Detecting Patterns of Physiological Response to Hemodynamic Stress via Unsupervised Deep Learning

no code implementations • 12 Nov 2019 • Chufan Gao, Fabian Falck, Mononito Goswami, Anthony Wertz, Michael R. Pinsky, Artur Dubrawski

By analyzing the clusters of latent embeddings and visualizing them over time, we hypothesize that the clusters correspond to the physiological response patterns that match physicians' intuition.

BIG-bench Machine Learning Survival Prediction +2

Characterization of Hemodynamic Signal by Learning Multi-View Relationships

no code implementations • 17 Sep 2017 • Eric Lei, Kyle Miller, Michael R. Pinsky, Artur Dubrawski

We aim to investigate the usefulness of nonlinear multi-view relations to characterize multi-view data in an explainable manner.

Clustering

Real-Time Visual Analysis of Microvascular Blood Flow for Critical Care

no code implementations • CVPR 2015 • Chao Liu, Hernando Gomez, Srinivasa Narasimhan, Artur Dubrawski, Michael R. Pinsky, Brian Zuckerbraun

Our method is able to extract microcirculatory measurements that are consistent with clinical intuition and it has a potential to become a useful tool in critical care medicine.

Video Stabilization