Digital tracking has become increasingly popular in a wide range of health domains, but new research from the University of Bath argues that while these may have merits in many areas, we should be cautious about deploying it where mental health is concerned.

The method, known as “digital phenotyping”, uses the digital information given off by our phones alongside medical data and survey information from the patients during the day to provide insight into their mental wellbeing.

The paper accepts that the method has considerable potential, but that many of the more enthusiastic claims to date lack rigorous evidence to support them.  For instance, a fall in smartphone-based communication might be a sign of social withdrawal for one person, but for another, it may simply mean that communication has shifted to face-to-face instead.

“There are serious ethical questions due to the intrusive nature of having all digital interactions recorded,” the researchers explain. “We do not yet know the impact of continuous monitoring on people, yet alone those with severe psychiatric illness such as schizophrenia, bipolar, and various depressive disorders, commonly seen in current research samples.”

Ethical concerns

The paper also highlights some ethical concerns around the use of data and maintenance of privacy, especially when the sensitive data from our devices are combined with health information.  The authors argue that professional bodies will produce guidelines on appropriate data governance.

There are also clear comparisons with the use of fitness data by medical insurance companies, where the paper argues that people don’t always understand the implications of the data they’re sharing.  For instance, they cite examples of people forgetting to wear their device and invalidating their insurance because their activity levels drop.

“As the majority of the population now owns a smartphone, digital phenotyping could help to reduce digital and health inequalities as this can allow additional touchpoints for those who might use healthcare services less,” the authors conclude. “However, the research remains in its infancy and requires a series of difficult questions to pave the future of digital medicine.”