Ph.D. Position: Developing Personalized Digital Biomarkers for Metabolic Health with Wearables and Machine Learning
Engineering digital biomarkers of interstitial glucose from non-invasive smartwatches (npj Digital Medicine, 2021); A digital biomarker of diabetes from smartphone-based vascular signals (Nature Medicine 2020); Wearable sensors enable personalized predictions of clinical laboratory measurements (Nature Medicine 2021).
Technological advances in wearables and biosensors are rapidly transforming how we monitor and manage metabolic health, moving beyond finger pricking and blood picks. Data from wearables and smartphones hold massive potential to provide personalized insights into blood glucose levels and to inform decisions about diet and exercise in everyday life and at scale. What are the latest technological developments across wearables and biosensors, and how can we best leverage them to develop novel digital biomarkers in metabolic health?
The CSS Health Lab is a research laboratory at the Centre for Digital Health Interventions, a joint initiative of ETH Zurich and the University of St. Gallen (HSG), dedicated to various aspects of digital health and supported by CSS, one of the largest Swiss health insurance companies. Given the increasing health and economic burden of non-communicable diseases, the lab aims to make prevention measurable, actionable, and accountable and to make preventative care successful.
To strengthen the CSS Health Lab, we offer the following position at HSG’s School of Medicine in St. Gallen under the supervision of Mia Jovanova, PhD, upcoming Scientific Director of the CSS Health Lab and Postdoctoral Research in Digital Biomarkers for Healthy Longevity at the School of Medicine, University of St. Gallen, with Prof. Dr. Tobias Kowatsch and Prof. Dr. Elgar Fleisch being co-supervisors: Research Assistant to obtain a Ph.D. in Management, offered by the School of Management at HSG.
You must be eligible for a Ph.D. at HSG (School of Management), and you will work on projects to develop novel digital biomarkers for metabolic health using various passive data from wearables (e.g., V02max, blood pressure, oxygen saturation, respiratory rate, heart rate variability) and smartphones. As part of our team, you take direct project responsibility. You will lead machine learning pipelines for feature engineering, algorithm development, and validation using repeated measurements from wearables and smartphones.
You must have a strong technical background in machine learning and statistical modeling for intensive longitudinal and high-dimensional data from wearables. You will work in a highly interdisciplinary team at the intersection of computer science, behavioral medicine, clinical psychology, and business innovation.
Employment conditions, compensation, and benefits are attractive and based on the guidelines of HSG. The average duration for obtaining a Ph.D. is 3.5 years.
You should meet the following requirements:
- Strong expertise in machine learning methods for longitudinal and high-dimensional data from wearables and biosensors.
- A master’s degree in computer science or engineering, with a GPA (Grade Point Average) of at least 5.0 (GPA of 2.0 and better in Germany and Austria) and a strong experience in wearables and biosensor technology.
- Strong expertise in Python, R, or similar software/ languages.
- Strong interest in metabolic health, healthy longevity, health economics, and technology-based innovation.
- Prior experience (or interest) in applied research projects, start-ups, or venture capital and work experience in the digital health industry is advantageous.
- Self-confident appearance and high conceptual and communication skills, especially regarding presenting research results to a broad and interdisciplinary audience.
- Profound knowledge (written/oral) in German and English.
If you are fascinated by the described task and would like to be part of a highly motivated, young team, we would be pleased to receive your electronic application via the following link: HSG: Ph.D. Position: Developing Personalized Digital Biomarkers for Metabolic Health with Wearables and Machine Learning (unisg.ch)
For all inquiries, please email Prof. Dr. Tobias Kowatsch.