Population health & cognitive computing: 4 insights from IBM Watson Health's Dr. Anil Jain

Since the formation of IBM Watson Health in April 2015, IBM's cognitive computing healthcare business unit has only grown. Following the launch of the Watson Health Cloud, IBM Watson Health acquired population health management software provider Phytel and cloud-based integration solution provider Explorys. IBM also acquired Merge Healthcare for $1 billion, and just last week closed the $2.6 billion acquisition of Truven Health Analytics.

The combination of these companies creates a data, analytics and cognitive computing powerhouse. Anil Jain, MD, senior vice president and CMO of Explorys and vice president with Watson Health, describes how the power of data can be harnessed to bring insights to practicing clinicians and support the ambitious goals of population health.

Editor's note: The interview has been lightly edited for clarity and concision.

Question: What do you think are the biggest challenges and opportunities associated with the significant influx of data in healthcare?  

Dr. Anil Jain: It is not just the sheer amount of data, but also the types of data. There is the clinical data you typically think of, but also claims data. Now, wearables are generating exogenous data. It is now the volume, variety and velocity. Caregivers are making decisions in real time.

The biggest challenges relate to the interoperability of data and then standardizing and cleansing the data. Just because you can get the data, that does not mean you can make sense of it. Then it comes down to appropriately using all data available.

As we get better at understanding patterns in the data, we are going to be able to account for any noise in the data. Watson Health has a clinical data set with millions of data points. When you have those numbers, any noise in that data can be smoothed out. If you have a large enough sample size, you can draw out patterns, which can be tested on smaller groups. The capabilities of predictive analytics allow you to get as close to the dart board as you need to be.  

Q: What role do you think the Watson Health Cloud has to play in population health?

AJ: I think it is a perfect fit. Explorys and Phytel, which were acquired by IBM Watson, were in the population health space. This combination is the poster child for bringing data together, cleaning it up and making rich analytic models. Combine that with the cognitive computing capabilities of IBM, [and] Watson Health becomes the perfect vehicle [for population health] in many ways. You can find the best course of action for each and every case.

Q: How can providers use all the capabilities the Watson Cloud offers in their practices?

AJ: Fortunately, when Watson Health was launched back in April 2015, Explorys and Phytel already had a set of solutions that allowed them to take advantage of the cloud. These solutions are already being used across dozens of health systems. The Watson Cloud is just an extension. Over time, we will have the ability to drive even further into the most complex of cases.

Now, we are aiming to make sure complex patients across the country who are running out of traditional therapy options are matched with clinical trials through the Watson Clinical Trial.

Q: How will cognitive computing capabilities in healthcare evolve over the next few years?

AJ: A couple of years from now, most clinicians managing patient populations will expect a few things from Watson Health. They will expect all patients to be risk-stratified. How sick are they? How sick will they get? Evidence included in the literature, the full spectrum of a patient's clinical data and any exogenous data will be accounted for and used to stratify the patient to ensure the right care resources are being delivered.

Physicians will expect to be able to connect with all colleagues in their community who are using Watson, even if they use different EHRs. Clinicians will come to expect a complete longitudinal health record, not just what is written in the chart, but what is hidden between the lines. Our system needs to see this and ask clinicians to verify. Cognitive population health solutions will put these abilities in their hands in a few years.  

Copyright © 2024 Becker's Healthcare. All Rights Reserved. Privacy Policy. Cookie Policy. Linking and Reprinting Policy.


Featured Whitepapers

Featured Webinars