1 code implementation • 28 Dec 2021 • Miroslav Fil, Munib Mesinovic, Matthew Morris, Jonas Wildberger
$\beta$-VAE is a follow-up technique to variational autoencoders that proposes special weighting of the KL divergence term in the VAE loss to obtain disentangled representations.
no code implementations • 10 May 2023 • Munib Mesinovic, Peter Watkinson, Tingting Zhu
Heart attack remain one of the greatest contributors to mortality in the United States and globally.
no code implementations • 18 May 2023 • Munib Mesinovic, Xin Ci Wong, Giri Shan Rajahram, Barbara Wanjiru Citarella, Kalaiarasu M. Peariasamy, Frank van Someren Greve, Piero Olliaro, Laura Merson, Lei Clifton, Christiana Kartsonaki, ISARIC Characterisation Group
Using a dataset of more than 800, 000 COVID-19 patients from an international cohort, we propose a cost-sensitive gradient-boosted machine learning model that predicts occurrence of PE and death at admission.
no code implementations • 16 Aug 2023 • Munib Mesinovic, Peter Watkinson, Tingting Zhu
To ensure trust and reliability in AI systems, especially in clinical risk prediction models, explainability becomes crucial.
no code implementations • 28 Oct 2023 • Munib Mesinovic, Peter Watkinson, Tingting Zhu
Survival analysis focuses on estimating time-to-event distributions which can help in dynamic risk prediction in healthcare.