Welcome at the (temporary) website of the Clinical Data Science group at Maastricht University, Maastricht UMC+ and Maastro Clinic.

Research themes

At CDS we have three main research themes.

Responsible use of all health related data

We perform research, develop and implement federated FAIR data infrastructures. Federated data infrastructures mean that we focus on keeping the data at the source. This alleviates data privacy and control concerns. FAIR data means Findable, Accessible, Interoperable and Reusable data. FAIR data is crucial in a federated data infrastructure as data may be captures in different languages and with different, local practices. Making health data available for learning in a federated FAIR manner, is one of our scientific strengths. To further strengthen this theme, we also have extensive experience in dealing with legal, ethical and technical challenges including compliance to GDPR and related regulations and meeting security standards that our partners set.

Learn AI applications from health data

We use artificial intelligence methods to learn from health and health related data. We apply a wide variety of machine and deep learning algorithms. We use AI for two main goals:

Improve efficiency and/or quality of health care

Efficiency and quality of health care can be improved if AI applications can perform tasks that either take a lot of human resources and/or need specialized skills. Deep learning for instance can perform routine tasks of radiation oncologists and technologists such as 3D segmentation of tumors and normal tissues in images with a performance that matches or surpasses human performance. And Natural Language Processing can make it easier to extract concepts from medical free text and documents.

Support decisions to improve future health

Prediction of a future health outcomes of an individual, like survival in a cancer patient after radiotherapy, is a difficult task as such outcomes are usually determined by many factors. But not being able to predict the future limits our ability to recommend treatments and other interventions (such as a lifestyle change) to individual patients and citizens. AI can handle many more predictive factors than humans and we thus do research in AI driven outcome prediction models. We use machine learning on real world data to derive such models. Determining validity, bias and generalizability of health outcome prediction models is a particular strength of our group. We also focus on relative simple and transparent AI as treatment decisions need to be explained and understood.

Apply AI for better health and healthcare

We introduce artificial intelligence applications to improve health of citizens and patients and improve health care. Depending on the applications this can take many forms. For instance we develop patient facing apps and websites where patients can use our outcome prediction models. We also develop plugins for Electronic Health Records that allow for decision support for health care professionals and shared decision making with patients. Making sure AIs are well understood by skilled and non-skilled users and are safe to use are important research topics in our group. We have also developed and apply methods to evaluate what effect an AI has on efficiency and outcomes. We often work closely with companies as AI applications are medical devices which need to be developed by professional providers and certified before they can be used (e.g. CE mark or FDA approval).

Staff

Please find here an overview of the people that are or were part of Clinical Data Science: Staff

Research projects

In projects we usually combine our research themes to meet the deliverables. We work in a variety of clinical settings including oncology, cardiology, neurodegenerative diseases and irritable bowel disease and in both in care and prevention. Please visit our project page for information on our past and current projects. Projects

Outcome prediction models

One of our research goals is to develop models (algorithms, software, formulas) that can prediction future health outcomes in people. Please visit our models page for an overview. Models