EVYD Technologies Problem Statements

Recording

EVYD Technology: Problem Statement Sharing Session

EYVD Technologies: Problem Statement 1 – Creating an AI Health Coach

Prize: 3-month internship position (Singapore or Brunei) or mentoring opportunity

1st place $350 USD - Microsoft Funded

This 3-month internship position will be unpaid and take place at either EVYD Technology’s Singapore or Brunei office. The winner will need to be able to work in Brunei or Singapore. Alternatively, EVYD Technology can offer a mentoring opportunity for the winner who does not meet the criteria or cannot participate in the internship.

Background:

The global health landscape is dominated by noncommunicable diseases (NCDs) such as heart disease, cancer, diabetes, and obesity, contributing to 74% of deaths worldwide, according to the World Health Organisation. The rise of these diseases is largely due to unhealthy lifestyles, including poor diet and inactivity, leading to risk factors like hypertension, elevated blood sugar, and obesity. These conditions can escalate into severe health problems, including cardiovascular diseases and early mortality, if not adequately managed.

Amidst this, healthcare providers play a crucial role in promoting healthier lifestyles among those at risk. Yet, the journey to a healthy lifestyle is deeply rooted in behavioural change, demanding more than just health education—it requires impactful coaching techniques. Unfortunately, most healthcare professionals lack training in such methodologies, posing a significant challenge in addressing NCDs effectively.

The challenge:

Imagine a world where an AI health coach exists, capable of offering personalised coaching tailored to an individual’s specific health risks (for instance, hypertension or high cholesterol). This AI health coach aims to steer people towards a healthier lifestyle, encompassing a nutritious diet, regular physical activity, and effective stress management.

Your task is to develop an AI health coach solution. This AI coach should not only possess a comprehensive, evidence-based health knowledge base but should also employ motivational behavioural science strategies to foster habit change successfully.

Objectives:

• Personalisation: Your solution should assess and understand individual health risk factors and preferences, offering customised advice and plans.
• Knowledge integration: Include an evidence-based health information repository to support the advice provided.
• Behavioural change: Utilise motivation-based behavioural science techniques such as Stages of Change model to encourage users to adopt and maintain healthier lifestyle choices.
• Engagement: Design engaging and interactive elements to keep users motivated and committed to their health journey.

Additional mini challenge:

Cultural sensitivity: In a world rich with cultural diversity, how can your AI Health Coach respect and adapt to the cultural nuances of diet, exercise, and health beliefs of its users? Could integrating cultural intelligence into the AI improve its effectiveness in fostering healthier lifestyles?

Tech stack for the challenge:

Azure Machine Learning, Azure OpenAI, Power Apps.

Relevant literature for knowledge base:

  1. ⁠Sacks, Frank M., et al. “Effects on blood pressure of reduced dietary sodium and the Dietary Approaches to Stop Hypertension (DASH) diet.” New England journal of medicine 344.1 (2001): 3-10.

  2. Siervo, Mario, et al. “Effects of the Dietary Approach to Stop Hypertension (DASH) diet on cardiovascular risk factors: a systematic review and meta-analysis.” British Journal of Nutrition 113.1 (2015): 1-15.

  3. Hinderliter, Alan L., et al. “The DASH diet and insulin sensitivity.” Current hypertension reports 13 (2011): 67-73.

  4. Muraki, Isao, et al. “Fruit consumption and risk of type 2 diabetes: results from three prospective longitudinal cohort studies.” Bmj 347 (2013).

  5. ⁠Blair, Steven N. “Physical inactivity: the biggest public health problem of the 21st century.” British journal of sports medicine 43.1 (2009): 1-2.

  6. ⁠Buettner, Dan, and Sam Skemp. “Blue zones: lessons from the world’s longest lived.” American journal of lifestyle medicine 10.5 (2016): 318-321.

  7. ⁠Lloyd-Jones, Donald M., et al. “Status of cardiovascular health in US adults and children using the American Heart Association’s new “Life’s Essential 8” metrics: prevalence estimates from the National Health and Nutrition Examination Survey (NHANES), 2013 through 2018.” Circulation 146.11 (2022): 822-835.

  8. ⁠Tiny Habits® for Gratitude-Implications for Healthcare Education Stakeholders (frontiersin-journals-public-health-articles)

  9. ⁠Osuka, Yosuke, et al. “Exercise type and activities of daily living disability in older women: An 8‐year population‐based cohort study.” Scandinavian Journal of Medicine & Science in Sports 29.3 (2019): 400-406.

  10. ⁠Ôunpuu, Stephanie, Abdissa Negassa, and Salim Yusuf. “INTER-HEART: A global study of risk factors for acute myocardial infarction.” American heart journal 141.5 (2001): 711-721.

  11. ⁠Ornish, Dean, et al. “Intensive lifestyle changes for reversal of coronary heart disease.” Jama 280.23 (1998): 2001-2007.

