The COVID-19 pandemic has accelerated our integration of technology into our everyday lives — whether for personal or work use, there's probably not a day that goes by where you haven't found a way to integrate it to improve your quality of life. I can't imagine a day where I'm not using my phone to talk with others, my laptop to do work, or an app to facilitate digital transactions. Technology has also made it possible to conduct appointments remotely through the telehealth network, or through remote administration of various tests and questionnaires.
However, there are places where we can accelerate the use of technology, as well as machine learning, to improve diagnostic accuracy and treatment trajectory in psychiatry. Perhaps by shying away from the tried-and-true method of "trial and error," there may be an opportunity to shift our focus and invest in precision-based medicine.
Indeed, the neurobiology of psychiatric illnesses is not a "one size fits all" scenario, and in fact, it is heterogenous, diverse, and variable and nature — simply because the brain, our behavior, and the external factors that influence these variables are dynamic. As a result of these highly complex systems, which can be characterized as a composition of nonlinear, multiplicative, cascading effects, there is a need to identify solutions that can process these complex processes and produce precise and action output.
Current medications and therapeutics may only be effective for certain subgroups of individuals, thus referring to the "tried and true" method. That's not to invalidate the current treatments available, but instead to offer another solution to enhance the treatment decision process. In other words, perhaps there is an opportunity to incorporate deep learning to process these complex datasets.
If we can understand the complex neurobiological mechanisms that underlie the various psychiatric disorders, then we can start to identify diagnostic biomarkers and shared disease markers, which can help inform our understanding of different therapeutic response profiles. This information may form the basis for precision-based therapeutic interventions at the individual level. In order to achieve this objective, we would need large and powerful datasets, which could be obtained, for example, from electronic health record databases, social media platforms, and ecological momentary assessment, among other sources.
A couple of years ago, I conducted a narrative review looking at the use of ecological momentary assessment to assess depressive symptoms. We found that passive smartphone-based applications may help assess depressive symptoms; however, at the time, this area was still nascent and underdeveloped. Now that time has passed and we are on a much faster technology growth phase, I think it would be prudent to revisit these tools (eg, for diagnostic accuracy and treatment profiling).
For example, data that could be collected from ecological momentary assessment may include physical activity, sleep quality, phone use, social media use, and GPS information. As such, these measures of physical and social activity may act as a proxy for understanding the individual. However, integrating these kinds of data may be associated with certain privacy, monitoring and confidentiality concerns.
Taken together, there is considerable potential to integrate machine learning into psychiatric care and also accelerate research and precision-based medicine in psychiatry.
Join Medscape's new blog initiative! We're looking for physicians, nurses, PAs, specialists, and other healthcare professionals who are willing to share their expertise in one to two paid blog posts per month. Please email Medscape-Blogs@webmd.net for more information.
Follow Medscape on Facebook, Twitter, Instagram, and YouTube
© 2022 WebMD, LLC
Any views expressed above are the author's own and do not necessarily reflect the views of WebMD or Medscape.
Cite this: Leanna M.W. Lui. Paving the Way for Machine Learning in Psychiatry - Medscape - Feb 14, 2022.
Comments