Doesn't All This Patient Data Overwhelm Doctors?

Read Transcript

The way we think about analytics, and this is where big data comes in, in fact I think in five years the value of the data we're collecting and the information we can extract from it will probably outweigh the value of the application itself. So, what is data for us? Think of a two by two where you have the presence or absence of data and in this dimension you have, I know what I want to do with the data and I don't know what I want to do with the data, so play it out.

This quadrant here, I have data and I know what I want to do, that's what we call descriptive data, it's a report. Show me the percentage of times the patient was compliant, show me the percentage of times they tested before breakfast dropped and breakfast it's reporting 101. I know what I want to do but I don't have the data, this is the realm of predictive modelling.

So we're now working on prototypes for example to predict within the three hour window if the patient is going to go glycemic. Imagine the power of that, right? You're going to thwart them from going away to the ER which is a great thing. This dimension is interesting, says, I have data but I don't know what I'm looking for, that's a whole lot of a pattern recognition.

Can I learn something from that data and of course we call this last quadrant adaptive. This is perhaps the Star Trek that says, hey I don't have data and I don't know what I'm looking for, but can I watch the patient over time and evolve. So for example, messaging. If a patient is naive to insulin, you want to hand hold them.

But you don't want to hand hold them after a year, they'll get tired of the hand holding messages. So you want to grow with them. So analytics play that role, not just for the patient, analytics play that role for the doctor. The example we always use is, the space shuttle is a very complex instrument, and it's flown by a computer.

Yes there's a human pilot, but it's really flown by a computer because there's too many inter variable interactions. It's the same with a complex disease like diabetes. And why do we entrust it just to a human being who may have had 6-10 hours or 6-10 weeks of training in med school on diabetes, right? And so if we can actually have a system to help them.

They actually value it.