What does a mountaineer have in common with an ailing heart failure patient? Until recently, very little. Even their respective access to medical-grade, “wearable” sensors differed.
Although logic would dictate such devices were reserved primarily for the chronically ill patients who needed them most, the reality is that cost prevented such a wide distribution across the millions who suffer from chronic diseases.
To date, these types of biosensors have largely been available only to elite athletes for use in improving their performance at various extreme sports, such as high-altitude climbing. As a mountaineer myself—and a physician—I’ve repeatedly wondered over the years when a variation of the technology would advance to help the millions worldwide who live, often very painfully, with chronic diseases such as heart failure, COPD and diabetes. And finally, it would seem that time has arrived.
With the popularity of Fitbit and other wearable fitness monitors, we’ve seen orders-of-magnitude improvements in the affordability and precision of wearable biosensors. Tiny stick-on cardiac monitors that once cost tens of thousands of dollars, now sell for tens of dollars and deliver far broader types of clinical grade data, wirelessly.
That’s one half of the challenge solved.
As for the other—taming the vast streams of data the devices generate—a solution for that is now on the horizon, too. And it’s one that enables any clinician to recognize clear signals from the data that a patient is headed for trouble and needs help now to avoid an ER visit.
Here’s how it works. Using a hybrid approach to analytics that combines natural language authoring with artificial intelligence, coined “Human Augmented Machine Learning,” clinicians can build the clinical rules or models that trigger alerts, without needing to bring in IT professionals to write computer code.
These models analyze any number of patient-personalized rules in real time to trigger alerts when an anomaly occurs. For example, a clinician can tell the system to “alert a care manager when a patient’s blood pressure rises more than 5%, over three consecutive reliable recordings above the patient's baseline levels, from a moving average of the last five days.”
Adding to the system’s agility, it continually learns about which rules and interventions worked best for which patient. This is accomplished using another novel concept called “Adaptive Physiological Modeling” that lets the system learn from patient data and case manager feedback, and improve its accuracy and reduce false alerts.
For instance, if a case manager reports that an alert was a false positive, the system uses machine learning techniques to immediately recommend adaptations to the physiological model to correct the problem.
My hope is that we can use these technologies to eliminate all avoidable hospitalization and solve the trillion-dollar problem of chronic disease that is crippling our nation’s health and economy.
A grand challenge, yes, but given the astonishing advances in wearable technology and analytics, one grounded in reality. Certainly in the more immediate future, this approach marks a significant paradigm shift in healthcare, potentially enabling the limited number of disease management professionals across the country to easily monitor, and manage, millions of patients at a time.
Already the technology is being tested in controlled studies with thousands of COPD, CHF, cancer and frail patients. We still have a climb ahead of us, but for the first time, the summit is clearly in sight.
Jack Kreindler, MD is chairman, chief medical officer and founder of Sentrian, the Remote Patient Intelligence™ company. Also the founder of London’s Center for Health and Human Performance, Kreindler lectures internationally on the future of medicine and is a guest expert presenter for CNBC, Sky Sport, BT Sport and the BBC.