PHD POSITION 'BALANCING NATURE AND CULTURE IN SOUTHWEST EUROPEAN LANDSCAPE EVOLUTION AND INTEGRATED LEGACIES'
2 dagen geleden - VU - Amsterdam
The ageing population and the increased incidence of chronic disease is imposing unparalleled financial and societal burden. There is an urgent need for a …
The ageing population and the increased incidence of chronic disease is imposing unparalleled financial and societal burden. There is an urgent need for a paradigm shift towards "precision medicine": a tailored, personalized approach in medicine to improve patient care and quality of life, while reducing healthcare costs. Despite improvements in anesthesia and post-operative care, about 25% of patients undergoing surgery suffer from serious post-operative complications. Early identification of patients at risk is fundamental to enable effective prevention, improve patient safety, and permit optimal guidance of clinical decision making. This must be combined with unobtrusive, continuous patient monitoring at all levels of care to enable patient-specific decision support.
Prevention and timely intervention have been facilitated by the implementation of warning systems. However, current systems typically rely on sparse, non-real-time data sampled from the patient to calculate warning scores. These are mostly based on heuristic predictive models detecting deviations from population-averaged "normal" values. Thus, they have limited accuracy, they are not patient-specific, and they can only be used for long-term prognosis. A step towards more intelligent decision-making tools calls for real-time, patient-specific, quantitative analysis of a bio-signals in a dynamic, adaptive paradigm, able to incorporate domain knowledge and new measurements as they become available.
Biomedical diagnostic (BM/d) research lab at TU/e
The BM/d lab is devoted to model-based quantitative analysis of medical images and bio-signals, with the goal of improving patient care and management. In the context of perioperative care, we focus on modeling and analysis of bio-signals, taking into account the full measurement chain, with the goal of improving diagnosis and prognosis, and enabling long-term monitoring. By model-based signal analysis we aim at extracting features that are related to the underlying physiology/pathology, facilitating clinical interpretability. Combination of model-based feature extraction with data-driven approaches, e.g. machine learning, for feature selection enables the development of effective risk prediction models to support clinical decision making. Exploiting the increasing availability of large clinical datasets, data-driven approaches offers an opportunity to unravel hidden aspects of the underlying complex physiology, which might be relevant for understanding the investigated process, yet not directly measurable.
Job description and requirements
In this context, we are seeking a highly motivated master graduate with knowledge and interest in medical data analytics, and with a strong background in model-based analysis of bio-signals. The position is available within the BM/d research lab, part of the Signal Processing Systems (SPS) group (Electrical Engineering department, TU/e), and it involves joint collaborations with the Stochastics group (Mathematics and Computer Science department, TU/e), and with clinical and industrial partners, including the Catherina Ziekenhuis Eindhoven and Philips, as part of the Eindhoven MedTech Innovation Center (e/MTIC).
We are looking for candidates that meet the following requirements:
- Master degree in Electrical Engineering, Biomedical Engineering, or Computer Science
- Background in medical signal processing and data analytics
- Excellent education track record
- Good analytical skills
- Affinity for working in an interdisciplinary and highly international environment.
- Proficiency in English