How Can Machine Learning Contribute to Our Wellness? Posted on : Oct 17 - 2020

However, what if we add to this and take a more holistic approach to health, describing it as more than just the “absence of illness?”

Wellness is a somewhat elusive concept, defined by the WHO as “a state of complete physical, mental, and social well-being, and not merely the absence of disease or infirmity.” Can machine learning contribute to our wellness?

It Does Start with the Absence of Illness

Health does feature prominently in the overall wellness of a person for the simple reason that being free of illness is the main prerequisite. In other words, suffering from a disease of some kind will trump everything else you do for your wellness.

There is no doubt that machine learning has established its role in healthcare with its capabilities. From the vaunted use of machine learning in the oncological field, through its use in dealing with rare diseases, to improving Alzheimer’s diagnosis, the current and future uses of machine learning in treating illnesses are numerous.

Another important health-related use for machine learning, which also has to do with wellness, is the prevention of acute, serious episodes and exacerbation of existing conditions. A great example of this is AireHealth with their platform and device for treating chronic lung disease (unfortunately very much in vogue due to Covid-19). Their platform analyzes real-time data from the device (a nebulizer) and lung sound analysis from the connected spirometer, recommending changes in treatment or other action meant to prevent acute episodes that often lead to emergency room visits.

Predicting the Mood

When we speak of mood in terms of wellness, we need to make a distinction between the mood in the medical sense (depression, anxiety, and other mood disorders) and the colloquial mood (happy, grumpy, etc.). Both these “types” of mood play an enormous role in the overall wellness of an individual, and there have been some very interesting uses of machine learning in helping people with both.

A great example of ML application to mood disorders is a 2019 study from South Korea, in which a team used machine learning to very successfully predict different types of episodes in patients with mood disorders (especially those suffering from bipolar disorders, where accuracy was near or above 90%).

A Chinese study from 2019 utilized machine learning to speed up the diagnostic process for patients with bipolar disorder. The technology helped prevent misdiagnosis as major depressive disorder and find the right treatment more quickly. View More