In an age where the collection of data is accelerating at unprecedented rates, the ways in which we use these data are as diverse as the devices used to collect them. The ubiquity of smartphone devices has allowed anyone with an iPhone to conduct a longitudinal case study of their own aging. In the field of gerontology, the capacity to track a variety of behaviors in great breadth and depth over an extended period presents an excellent research opportunity; however, with great (statistical) power comes great responsibility.
Recently, my colleagues and I have written about the challenges and opportunities of using mobile devices as data collection mechanisms amongst older adults. As we noted, the digital divides that impeded the integration of these devices into older adults’ lives, with respect to uptake and usage, have been an inhibitory force in the use of these data by researchers. If we are unable to collect data in the first place, any potential research prospects are over before they have begun. Further, data-driven analytical methods are subject to the “garbage in: garbage out” principle: if your data have not been collected in a representative manner or in an accurate way, your findings will reflect these shortcomings in their relevance and applicability. Therefore, in order to be able to draw meaningful conclusions from these data we must ensure that they are reliable and valid. Assuming for a moment, that we have overcome these data collection challenges, we enter an entirely new realm of possibilities (and potential problems).
Precision medicine is an emerging approach in the health sciences, taking into account individual biopsychosocial variability in the diagnosis, treatment and prevention of illness. This approach was popularized in the mainstream media by President Barack Obama and his Precision Medicine Initiative. In his 2015 State of the Union address, Obama discussed some of the advantages of this approach, concisely captured in the Initiative’s mission statement: “To enable a new era of medicine through research, technology, and policies that empower patients, researchers, and providers to work together toward development of individualized care.” At its core, precision medicine utilizes big data approaches to develop individualized recommendations for the prevention and treatment of diseases.
The Precision Medicine Initiative, alongside other large-scale investments of grant funding and industry, has enabled the field to expand very rapidly. Subfields such as precision oncology and precision cardiology have seen game-changing advances from this computational approach. Cancer treatment can be tailored in a more sophisticated and individualized manner than was previously possible and major innovations in the treatment of cardiovascular disease are now being tested and implemented. However, not every field has fully realized the potential benefits afforded by this innovative approach.
Precision Mental Health
“Precision mental health” aims to apply the principles of precision medicine, i.e. taking into consideration individual variation in disease onset and treatment, to the study of psychopathology. Studying mental health amongst older adults using traditional means is challenging, due in part to the complex interrelationships between physical and psychological comorbidities that may obscure underlying mental illness, for example many of the symptoms of depression, such as decreasing interest in activities, may be mistaken for symptoms of age-related decreases in physical or cognitive functioning. In order to address these complex interrelationships, analytical procedures with computational sophistication that go above and beyond traditional epidemiological frameworks may provide possible solutions. The computational capacity of precision medicine approaches applied to the study of mental health has shown great promise, with some researchers even suggesting that this field “promises to be even more transformative than in other fields of medicine that have already lessened the translational gap”.
My perspective on the uptake of technological and analytical innovations in research contexts is a balance of optimism and skepticism; precision mental health is no different. On one hand, I think that new approaches to old problems may provide insights that could not otherwise be gleaned. On the other, I am increasingly wary of “black box big data” approaches and spurious correlations identified through unsupervised learning. To avoid these sorts of issues, I think that innovations should be viewed as one of many tools in the toolbox, rather than the tool. Further, the input from relevant persons, e.g. researchers, clinicians, and stakeholders, should be the primary driving research force and that these innovations should be used as a supplement to their expertise.
The collection of behavioral data from older adults’ does not appear to be slowing down nor does the scope of application and analysis of this information. Precision medicine is an exciting approach to the analysis of these data, providing personalized insights into the diagnosis and treatment of a variety of disorders. Although mental health is an increasingly important area of research, the field of “precision mental health” has lagged behind its more biomedical peers, e.g. precision oncology. There is great promise in being able to use these computational approaches to the study of psychological phenomena amongst older adults; however, we must be cognizant of the limitations of these new approaches in the integration of old and new. Whilst precision mental health may not have all the answers, I think that having increasingly sophisticated means of generating and testing hypotheses is bringing us ever closer to a better approximation of what those answers might look like.
About the Author
Theodore D Cosco joined the Oxford Institute of Population Ageing in 2016 as a Research Fellow. He holds a Canadian Institutes of Health Research Postdoctoral Fellowship to conduct a project entitled “Resilience and healthy ageing across the life course” in conjunction with the MRC Unit for Lifelong Health & Ageing.
We welcome your comments on this or any of the Institute's blog posts. Please feel free to email comments to be posted on your behalf to firstname.lastname@example.org or use the Disqus facility linked below.
Opinions of the blogger is their own and not endorsed by the Institute
Comments Welcome: We welcome your comments on this or any of the Institute's blog posts. Please feel free to email comments to be posted on your behalf to email@example.com or use the Disqus facility linked below.