The Internet of Things, event stream processing and wearable devices such as Apple Watch and FitBit, just to name a few, all have massive potential to meaningfully contribute to the broader health care world. They accomplish this by transmitting personal health data in near-real time in support of potential diagnosis and treatments scenarios aligned with what we understand as eHealth, but there are many challenges.
Here are three of many examples that help you understand the practical implications of this trend. In the first, we are introduced to Apple HealthKit:
"With HealthKit, developers can make their apps even more useful by allowing them to access your health data, too. And you choose what you want shared. For example, you can allow the data from your blood pressure app to be automatically shared with your doctor. Or allow your nutrition app to tell your fitness apps how many calories you consume each day. When your health and fitness apps work together, they become more powerful. And you might, too."
Under Armour takes a slightly different perspective, they are embedding their clothing and fitness gear with sensors to create “the ultimate performance and health app.”
And, finally, a real-world example of the potential of all of this technology to save lives:
“Paul Houle, a 17-year old who plays nose tackle for the Tabor Academy football team, credits his brand new Apple Watch for saving his life. Houle had just wrapped up a practice session when he started feeling pain in his chest and back. Using his Apple Watch, he discovered that he had a heart rate of 145 for two hours after practice ended. After calling his trainer, Houle's heart rate was checked manually, resulting in an immediate visit to the hospital.
Houle was diagnosed with rhabdomyolysis, a condition that results when heavy exercise leads muscle cells to leak enzymes and proteins. Rhabdo can lead to kidney failure and death.”
We are experiencing explosive growth of individuals using commercially available personal health monitoring devices, which are able to exchange data with a variety of connected software and hardware platforms. As those data become available for analysis, as part of an ever changing and personal “digital health picture”, it is inevitable that information will make their way into more formal data streams that clinicians use to diagnose and treat ailments.
This situation presents a significant amount of risk to individuals and institutions that are interested in using these devices and data to make health care decisions at the personal and population levels. More importantly, the challenge of embedding into these devices a level of intelligence so that clinically risky or dangerous readings will appropriately alert the individual and/or the clinician, without that alert being ignored (alert fatigue), is a profound and untested challenge.
As the Internet of Things becomes omnipresent and the concept of eHealth an everyday reality, the problem of alert fatigue will grow geometrically and the distinction between data collected, transmitted and processed from clinically validated systems to personal, consumer devices will be difficult to distinguish.
Today, consumers and clinicians are at risk for not noticing or ignoring alarms and alerts generated by IoT connected devices that may lead to injury or death. For SAS, this represents an opportunity to develop embedded, in-line analytic processes that facilitate the use of streaming data quality functionality as well as advanced analytics to develop intelligent, proactive and learning alert systems. Paraphrasing a well-known marketing slogan, “SAS may not make IoT devices but, we make the data they generate better”. And SAS is beginning to do just that.