If a new study is correct, physicians trying to gauge whether or not you are depressed may soon be interested in having a close look at your Instagram posts (1). Because they reveal a great deal about behavior, Instagram posts and possibly other social media activities may turn out to be invaluable databases for mental health care practitioners.
The ability to sift through large aggregates of digital information has given epidemiologists new power to discover influenza epidemics as they emerge (2). Predictive analytics based on marketing data can already offer retailers amazing – and profitable – insights into the needs of their customers (3). Recognizing the potential, health care professionals have adopted social media to facilitate communication with patients (4), although the potential diagnostic power of these tools remains largely untapped.
Could we reach a point where computer analyses of Instagram posts become an important addition to the standard methods for diagnosing depression? Nothing is certain yet, but perhaps this tantalizing prospect will remind predictive analytics scientists that the time is ripe for burgeoning digital information troves to make important contributions to medicine. For example, the pathological changes of Alzheimer’s disease (AD) are thought to develop silently years before clinical signs and symptoms of dementia become obvious. However, a retrospective analysis of the published works of author Iris Murdoch reveal the probable imprint of AD before she received a formal, and ultimately pathology-confirmed, diagnosis (5, 6). This is where Google data scientists might now make a seminal contribution by analyzing written communications such as e-mails and assessing how they may have changed over time to identify the early linguistic signals that flag future AD.
Analyses of Gmail might achieve something well beyond the current capabilities of medical science – recognizing young subjects at high risk for AD decades before even subtle signs of dementia begin. A detailed study of women in religious orders revealed that the writing style and content of autobiographical essays written when they first entered their vocation predicted the individuals most likely to be afflicted with AD at the end of their lives (7, 8, 9). Advance knowledge may enable at-risk persons to alter diet and other behaviors to mitigate the threat. If the conclusions of the Religious Order study are correct it gives us hope that although writings might reveal AD risk, the final outcome is not necessarily etched in stone.
What you say and how you say it online have important health implications. It is time to harness the healing power of social media and digital communications.
(1) N. Chokshi. 2017. Your Instagram Posts May Hold Clues to Your Mental Health. The New York Times, 10 August 2017. https://nyti.ms/2uJePdQ
(2) G. Eysenbach. 2006. Infodemiology: Tracking Flu-related Searches on the Web for Syndromic Surveillance. Proceedings of the American Medical Informatics Association (AMIA) Symposium 2006; 244-248 http://www.webcitation.org/5LIlQNbDQ
(3) C. Duhigg. 2012. How Companies Learn Your Secrets. The New York Times Magazine, 16 February 2012. http://www.nytimes.com/2012/02/19/magazine/shopping-habits.html
(4) D. R. George et al. Dangers and Opportunities for Social Media in Medicine. Clinical Obstetrics and Gynecology 56(3):453-462. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3863578/
(5) P. Garrad et al. 2004. The Effects of Very Early Alzheimer’s Disease on the Characteristics of Writing by a Renowned Author. Brain 128(2);250-260. http://brain.oxfordjournals.org/content/128/2/250
(6) R. Highfield. 2004. Decline of Iris Murdoch… in her own words. The Telegraph, 1 December 2004. http://www.telegraph.co.uk/news/uknews/1477906/Decline-of-Iris-Murdoch…-in-her-own-words.html
(7) D. A. Snowdon et al. 1996. Linguistic ability in early life and cognitive function and Alzheimer’s disease in late life: Findings from the Nun Study. Journal of the American Medical Association 275:528–532.
(8) P. Belluck. 2001. Nuns Offer Clues to Alzheimer’s and Aging. The New York Times, 7 May 2001. http://www.nytimes.com/2001/05/07/us/nuns-offer-clues-to-alzheimer-s-and-aging.html
(9) J. A. Mortimer et al. 2005. Very Early Detection of Alzheimer Neuropathology and the Role of Brain Reserve in Modifying Its Clinical Expression. Journal of Geriatric Psychiatry and Neurology 18(44):218-223. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1405917/