AI in Healthcare EU Funded Projects - IBM Research

EU-Funded Projects

Existing and Accepted EU projects

Project	Goal	Role
(2021-2026)	How do SARS-COV-2 variants, coupled with other factors, influence the clinical course of COVID-19? Is there any vaccine or test escape related to variants? Do variants influence the spread in the school setting, and how? Can we define a better testing and containment strategy in the school setting? What is the impact of containment measures, including schools closure, on pupils and teachers? These are some of the questions that the EuCARE project will strive to answer.	IBM is leading the development of advanced AI technologies including prediction algorithms and causal inference methods to analyze the effect of interventions on clinically relevant outcome and public health outcomes related to the pandemic, and how these effects are influenced by viral variants.
(2020-2023)	To combine the most advanced technologies for data and knowledge management with a sound socio-psychological approach in order to develop a coaching system for improving the quality of life of patients after cancer treatment.	We lead a development of comprehensive AI framework for decision support that combines AI-based models for personalized prediction of patient outcomes and adverse events, clinical treatment guidelines and patients behavioral information.
(2019-2022)	Training young scientists and fostering international collaboration, with specific focus on machine learning methods for personalized medicine (continuation of MLPM, see below).	Supervising an early stage researcher (ESR) and seconding researcher(s) in applying causal inference algorithms to observational data to estimate individual-level effect of intervention.
(2018-2019)	To identify the gaps in the present EU-R&D research program and to develop EU R&D Strategy and Roadmap.	Active participation including serving on the management committee.

Selected past EU projects

Project	Goal	Role
(2018-2021)	Optimization of the neoadjuvant breast cancer treatment by the use of diagnostic imaging (introduction of Radiomics tools). This is a part of a larger effort aimed at use of AI for streamlining various medical treatments and processes.	We lead Breast Cancer pilot and develop machine learning tools for prediction of the optimal neoadjuvant treatment based on combination of image (mammography, ultrasound and MRI), clinical and genomic data.
(2017-2021)	Training young scientists and fostering pan-European collaboration, with specific focus on metabolism and cancer immunology.	Supervising an early stage researcher (ESR) and seconding researcher(s) in applying machine learning tools to study the metabolism-immune system connections in cancer.
(2019-2020)	To make the transforming promise associated with Advanced Therapies a reality for the benefit of patients and society.	A “place” where medicine, basic research, technology development and engineering meet, communicate and work together. Through this coordinated, financially strong, academia-industry partnership, we hope to exert a game-changing impact on Europe´s economy and society.
(2006-2008, and on going)	Development of an AI system that learns from patients data and finds the best therapy regiment for a given HIV patient and creation of a freely available clinical decision support system to assist physicians in selecting the optimal treatment.	Development of machine learning tools for prediction of the in-vivo efficacy of anti-retroviral therapy regimens, based on the use of viral genotype data integrated with treatment response data derived from the clinical practice. Leading the creation of an ensemble methods that combine various such AI tools. See selected publications at Bioinformatics, HIV Medicine, AISAT and PMLR.
Hypergenes (2008-2011)	Personalized prediction of the hypertension development.	Development of the disease model that predicts the future clinical range of each risk parameter, exploring also the contribution of the genomic data.
(2015-2016)	To identify the gaps in the present EU-R&D research program.	Active participation and co-leading the development of the roadmap (see the we-care proposed roadmap at the Lancet https://www.ncbi.nlm.nih.gov/pubmed/26876711.
(2014-2016)	Training young scientists and fostering international collaboration.	Hosting foreign students and helping to train them in use of machine learning in the healthcare domain.