Objective

This master’s thesis project aims to develop a comprehensive machine learning model leveraging both clinical and genetic data from patients diagnosed with diffuse large B-cell lymphoma (DLBCL), the most common aggressive lymphoma. Publicly available datasets encompassing a wide range of clinical parameters and genetic profiles will serve as the foundational data source. The primary objective is to identify specific risk features strongly correlated with poor therapeutic response or significantly shortened survival time. By pinpointing high-risk patients, the model will enable healthcare providers to tailor treatment plans more effectively, potentially improving clinical outcomes and the overall prognosis for patients with DLBCL.

Tasks

Data Integration

• Merge and preprocess diverse data types from publicly available sources, ensuring dataset compatibility and integrity.

Model Development

• Design and implement predictive models using machine learning techniques on integrated clinical and genetic datasets.
• Evaluate the model’s performance to identify high-risk patients accurately.

Explainable AI

• Incorporate methods from explainable AI to enhance the interpretability of the model’s predictions for healthcare providers.

Prerequisites

• Strong programming skills in Python.
• Experience with machine learning and handling datasets.
• Familiarity with explainable AI methods is a plus.

We offer

• Pursue your master’s thesis on a captivating project at the intersection of medicine and computer science.
• Collaborate within an international, multidisciplinary team of physicians, computer scientists, and data scientists.
• The language in our group is primarily English.
• Hybrid and fully remote options are available.
• Dual mentorship by both a physician and a computer scientist.