Ginger.io: Putting the Patient-Provider connection at the center

A tool for outreach to patients produces unexpected benefits

This posting was written by guest author Julia Bernstein of Ginger.io. Ginger.io’s CEO Anmol Madan will be speaking on this topic at Strata Rx.

The traditional, office-based model for health care is episodic. The provider-patient relationship exists almost completely within the walls of the exam room, with little or no follow-up between visits. Data is primarily episodic as well, based on blood pressure reading done at a specific time or surveys administered there and then, with little collected out of the office. And even the existing data collection tools—paper diaries or clunky meters—are focused more on storing data that on connecting the patient and provider through that data in real time.

There is no way to get in touch when, for instance, a patient’s blood sugar starts varying wildly or pain levels change. The provider often depends on the patient reaching out to them. And even when a provider does put into place an outreach protocol, it is usually very crude, based on a general approach to managing a population as opposed to an understanding of a patient. The end result is a system that, while doing its best within a difficult setting, is by default reactive instead of proactive.

From episodic to continuous care

How do we eliminate the walls of the clinic? The many new sources of “big data” provide a way to gather previously untrackable information. The four billion mobile phones on the planet are powerful social sensors. As citizens of the information age, we leave behind digital traces of our behavior in our communication and movement patterns. As part of his PhD research at the MIT Media lab, Ginger.io co-founder and CEO Anmol Madan spent a year following MIT students to understand what we could do with this smartphone data. Ginger.io came out of his research, as a way to use that data to improve how we deliver care.

The Ginger.io system works by collecting two types of information from individuals using a smartphone app: self-reported data through surveys linked to specific medical conditions, and passive data from the phone’s sensors (e.g., mobility, call duration). Our system then crunches this data together to find behavior patterns suggesting that something has changed for a patient. We close the loop by providing alerts about the change back to a clinician who can reach out and intervene (Figure 1–click image to enlarge it).

How data moves through Ginger.io

Figure 1. How data moves through Ginger.io

The initial version of Ginger.io was focused on closing the loop between those doing researchers and their subjects. This service, particularly the web-based provider dashboard that we launched about a year ago, was very research-focused. It looked at who was sending data, who was filling out surveys, and how much information was being collected.

As we talked to our partners, both in research and in healthcare, we realized that while our technology was well-suited to improving clinical trial data collection, its real magic lay in our ability to change how healthcare is delivered today. With real time data, we could address the episodic care conundrum, and find new ways to connect patients and providers outside of office visits.

A data-driven patient-provider relationship

With this new focus on the patient-provider connection, we have been actively redesigning our product to put that very important relationship at the center. Now, clinicians can use our dashboard to see how each of their individual patients is doing: survey responses, sensor data, and alerts when something isn’t going right. These are the tools a clinician needs to have a better conversation with a patient when it matters most—and to make that conversation about more than just a routine check-in, but about something that’s real.

We asked Peter Smith, Ginger.io Customer Champion, what he’s learned from our providers and individual partners about designing a system that uses technology to enhance relationships. He told us, “It’s really about building tools where both patient and provider feel they are working together towards a shared goal.” Pete’s perspective is based on his experience implementing the system with a number of our partners, including Novant Health in North Carolina, targeting at-risk people living with diabetes, and Kaiser San Diego, where we are helping a clinical team better manage depression in a population of chronically ill patients.

For these deployments, Pete and the team have spent a lot of time getting both our clinical partners and the patients using our system excited about the work we’re doing. In both cases, we found that essential to our “pitch” was the clear communication of the value to the person on the other side of the data exchange. Clinicians needed to see that their patients would be getting value in terms of a closer connection and better care. Conversely, patients needed to understand how much their care teams could do with new, real time information.

As we continue to build, we are thinking through more ways to put the patient-provider relationship front and center, and communicate its value. For instance, we’re experimenting with health tips that include both educational content as well as messages from the provider to the patient. We’re also thinking through other important relationships that we can enhance, like patient and supporter. We’re excited to use data to put relationships first, and to see how we can continue to improve care.

tags: , , , , , , , , , , ,

Get the O’Reilly Data Newsletter

Stay informed. Receive weekly insight from industry insiders.