Causal Machine Learning for Healthcare & Life Sciences

Our specialty lies in developing algorithms that learn to recognize complex patterns within rich and massive data. Our machine learning and causal reasoning tools are built to solve an array of different challenging problems in the healthcare industry.

We focus on a range of models, from clinical decision-support systems, through analyzing medical device signals with dynamic and deep networks, to analyzing real-world observational healthcare data to gain drug response insights and candidates for drug repurposing.

The team participated in several EU consortia in FP6 and FP7 and is now seeking partners with computational, experimental, and clinical groups to submit H2020 proposals that involve the analysis of complex omics, clinical, and environmental data. Of particular interest are projects that integrate various data modalities recorded over time, where the team can use its expertise in building computational tools to model the system dynamics and to infer causal interactions between the various entities.

We are also a partner in the Marie Curie Innovative Training Network (ITN) META-CAN, a pan-European interdisciplinary and intersectoral training program for excellence. As part of this network we are looking for smart research students to analyze omics data and help us discover the metabolic adaptations of cancer cells to the central nervous system niche.

 

Yishai Shimoni, Manager Causal Machine Learning for Healthcare & Life Sciences, IBM Research - Haifa

Yishai Shimoni,
Manager, Causal Machine Learning for Healthcare & Life Sciences,
IBM Research - Haifa

Research

Analyzing Observational Healthcare Data

 

What-if scenario analysis for policy makers

 

Drug Repurposing

 

Medical Device Data Analytics