Enhancing health expectancy to make communities resilient to pandemics
The research aims to develop a public alert system using open-source Big Data. The system targets individuals at the grass-root level to help make informed consumption, social and economic decisions to enhance their health expectancy. Enhancing health expectancy is expected to make individuals resilient to downturns and pandemic conditions
Dr Mathew Parackal
Primary Investigator
Department of Marketing
University of Otago
New Zealand
- Recover (Improve health & economic system resilience), such as: Best protective interventions, especially for vulnerable populations, Avoid/mitigate negative second-order consequences, Integrate true costs of pandemic risk into economic systems
We have successfully lengthened the life expectancy, all the same, the quality of life remains questionable. This is evident from many western societies legalising euthanasia. The ageing population along with people with poor life quality and having underlying health issues makes us vulnerable to downturns and pandemic conditions. The challenge is to enhance health expectancy, that is, life expectancy spent in good health, free of functional restrictions. Enhanced health expectancy will make individuals physically and emotionally resilient. We view health expectancy as the outcome of our choices (e.g. consumption, socio-economic and work-life balance). Incidentally, digital footprints of these choices are available as Big Data in many modern economies. Our primary aim would be to develop a health expectancy construct to be used as the predictor variables to model an alert system for optimising choices. We adopt Dahlgren and Whitehead's rainbow model to theorise the relationship between individuals and the choice dimensions. Using the NZ Living Standard, we structure the dimensions into four capitals (Environment, Social, Human, Financial) to identify open source Big Data sources for modelling health expectancy. Once validated, the model will inform choices that enhance health expectancy, making individuals resilient to downturns and future pandemic conditions
Our solution is targeting individuals (or citizens) of a population or country. The solution is aimed at helping individuals make informed decisions to enhance their health expectancy.
We hope to establish a country level health expectancy measurement and standardised constants (or coefficients or bi) for all types of day to day choices. We hope to apply supervised and unsupervised machine learning to generate artificial intelligence to help individuals make informed decisions that enhance health expectancy, making them resilient to all kinds of downturns or setbacks.
Our research is public health and communication have shown that many individuals their health and wellbeing are deteriorating after a certain point. We observed that in our research that investigated the impact alcohol had on wellbeing.
We have over the years been an advocate for public health, communicating our knowledge via media and publication. We have extensively worked on the harms caused by alcohol on the fetus (FASD). Our interest in knowledge translation led to maintain an e-journey at www.thoughtleader.nz
- Proof of Concept: A venture or organisation building and testing its prototype, research, product, service, or business/policy model, and has built preliminary evidence or data
- Artificial Intelligence / Machine Learning
- Big Data
Our solution is targeting the general public, that is, to make people resilient to situations that COVID19 has created. We also will be publishing our solution in peer-reviewed journal articles to make our methodologies and measures know to the research community. Our data will be made open source to other researchers via a cloud-based storage.
Simply put, we expect that our solution helps people make better choices. Our rationale is that by making better choices, people can enhance the quality of life and their health expectancy. If the population health expectancy is enhanced, we would collectively be resilient to economic and health setbacks.
There is strong evidence of improving prediction by combining multiple variables and data sources. For example, researchers have successfully used the purchase of 23 consumer durable (consumption data) to predict pregnancy. Our own research combining human values with intention produced an accurate prediction of voter behaviour.
In the first year, we would identify the relevant variables to define the constructs of interest (Health expectancy). Once the variables and constructs have been validated, we will start modelling them using Big Data sources for the populations to establish coefficients for the choices.
In the next three years, we hope to validate the model. Use the model to generate artificial intelligence (AI). The AI will be validated and visualised for quick interpretation for public consumption.
The validation study will confirm the effectiveness of our model. This will also inform us whether it can be made available for the consumption of the general public
- New Zealand
- New Zealand
Access to country-level data sources is the main barrier. We are awaiting the outcome of the funding application made to major research funders in NZ.
We hope participating in the Trinity Challenge will help find collaborators who give help us access high-level data sources
- Academic or Research Institution
University of Otago
The main barriers that stop us from working on the solution include funding and access to data courses. We are hoping that being part of the Trinity Challenge and the TTC network will help us overcome these barriers.
We need country-level access to data social media data and data sources. We would like to partner with Facebook and Google to gain access to national-level social and search data.