Skip to Main Content

COVID-19 is an emerging, rapidly evolving situation.

What people with cancer should know: https://www.cancer.gov/coronavirus

Get the latest public health information from CDC: https://www.coronavirus.gov

Get the latest research information from NIH: https://www.nih.gov/coronavirus

Principal Investigator
Name
Elham Taghizadeh
Degrees
Ph.D.
Institution
Fraunhofer MEVIS: Institute for Digital Medicine
Position Title
Research Scientist
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-645
Initial CDAS Request Approval
Mar 10, 2020
Title
Similar Patient Search for Cancer Patients
Summary
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.
Aims

• Integration of image and non-image data
• Extraction of the most relevant information to identify similar patients
• Automatic selection in a large database of a cohort of patient, who are similar to a specific one

Collaborators

Constantin Disch, Fraunhofer MEVIS: Institute for Digital Medicine
Marco Vicari, Fraunhofer MEVIS: Institute for Digital Medicine
Joachim Georgii, Fraunhofer MEVIS: Institute for Digital Medicine
Simon Konstandin, Fraunhofer MEVIS: Institute for Digital Medicine
Saulius Archipovas, Fraunhofer MEVIS: Institute for Digital Medicine
Stefan Kraß, Fraunhofer MEVIS: Institute for Digital Medicine
Jan Moltz, Fraunhofer MEVIS: Institute for Digital Medicine
Max Westphal, Fraunhofer MEVIS: Institute for Digital Medicine