Department of Health Sciences and Technology
The Biomedical Data Science (BMDS) Lab investigates data-driven solutions for healthcare applications, focusing on neurological conditions such as spinal cord injury (SCI), lower back pain, neurodegenerative disorders, and neurological tumors. At the core of our research is collaboration across disciplines, bringing together expertise in medicine, biology, computer science, and data science. We are seeking a scientific assistant to join our growing team and contribute to interdisciplinary research partnerships. The anticipated start date is July 1, 2025.
Project Overview
Traumatic SCI has profound and lifelong implications for affected patients and their families. A major challenge in drug development for traumatic SCI is the high failure rate of clinical trials, even when promising preclinical evidence exists. One of the key obstacles is the assumption that SCI can be treated without accounting for substantial variability in individual biological, clinical, health, and injury-related characteristics. Traditionally, a uniform physiological recovery capacity and consistent benefits from experimental treatments are assumed, contradicting the established understanding of natural recovery variability. The proposed project aims to bridge this critical gap by distinguishing between patients’ baseline natural recovery and treatment-induced improvements. By isolating the true treatment effect, the project seeks to provide a clearer and more accurate assessment of how interventions influence recovery trajectories.
Responsibilities
- Familiarize yourself with various international databases collecting data on SCI patients, which will be readily available at the start of this project.
- Implement, train, and benchmark state-of-the-art data science pipelines to characterize SCI recovery trajectories and injury patterns. Integrate personalized physiological measurements into a recovery prediction model, while adapting Bayesian Neural Networks for SCI data and analyzing the impact on model uncertainty.
- Develop and implement methods to utilize predicted natural recovery to effectively isolate, analyze, and quantify treatment-induced improvements in SCI patients.
- Collaborate with clinical experts to develop an exploratory web platform for traumatic SCI recovery, ensuring it aligns with the needs of both patients and healthcare professionals.
Qualifications
- A Master's degree in a relevant field such as data science, computer science, physics, computational biology, or biomedical research.
- Proficiency in Python programming, with experience in statistical analysis and implementing machine and deep learning models using Keras/TensorFlow and/or PyTorch.
- Experience in collaborative coding, version control, and utilizing computer clusters.
- Background in biomedical projects and experience in interdisciplinary collaboration are ideal.
- Experience in SCI-related research is a plus.
- Motivated to work as part of a diverse team and committed to scientific excellence.
- Proficiency in both written and spoken English.
What We Offer
We offer a 1-year project-based contract at the BMDS Lab (80–100% workload), with the potential for a second-year extension. The position includes:
- Opportunities to engage with diverse communities bridging data science and SCI research, leading to high-impact publications.
- Enhancement of your data science skills while gaining insights into the biomedical aspects of critical health conditions, focusing on SCI.
- A position in a highly motivated, multidisciplinary, and collaborative team.
- The chance to learn from experts in the field and contribute to an active research lab.
- Support for your scientific career development and application for doctoral fellowships, if desired.
Apply online using the form below. Only applications matching the job profile will be considered.
Contact Information
Further information about the BMDS lab can be found on our website. Questions regarding the position should be directed to Olga Taran at olga.taran@hest.ethz.ch (no applications).