Digital devices for collecting patient data — from connected blood pressure monitors to Ginger.io's voice analysis software — are creating a new category of medical data, digital biomarkers. According to a new report from Rock Health, these biomarkers have the potential to deliver new health insights, but there are challenges to incorporating these biomarkers into the existing efficacy landscape.
The report discusses how digital data collection simplifies and reduces the cost of large longitudinal studies, while also adding a new element of personal data collection that individuals in the study can benefit from.
“Digital biomarkers offer a cost-effective opportunity to extend the collection of population level health data over time and introduce longitudinal data for individual consumers,” the report authors write. “Through passive and continuous monitoring, it becomes possible to collect real-world data over extended periods of time. This data can be used to guide an individual’s care or it can be combined with data from other individuals to enable more precise population health management.”
Digital biomarkers have other advantages. Services like Ginger.io, which use voice and behavior analysis to predict mental health status, could eventually provide more objective measures of health metrics that have traditionally been subjective. Digital biomarkers are easier to integrate with one another than traditional biomarkers, which can be helpful in common situations where a panel of data points is more predictive than any data point in isolation. And digital data collection allows continuous data about an intervention to be collected, even after a patient left the lab. Finally, digital biomarkers enhance the role of the consumer in managing his or her own health.
So what challenges will digital biomarkers face? Well, for one thing, it’s not a foregone conclusion that more data is better. For instance, continuous data on something like blood pressure could bring new insights, but it could also bring noisy data. So the biomarkers themselves will need to be validated before they can be used to validate anything else. And this might be more complicated than it sounds.
“Traditional clinical trials regard double-blinded, randomized controlled trials as the gold standard,” the report says. “However, given the consumer-centric nature of digital biomarkers, this may create biases. For example, the act of tracking a metric inherently changes patient behavior and outcomes, which may skew the population set for digital biomarkers. Therefore, there is a need to consider alternative validation strategies for digital biomarkers.”
And of course, for these biomarkers to be useful, standards will have to emerge about how this data is collected and used, and consistent and meaningful infrastructures will have to emerge for storing the data such that it can be easily accessed and compared to other biomarkers.
“Standardization of how data is stored, labeled, and tagged allows for more than just the ability to process exchanged information -- it provides context around each data point,” the report adds. “For instance, in HealthKit, individuals enter glucose readings without denoting if they were taken after fasting versus after a meal.”