WIKAYA technology is the result of significant advancements that we have witnessed over the past few decades with regards to understanding the causes of chronic diseases, human behavior, and machine learning capabilities.
WIKAYA is a product of integrating state-of-the-art knowledge in two fields:
I – Clinical
Prevention of chronic diseases has long been the focus of healthcare service providers because of its potentially huge impact on the population’s health and, consequently, on the cost of healthcare services.
While the causes of chronic diseases are mostly known and can even be identified in advance, the main challenge still remains the population’s compliance with given prevention guidelines, and in many cases, the lack of awareness and knowledge as to what can and needs to be done as a preventive measure.
Prevention guidelines are usually very generic (e.g., maintaining healthy weight, eating healthy nutrition, stopping smoking, doing physical activity, etc.) and not prioritized.
The comprehensive WIKAYA prevention app relates to 3 aspects:
In Phase I, WIKAYA focuses on the primary and secondary prevention of the following diseases:
At a later stage, this phase will also include Stroke and Chronic Obstructive Pulmonary Disease (COPD).
WIKAYA technology appeals to users who have not been diagnosed with chronic diseases at this stage.
In Phase II, WIKAYA will also provide tertiary prevention to prevent complications among user who have already been diagnosed.
The traditional approach to prevention begins with risk calculation, using evidence-based disease risk calculators that have been in use by physicians for many years. The main weakness of this approach, however, is that risk of chronic disease is composed of two factors:
1- Modifiable risk factors that can be changed, such as nutrition, physical activity, and smoking.
2- Non-modifiable risk factors that cannot be changed, such as age, gender, race and family history.
WIKAYA can be summarized by “Think Prevention”, rather than risk. That is why we focus on the modifiable risk factors and measure people’s efforts – not results – as, at the end of the day, efforts are what really matter when it comes to creating an impact.
Take, for example, the following cases: Two different individuals with different family histories, age, and race. Both exercise three hours a week, eat healthy food and do not consume alcohol. They may have different levels of cholesterol as this can also be affected by genetics. In other words, although they make the same preventive efforts, they may differ in terms of risk.
That is why we created the WIKAYA Prevention Score – a unique scoring system that gives users a clear indication of their level of preventive efforts. The scoring is derived from risk calculations that are based on the “Population Attribution Fraction”. The modifiable risk factors are isolated as they are the only factors included in the Prevention Score. Recommendations for lifestyle changes and preventive efforts are calculated and prioritized individually for each and every user.
Early detection of chronic diseases may improve outcomes and significantly affect disease management – in some cases even in terms of mortality and morbidity.
WIKAYA’s default recommendations for screening tests are based on the US Preventive Services Task Force (USPSTF) recommendations (but can be amended to comply with additional jurisdictional health organizations and requirements).
Health literacy has proven to be an important factor in the prevention of diseases in general and of chronic diseases in particular. WIKAYA algorithms provide personally-customized health education content to improve awareness and help users make relevant and helpful decisions regarding their health. WIKAYA periodically tests users’ relevant knowledge and updates the scoring accordingly.
II – Artificial Intelligence
WIKAYA uses data algorithms to predict compliance with prevention recommendations and prioritize them.
Our algorithms collect data through mobile devices (smartphones and wearables), analyzes it, and then calculates compliance probability for several forms of prevention recommendations, to provide users with recommendations of the highest probability (and the highest impact for the scoring system).