

Live Session recording

Video timeline

• 00:00 - Welcome and house rules - Michele Erba - Pristine Agency
• 01:35 - Introduction - Jamie Smith - Sahlgrenska Science Par
• 05:00 - Challenge 3 - Forever Vital - Prof. Axel Wolf - Director of Gothenburg Centre for Person-centred Care GPCC & Senior Consultant at the Sahlgrenska University Hospital
• 26:13 - Q&As
• 29:30 - Wrap up

Challenge problem statement

As the global population ages, managing chronic diseases becomes increasingly critical for maintaining quality of life and reducing healthcare costs. Conditions like diabetes, cardiovascular disease, and neurodegenerative disorders require continuous monitoring and personalized interventions. By adopting a personalized approach and leveraging personalized medicine, we can develop innovative tools to better manage chronic conditions and promote healthy aging, enabling individuals to live longer, healthier lives.

Challenge expected outcome

Your task is to develop solutions that improve chronic disease management and promote healthy aging. Consider using personalized medicine and data-driven approaches to develop solutions could include personalized care plans, predictive models for disease progression, and/or real-time monitoring systems that integrate lifestyle and medical data to enhance disease management and support healthy aging strategies.

Tools made available to participants

We’ve provided data, articles, and resources to kickstart your ideas, but we encourage you to explore beyond these materials for deeper research.

Datasets and resources:

1. Global Burden of Disease (GBD) Study

• Link: GBD Results Tool
• Details: This dataset provides comprehensive global data on chronic diseases such as diabetes, cardiovascular disease, and neurodegenerative disorders. It also includes health-related quality of life metrics and age-specific data, which is crucial for developing personalized care plans and predictive models.

2. UK Biobank

• Link: UK Biobank
• Details: UK Biobank provides health and genetic data from over 500,000 participants, focusing on chronic disease, aging, and lifestyle factors. This dataset is ideal for creating predictive models of disease progression and real-time monitoring systems that consider genetic, lifestyle, and environmental factors.

3. The Alzheimer’s Disease Neuroimaging Initiative (ADNI)

• Link: ADNI Data
• Details: ADNI provides neuroimaging, clinical, and biomarker data on Alzheimer’s and related neurodegenerative disorders. This dataset is valuable for research on personalized interventions and predictive models for neurodegenerative diseases, particularly for the elderly.

4. National Health and Aging Trends Study (NHATS)

• Link: NHATS Data
• Details: NHATS focuses on aging trends and late-life disability, offering data on physical and cognitive health, daily living activities, and long-term care. Participants can use this data to create interventions that support healthy aging and improve chronic disease management in older adults.

5. Health and Retirement Study (HRS)

• Link: HRS Data
• Details: HRS provides data on aging, health, retirement, and social and economic factors. This dataset is useful for understanding how aging populations manage chronic diseases and for designing personalized care plans that consider socioeconomic and lifestyle factors.

6. The Cardiovascular Health Study (CHS)

• Link: CHS Data
• Details: CHS includes data on cardiovascular disease risk factors, progression, and outcomes in older adults. Participants can use this dataset to build predictive models for managing cardiovascular diseases in elderly populations using personalized medicine.

7. The Framingham Heart Study

• Link: Framingham Heart Study
• Details: This dataset includes long-term data on cardiovascular health, risk factors, and aging. It can be leveraged to develop personalized interventions and predictive models for managing cardiovascular conditions in aging populations.

8. The Global Longitudinal Study of Osteoporosis in Women (GLOW)

• Link: GLOW Data
• Details: GLOW provides data on osteoporosis and fracture risk in older women. Participants can use this data to build personalized treatment plans and real-time monitoring tools for managing osteoporosis, a common chronic condition in aging populations.

9. Aging, Dementia and Traumatic Brain Injury (AD&TBI) Initiative

• Link: AD&TBI Data
• Details: This dataset provides insights into aging, dementia, and traumatic brain injury, focusing on elderly populations. It is useful for developing tools that monitor cognitive decline and create personalized treatment plans for brain health.

10. Centers for Disease Control and Prevention (CDC) Chronic Disease Indicators (CDI)

• Link: CDC Chronic Disease Indicators
• Details: This dataset offers a comprehensive set of chronic disease indicators, including diabetes, heart disease, and arthritis. It provides critical information to create predictive models for managing chronic diseases in older adults.

11. Genomics England 100,000 Genomes Project

• Link: 100,000 Genomes Project
• Details: This project provides genomic data related to aging and chronic diseases, including cancer and rare diseases. This dataset is useful for developing personalized medicine tools tailored to genetic risk factors in aging populations.

12. Global Aging Data from the United Nations Population Division

• Link: UN Population Aging Data
• Details: This dataset provides global aging statistics, including life expectancy, aging-related health conditions, and demographic shifts. It can help participants design solutions that address the global aging population's needs.

13. Longitudinal Aging Study Amsterdam (LASA)

• Link: LASA Data
• Details: LASA offers data on the physical, cognitive, emotional, and social functioning of elderly people. This dataset can be leveraged for developing predictive models and monitoring systems that address multiple facets of healthy aging.

14. Global Burden of Disease Study (GBD) - Ageing and Chronic Disease Metrics

• Link: Global Health Data Exchange
• Details: This subset of the GBD Study focuses on age-related diseases and chronic conditions like dementia, diabetes, and cardiovascular diseases. It provides metrics to help participants create data-driven solutions that focus on personalized care for the elderly.

15. EPIC Study (European Prospective Investigation into Cancer and Nutrition)

• Link: EPIC Study Data
• Details: EPIC provides data on lifestyle factors, diet, and chronic disease incidence in older populations. It can support the development of personalized interventions aimed at reducing the risk of chronic disease through lifestyle changes.

Example of potential ideas:

• AI models that predict and prevent disease progression in elderly patients using personalized health data.
• Co-created platforms for chronic disease management that combine medical and lifestyle data for personalized care plans.
• Collaborative real-time monitoring systems using wearable devices and AI to improve chronic disease outcomes and support healthy aging.