  12. ⁠Barnard, Neal D., et al. “A low-fat vegan diet improves glycemic control and cardiovascular risk factors in a randomized clinical trial in individuals with type 2 diabetes.” Diabetes care 29.8 (2006): 1777-1783.

  13. ⁠InterAct Consortium. “Association between dietary meat consumption and incident type 2 diabetes: the EPIC-InterAct study.” Diabetologia 56 (2013): 47-59.

  14. ⁠Mishra, S., et al. “A multicenter randomized controlled trial of a plant-based nutrition program to reduce body weight and cardiovascular risk in the corporate setting: the GEICO study.” European journal of clinical nutrition 67.7 (2013): 718-724.

  15. ⁠Sun, Qi, et al. “White rice, brown rice, and risk of type 2 diabetes in US men and women.” Archives of internal medicine 170.11 (2010): 961-969.

  16. ⁠Aune, Dagfinn, et al. “Whole grain and refined grain consumption and the risk of type 2 diabetes: a systematic review and dose–response meta-analysis of cohort studies.” European journal of epidemiology 28 (2013): 845-858.

  17. Anderson, James W., and Kyleen Ward. “High-carbohydrate, high-fiber diets for insulin-treated men with diabetes mellitus.” The American journal of clinical nutrition 32.11 (1979): 2312-2321.

  18. ⁠Yao, Baodong, et al. “Dietary fiber intake and risk of type 2 diabetes: a dose–response analysis of prospective studies.” European journal of epidemiology 29 (2014): 79-88.

  19. ⁠Dunaief, D. M., et al. “Glycemic and cardiovascular parameters improved in type 2 diabetes with the high nutrient density (HND) diet.” (2012).

  20. ⁠Dunstan, DAVID W., et al. “Television viewing time and mortality: the Australian diabetes, obesity and lifestyle study (AusDiab).” Circulation 121.3 (2010): 384-391.

  21. ⁠Marengoni, Alessandra, et al. “The effect of a 2-year intervention consisting of diet, physical exercise, cognitive training, and monitoring of vascular risk on chronic morbidity—the FINGER randomized controlled trial.” Journal of the American Medical Directors Association 19.4 (2018): 355-360.

  22. ⁠Ornish, Dean, et al. “Intensive lifestyle changes may affect the progression of prostate cancer.” The Journal of urology 174.3 (2005): 1065-1070.

  23. https://www.pcrm.org/health-topics/high-blood-pressure⁠

  24. https://www.pcrm.org/health-topics/weight-loss⁠

  25. https://www.pcrm.org/health-topics/alzheimers

EYVD Technologies: Problem Statement 2 - Discovering personas associated with Type 2 diabetes risk using data

Prize: 3-month internship position (Singapore or Brunei) or mentoring opportunity

1st place $350 USD - Microsoft Funded

This 3-month internship position will be unpaid and take place at either EVYD Technology’s Singapore or Brunei office. The winner will need to be able to work in Brunei or Singapore. Alternatively, EVYD Technology can offer a mentoring opportunity for the winner who does not meet the criteria or cannot participate in the internship.

Background:

Type 2 diabetes mellitus (T2DM) stands as a towering challenge in the realm of global health, its prevalence soaring as one of today’s most widespread noncommunicable diseases (NCDs). At the heart of T2DM lies a complex web of lifestyle choices—what we eat, how much we move, and even how we rest. These choices weave together to form patterns that can significantly elevate the risk of developing this life-altering condition.

The challenge:

Your task is to dive deep into this data and emerge with insights that illuminate the personas at high risk for T2DM. A “persona” here is not just a statistic but a richly detailed portrait composed of lifestyle attributes: demographics, health behaviours, and overall health status.

Objectives:

• Data exploration: Analyse the dataset to identify key factors and patterns that correlate with an increased risk of T2DM.
• Persona creation: Synthesise your findings to construct detailed personas—comprehensive profiles embodying the lifestyle attributes that signal a higher risk of T2DM.
• Insight generation: Provide actionable insights based on the personas identified. How can these insights inform public health strategies, personalised interventions, and awareness campaigns to combat T2DM?

Some guiding questions:

  1. What combinations of lifestyle attributes (e.g., diet, physical activity, sleep patterns) are most commonly associated with a high risk of T2DM?
  2. How do demographic factors (such as age, gender, socioeconomic status, and geographic location) intersect with lifestyle choices to influence T2DM risk?
  3. In what ways can understanding these personas inform more targeted and effective interventions for preventing T2DM?
  4. How might this persona-based approach contribute to public health policies and personal health practices?

This challenge invites you to blend analytical rigor with creative thinking, using data to craft narratives that reveal the human side of health statistics. Through your exploration, you will not only identify those at greatest risk but also contribute to shaping interventions that can alter the course of their health journeys.


Tech stack: Azure Machine Learning, Power Apps.

 
 

Sponsored by:

Powered by:

Stay connected: