Skip to main content

Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources (EXTREMUM)

About the project
The aim of the project is to develop a novel platform for learning from complex medical data sources with focus on two healthcare application areas: adverse drug event detection and early detection and treatment of cardiovascular diseases.

The team will present a new framework for data management and analysis of the integration of data, methods for machine learning as well as ethical issues related to predictive models. The fundamental breakthrough of this project is to establish a novel knowledge management and discovery framework for medical data sources. The outcome will be a set of methods and tools for integrating complex medical data sources, a set of predictive models for learning from these sources with emphasis on interpretability and explanatory features, and simultaneously focusing on maintaining ethical integrity in the underlying decision mechanisms that rule the machine learning.


Background

One of the biggest challenges that research and business entities have been facing recently is that the data provided by today’s technologies originate from multiple data sources in massive quantities and at rapid rates. In addition to their volume, such data sources are by nature complex and heterogeneous. In the presence of these complex and continuously growing information sources, domain scientists, data analysts, and novice users have been struggling to manage this complexity and arrive, from abundant data, to usable and interpretable models, as well as exploitable domain knowledge. Towards this end, these data sources need to be monitored in real-time, hence data integration and indexing, as well as predictive modelling become a major challenge. Consider, for example, the healthcare domain, where numerous data sources in the form of Electronic Health Records (EHRs), such as billing codes, registry data, and pharmaceutical data, are used for developing predictive models of, e.g., heart failure prevention and treatment progression, or adverse drug effect (ADE) detection.

An example workflow of the EXTREMUM framework; starting from radiography exams, ranking them based on their severity and urgency, then moving on their classification and tagging, while eventually producing clinically relevant explanatory text.

Cross-disciplinary collaboration
The project is a collaborative effort between four research institutions: the department of Computer and Systems Sciences at Stockholm University, the Department of Law at Stockholm University, RISE Research Institutes Sweden, Division ICT, and the Department of Automatic Control, School of Electrical Engineering and Computer Science (EECS, KTH).

Newsletter

Subscribe to our newsletter!

Contacts

Picture of Panagiotis Papapetrou

Panagiotis Papapetrou

Professor, Department of Computer and Systems Sciences at Stockholm University, PI of research project Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources at Digital Futures

+46 8 16 16 97
panagiotis@dsv.su.se
Picture of Lars Asker

Lars Asker

Associate Professor and Doc., Department of Computer and Systems Sciences at Stockholm University, Co-PI of research project Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources at Digital Futures

+46 8 674 70 02
asker@dsv.su.se
Picture of Stanley Greenstein

Stanley Greenstein

Senior Lecturer, Departement of Law at Stockholm University, Working group Trust at Digital Futures, Co-PI of research project Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources at Digital Futures

+46 8 16 25 98
stanley.greenstein@juridicum.su.se
Picture of Rami Mochaourab

Rami Mochaourab

Senior Researcher, Digital Systems division at RISE, Co-PI of research project Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources at Digital Futures

+46 10 228 41 56
rami.mochaourab@ri.se
Picture of Cristian Rojas

Cristian Rojas

Associate Professor, Division of Decision and Control Systems at KTH, Co-PI of research project Explainable and Ethical Machine Learning for Knowledge Discovery from Medical Data Sources at Digital Futures

+46 8 790 74 27
cristian.rojas@ee.kth.se