Elham Taghizadeh

Ph.D.

Fraunhofer MEVIS: Institute for Digital Medicine

Research Scientist

NLST (Learn more about this study)

NLST-645

Mar 10, 2020

Similar Patient Search for Cancer Patients

Best practice for diagnosis and treatment of cancer patients is described in clinical guidelines. Nevertheless, in decision making, clinicians must also take into account patient's specific conditions, like comorbidities, intolerance and pregnancy, which are not explicitly considered in the guidelines, although crucial in patient management. The decision making process could be improved by means of decision support systems that provide both a more comprehensive integration of patient data, and a deeper insight in patient's specific conditions. Indeed, the aim of this project is to develop new algorithms to support clinical decision making, on the basis of a large dataset of lung cancer patients who were treated in the past. In particular, one goal is to predict treatment effectiveness by analyzing the disease course of patients with similar conditions (Similar Patient Search). In this project, we will make use of image processing, machine learning and statistical methods to analyze clinical, radiological, pathological, and genomic data, and automatically extracts the relevant information to make a better and faster decision that is patient specific. The project outcomes will be presented to industrial partners by means of prototypal demonstrators, and submitted as conference and/or journal articles.