Skip to content

Blog

Why Machine Learning Fails… and Why It Won’t in Home Healthcare

machine-learning

As I woke up, coffee in hand, slowly browsing Facebook, Yann LeCun, director of AI research at Facebook, shared a link to this interview of Michael I. Jordan, IEEE Fellow, Pehong Chen Distinguished Professor at the University of California, Berkeley. As the author said, Jordan is one of the world’s most respected authorities on machine learning and an astute observer of the field. http://spectrum.ieee.org/robotics/artificial-intelligence/machinelearning-maestro-michael-jordan-on-the-delusions-of-big-data-and-other-huge-engineering-efforts

Mr. Jordan states that the hype around big data and so-called brain-like models will lead to the failure of the big data era. He used a very interesting analogy to represent the state of big data today:

“I like to use the analogy of building bridges. If I have no principles, and I build thousands of bridges without any actual science, lots of them will fall down, and great disasters will occur.”

{{cta(’84e60d68-cc8d-4ecf-8082-6edad840a07e’)}}

As director of the AlayaLabs, I’ve heard my fair share of hopes and dreams about the magic of machine learning within the context of home healthcare. Even with the hype around big data…but there’s no magic there.

By leveraging well designed algorithms and the computational power of today, we are able to dig into data and uncover patterns that the human eye would have missed. But, one needs to be careful and always be skeptical of what is found. We need to apply scientific processes to make sure our models are solid and we need to understand the assumptions and risks of our models.

But we know and understand those limitations.

We believe that machine learning will play a key role in remote patient monitoring by making the care worker’s job a lot easier.

AlayaCare takes pride in developing science close to the fields. We interview practicianers to understand what they look at to detect events and use this knowledge as priors in our models.

We capture what is out there and try to improve it by leveraging the power of machine learning.

At the end of the day, by working hand in hand with the people we’re trying to help, we believe that we are building better models that will yield better outcomes for the homecare agencies and ultimately, for the patients.

So while Mr. Jordan is correct in saying building bridges without proper planning or routing results in failure, he is also noting that when you carefully plan the bridge, know where you are coming from and where you are going something incredible occurs!