HIMSS19: Doctors don't know what to do with data from wearables
- Despite high levels of interest by consumers to take an active role in their health, Karl Poterack, Mayo Clinic's medical director of applied clinical informatics, is cautioning data being collected by wearables may have limited clinical applicability.
- The concern is despite the reams of data being collected, ranging from steps taken to continuous heartbeat monitoring, physicians don't know how to interpret the data. In addition, some are concerned having access to such data may expose them to new legal liabilities if an adverse event — that could have been prevented by paying attention to data precursors — occurs.
- Wearable devices that are not reviewed for accuracy from FDA, interoperability challenges to integrate wearable data with an EHR and a lack of high-quality research into the predictive value of data being collected remain key challenges to using wearable data to enable health professionals to intervene to improve the health of patients.
The key questions are whether wearable data are accurate and meaningful, and whether physicians can understand the clinical outcome implications of the data being shown to them by patients.
"If you present this data and bring in your device and say 'here I have this heart rate data from the last month' we're going to say, 'that's great, but we don't know what it really means,'" Poterack said to a HIMSS panel Thursday.
That's notable because consumers are increasingly using wearables with the goal of managing health conditions rather than to track fitness, according to a recent survey conducted by Rock Health. If doctors don't know what to do with the data being presented to them, it raises the question of the ultimate purpose of consumer wearable devices.
A significant number of consumer wearables are not reviewed by FDA, a concern to many physicians who worry about the specter of lawsuits if they examine patient wearable data.
"That's something that makes a lot of physicians really reticent and nervous about this," Poterack said. "There are a lot of places where not only does the physician say, 'I don't know what to do with this data,' they say, 'I don't want this data because I don't want to be potentially held responsible for having data from something.'"
Poterack pointed to a literature review examining whether wearable technology has predictive value. The JAMIA study found only eight instances of medium-to-high quality studies that used wearable data in predictive models.
"Given the small number of studies, we can only speculate on the utility of wearable technology for predicting clinical outcomes. However, there are several promising findings from this review that suggest that further research on wearable technology for predicting clinical outcomes is needed," the study states.
One challenge is that wearables data are siloed apart from patient outcome data, making research challenging. Funding is also a concern. Because people are unsure of the clinical usefulness of the data, institutions are less likely to fund research. It is, Poterack said, a chicken and egg problem.
"The vendors have the data. Hospitals, healthcare systems, physicians, we've got the patient outcome data. If we can sort of find a way to use existing infrastructure, link up the device data with outcome data, we can start developing some of these use cases," Poterack said.
Follow David Lim on Twitter