Anticipating Hypotensive Episodes in ICU

Year 2 Project Review – Vilnius September 2009

September 22, 2009

Over the weekend we had a chance to get the whole team together and review our progress.

Vilnius isn’t the easiest place to get to, for most of us at least, which helps us understand how difficult it can be for Arminas to join us in other parts of Europe.

But the real benefit of his hosting the meeting was we all got to experience Vilnius, a really interesting city in glorious autumn sunshine.

Rightly, the tourism was a side show to the main event – our project review.

The old town is steeped in history, full of character and a lot of fun. Lithuanian cuisine offers an exciting blend of gourmet and country cooking and there are dozens of quality restaurants where it can be enjoyed.

We aren’t ready to announce results to the world at large yet, but can confirm we’re heading in the right direction. We already have minute by minute parameter data collecting from multiple, international, sites and we are predicting upcoming hypotensive events.

Quite how we’re doing this is, for the moment, understood only by some very special people. Bayesian Artificial Neural Network technology is designed to find out stuff the human brain can’t cope with and in our case it is.

The project is still a year away from sharing its results, during which time some other very special people, will be managing the clinical trial.

BANN technology has received some bad press over the years, mostly because applications in financial trading disappointed.

In this project the technology is delivering on our expectations. That doesn’t mean it’s telling us what we want to hear, just telling us what it finds, and that’s what we want to hear.

Hypotension (sudden drop in blood pressure) is frequently experienced by patients in intensive care. Impacts are reduced quality of outcomes and extended lengths of stay, and that’s just the lucky patients.

Just to be clear – we aren’t diagnosing. We are offering clinicians an early warning of upcoming episodes, giving them a chance to get ready to intervene in line with their usual practice.

Ultimately the results of the project will help researchers understand how and why hypotensive episodes occur.

Reblog this post [with Zemanta]
This entry was posted in Uncategorized and tagged , , , , , , , , , . Bookmark the permalink.

3 Responses to Anticipating Hypotensive Episodes in ICU

  1. Pingback: Tweets that mention Avoiding Hypotension Intensive Care | Avantrasara --

  2. Pingback: Improving Patient Safety with Neural Networks | Widespread Solutions

  3. Pingback: Improving Patient Safety with Neural Networks | Avantrasara

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s