NEWS! Two papers accepted to the IEEE Biomedical and Health Informatics Conference, Las Vegas, 2018!

Vast amounts of heterogeneous and complex data from Electronic Health Records (EHRs) are ubiquitously being recorded at the patient level in healthcare (“big data”). This represents a largely untapped source of data-driven clinical information having the potential to transform health by developing autonomous monitoring systems as well as diagnosis and decision support tools. This will leap forward the quality of care for the individual patient, and lead to reduced costs in healthcare.

UiT Machine Learning Group, together with our partners, aims to move the research front in deep learning and artificial intelligence for data analysis beyond the current state-of-the art. This will in this project be done within the context of ubiquitous data and services in healthcare. In particular, our research activities will focus on prediction and prevention of postoperative complications, leveraging the power of deep learning on vast amounts of readily available EHR data and clinical imagery.

See projects

Around 25% of patients who undergo high-risk operations suffer from some form of postoperative complications within 30 days of surgery, are more likely to die within five years. Assessment of the individual patient risks potentially enables early prediction and intervention and can minimize complications and hence readmissions, but is hindered by current diagnostic methods. The potential impact of leaping forward postoperative prediction and prevention by deep learning is therefore immense.

Our consortium is seeking to raise funds to increase our activities in this line of research. A technical report describing this activity can be found here: Technical report.

We are dedicated to open and transparent research. Our aim is to engage with the public at large. Feel free to contact us if you have questions about the project and our research activities.


    [recaptcha size:compact]