PhD student at the intersection of data science, smart sensor technology, and neurology

Spinal Cord Injury Center
PhD student at the intersection of data science, smart sensor technology, and neurology
100 %
Traumatic spinal cord injury (SCI) is caused by sudden mechanical trauma to the spinal cord, resulting in mild to severe paralysis and reduced sensation. There are currently no effective treatments that can mitigate the damage in the spinal cord, leaving patients with lifelong deficits. Beyond their immediate health consequences, SCI has a devastating impact on the patients, caregivers, and society, reducing quality of life and massively burdening the health care system. Recovery from acute SCI is characterized by extensive heterogeneity. This means that patients recover to vastly different levels, even though they appear very similar initially. One promising approach to improve the prediction of recovery after SCI is to embrace the momentum of wearable sensor technology to track and quantify the physical activity of patients during their recovery and rehabilitation. Physical activity positively impacts recovery, but physical activity levels may fluctuate throughout the rehabilitation process not necessarily owing to changes related to neurological recovery and compensation strategies. These fluctuations can be accurately and objectively measured by means of wearable sensors. We aim to gather information gained from clinical (e.g., demographics, injury characteristics), functional (e.g., sensor data), and neurophysiological assessments (e.g., electromyography) with the overarching goal to improve the prediction and characterization of recovery following spinal cord injury. Our primary hypothesis is that incorporating sensor and electromyography data in the prediction models will allow us to recognize early clinically relevant subgroups of patients. Moreover, subtle therapeutic effects, which are currently less reliably revealed, will be detected by means of the combining of neurological and functional measures.
The topic of this PhD project concerns an important question in the field neurology: How can we improve the prediction of recovery after an acute spinal cord injury (SCI)? Specifically, using data science and machine learning, the project aims to identify digital biomarkers derived from wearable sensor technologies that are predictive of recovery and are sensitive to identify early clinically relevant subgroups of patients. The project capitalises on large biomedical datasets that are being collected at the University Clinic Balgrist, the European Study about Spinal Cord Injury, and an ongoing clinical trial. The project will be conducted in close collaborations with Prof. Catherine Jutzeler and Dr. Laszlo Demko from the ETH Zurich and clinical partners at the University Clinic Balgrist and the associated Spinal Cord Injury Center. University Zurich is a family-friendly employer with excellent working conditions. You can look forward to an exciting working environment, cultural diversity and attractive offers and benefits.
Your responsibilities
The primary objective of this PhD position is to refine the prediction of functional and neurological recovery by harnessing the power of the multi-dimensional data (i.e., clinical assessments, neurological and functional scores, data derived from wearable sensors) and machine learning algorithms. The PhD student will also be substantially involved in creating individual patient activity profiles to motivate the patient, guide the rehabilitation strategy, and pioneer the translation from the laboratory setting to the clinical routine as well as the implementation in the design of clinical trials.
The PhD student is expected to work towards a doctoral degree and participate in the teaching activities of the group. This full-time position offers the student an excellent opportunity to delve into the world of data science and machine learning as well as gain deep fundamental knowledge about neurology. The student will join an inclusive, diverse, and supportive working environment that praises scientific curiosity and creativity.
Your profile
You are a highly motivated, committed, and creative candidate, who can work in a multidisciplinary team and with outstanding communication skills.
At the time of appointment, you have completed a master's degree in Statistics, Computational Biology, Data Science, Health Sciences, Translational Medicine, or related fields with a strong focus on applied statistics and/or machine learning. A strong command of R or python programming are required. All work-related interactions are in English and thus, excellent English writing and communication skills are essential. Knowledge of German is an added value.
What we offer
We offer varied and interesting work in an inspiring and socially relevant environment.
Diversity and inclusion are important to us.
Place of work
Balgrist Campus
Start of employment
The tentative starting date is November 2022 or later. Applications are accepted until the position is filled.
UZH on social media