[visionlist] Hackathon on covid-19 prognosis from images and clinical data

Pavis Pavis at iit.it
Fri Jan 14 08:21:13 -05 2022

The 2nd Covid CXR Hackathon - Artificial Intelligence for Covid-19 prognosis - will start February 1 2022 with an official lunch at the Dubai Expo 2020 during a joint event on AI for health endorsed by the Italian and Israeli governments.

The Covid CXR Hackathon challenges the participants to implement and deploy machine learning based solution to aid the Covid-19 prognosis from early chest X-rays and clinical data. One of the main challenges of this hackathon will be the need for processing real-world data collected from several different structures upon first hospitalization in near-emergency conditions during the first outbreak in Northern Italy.
Hence, image quality (and format) is highly variable and clinical data, despite best intentions, is incomplete. Therefore, any developed approach will have to deal with missing data. This hackathon aims at finding solutions relying on both sets of data, with a heavy emphasis on image analysis and algorithm explainability, as deploying machine learning techniques in a clinical setting requires ease of understanding by medical personnel.

The participants are expected to find and submit solutions; the submissions will be evaluated on performance as well as explainability by a panel of clinician and computer scientists. Prizes will be available for the best performing teams, subject to the open source release of their technique.

More information about the hackathon registration and schedule will be available soon at this webpage:


The event is endorsed by ELLIS Genoa and Modena units, the Italian Institute of Technology (IIT), Fondazione Bruno Kessler (FBK). For any information please email: info at ai4covid-hackathon.it

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20220114/6d194284/attachment.html>

More information about the visionlist mailing list