Neural network

Neural Network Reduces False Positives in CAD

Using an advanced massive-training artificial neural network (MTANN), computer-aided detection (CAD) scheme, radiologists were able to improve their polyp detection rate and reduce the number of false positives in CT colonography (CTC), based on a study presented at the 2009 Radiological Society of North America (RSNA) annual conference in Chicago. Kenji Suzuki, PhD, assistant professor [...]

Releasing Early Results – Predicting Hypotension

Today Avantrasara released some early results from the Avert-IT research project, showing the Bayesian Artificial Neural Network anticipating hypotensive episodes. It’s far too early to suggest these results prove anything but they are showing what we expected – which is very encouraging. The graphic on the right shows monitored BPm for a patient in intensive [...]

Open Source Bayesian Artificial Neural Network

Could you be interested in using Bayesian Artificial Neural Network software? If so let us know. Part of our research required us to build a BANN to research a large amount of patient parameter data – all minute by minute readings from monitoring equipment. Next up for us is building a prediction engine based on [...]

New Clinical Care Research Hub

Our Avantrasara plans are building nicely, with real time monitoring showing encouraging signs of prediction based on statistical modeling and pattern recognition. The scientists tell me not to use the phrase Bayesian Artificial Neural Network.  Apparently it’s received bad press in the past with spectacular failures in financial markets.

Emergence of a Unique Resource

Clinicians lead developments in health care sciences through a proven process of discovery, publication, peer review and dissemination.  The fundamental concepts enabling this process are collaboration and sharing.

Just What Is Prediction

When it comes to forecasting the future we can get into hot water in a hurry.  After all no two economists can agree on anything, I’m told.  The collapse in financial markets recently seems to bear that out! Forecasting seems to be an especially risky activity when the results challenge accepted thinking.  Highly qualified scientists [...]

Interim Report on Prediction Success

As part of our project review, September 30th, Rob Donald presented a report on the results of his research with the Bayesian Neural Network. For us mere mortals the concept really isn’t easy to understand, but Rob found an excellent way to illustrate how the BANN works. It went something like this: Take a full [...]

Identifying Parameters Indicating Hypotension

On June 27th Rob published to partners a report on his finding during the Work Pack 1 research.  This is a summary of the report.

Associated Parameter Selection – by Rob Donald

Abstract This discussion paper gives an description of the techniques that will be used to identify the associated parameters to be included in the Bayesian Artificial Neural Network (BANN) train- ing database.

Clicky Web Analytics