PhD position on Physiological-Model-Based Artificial Intelligence for the recovery monitoring of elderly after hip fracture ...

A hip fracture in older adults is associated with complications and a high mortality rate of 10% within one month and 30% within one year after hip fracture surgery. It is therefore crucial to monitor patients’ health condition continuously and accurately after surgery to measure and evaluate patients’ recovery progress, timely detect and even predict clinical adverse events like delirium, cardiac arrhythmias and pneumonia. In this project, the University of Twente (Biomedical Signals and Systems group; BSS) in collaboration with the top clinical hospital Ziekenhuisgroep Twente aims to develop such a health condition monitoring system to assist patients’ recovery management and ultimately reduce the complication and mortality rate and increase their quality of life after hip fracture surgery.

This PhD position will focus on the health monitoring system development mainly based on multimodal physiological signals, for instance, inertial measurement unit (IMU), electrocardiography (ECG), photoplethysmogram (PPG), Electrodermal activity (EDA), and contactless movement and physiology signals. Specifically, the PhD researcher will develop physiological-model-based artificial intelligence technologies to assess patients’ recovery process, detect or even predict the occurrence of clinical adverse events like delirium, cardiac arrhythmias and pneumonia among elderly after hip fracture surgery. To obtain relevant data for the above described technology development and its feasibility test, the PhD candidate will also design medical research experimental protocol for both healthy control population and target patient population, apply for the protocol’s ethical approval (please check this website for more information about the relevant ethical regulations and approval process in the Netherlands), and take main responsibilities for performing the approved experiment.

This PhD position is embedded in the EU Horizon Europe Marie Sklodowska-Curie Doctoral Network (MSCA DN) SMARTTEST project. This position is linked to Doctoral Candidate 8 – DC08. For more information on the SMARTTTEST project, the recruitment process or details of the position, follow this link for more information.

The prospective PhD candidate is expected to perform high quality and internationally visible research with publications in high rank peer-reviewed journals. The candidate will join the Biomedical Signals and Systems group at the University of Twente and will be (co-)supervised by dr. Ying Wang, prof. dr. Johannes H. Hegeman and prof. dr. ir. Peter H. Veltink. The candidate will closely collaborate with dr. Ying Wang and fellow team members and is also expected to closely collaborate with the other partners within the SMARTTEST project. The candidate will be appointed for a period of four years, at the end of which a PhD thesis needs to be delivered. During this period, the PhD candidate will be offered the opportunity to broaden their knowledge by joining MSCA SMARTTEST consortium meetings and by participating in (inter)national conferences and workshops.

PhD position on Memristive Smart Materials for Information Processing

This position is part of the NWO KIC Smart Materials project, Smart Materials for Information Processing, in collaboration with the NanoElectronics (NE) group at the University of Twente and the Infomatter group at AMOLF. The SMIP project aims at revolutionising computing by developing adaptive, smart materials that combine memory and learning directly within their structure, uniting theory and experiment. These materials adapt their computations over time, reducing energy use and improving efficiency. Partnering with Toyota and Demcon TSST, SMIP will showcase this innovation through a self-learning chip prototype, improving performance and durability in automotive applications.

Specifically, this PhD project focuses on memristive materials as electronic realizations of the hysteron concept at the heart of the SMIP project. A hysteron is characterized by a hysteretic current-voltage characteristic; thereby, its response depends critically on its history. You will work on conceptualizing, fabricating, and characterizing effective memristive devices, with the goal of forming device networks for realizing the physical learning paradigm developed at AMOLF. You will integrate these memristive devices with the reconfigurable nonlinear processing units (RNPUs) developed in the NE partner group to harness the full richness of both material platforms.

PhD position - Green and safe routing for Cyclists

The rapid expansion of (peri-)urban areas across Europe presents a serious sustainability challenge. A modal shift towards cycling is required to achieve sustainable urban mobility, thereby reducing private car dependency, and improving health, air quality and noise pollution. In the project Green and safe routing, the challenge is to develop, validate and test a method that offers personalized, tailored travel and route advice in order to stimulate cycling.

This four-year PhD project is part of Horizon Europe project Bio-Intel-Mob. The project focuses on integrating sustainable mobility and logistics with intelligent solutions for safe, smart, green, resilient, and inclusive cities, with pilot demonstrations in Rome, Cascais, Riga, Vilnius, Melsungen, Ciampino, Urla and Rhodes.

The PhD project will involve:

• The use of data analytics (statistical models, machine learning, uncertainty quantification) to monitor and predict cycling travel conditions from various perspectives (safety, crowding, travel time, comfort, etc.). Therefore, various data sources including real-time traffic counts from inductive loop detectors, GPS traces, maintenance information and crowd-sourced data need to be combined.
• Learning personal mobility patterns, e.g., using space-time clustering techniques. Identify patterns based on observed travel behavior, and relate patterns to real-time and predicted travel conditions to recognize and predict events that may impact the trip of an individual.
• Developing a method for multi-objective, personalized (re)routing, i.e., generating routes and offering route suggestions based on mobility behavior, travel conditions, trip characteristics, and user preferences. Defined routes trade-off multiple criteria, where the exact importance of each objective is user dependent, and can be learned and improved over time based on previous choices and feedback.

Postdoc positie, klinische implementatie AI gebaseerde voorspelmodellen

Word jij enthousiast van het verbeteren en toepassen van AI bij het oplossen van klinische uitdagingen? Ben je communicatief vaardig en vind je het leuk om met mensen met verschillende achtergronden samen te werken? Als postdoc onderzoeker binnen de vakgroep M3i en het Rijnstate ziekenhuis maak je deel uit van het door ZonMW gefinancierde AI for EVAR-project, dat erop gericht is de zorg voor patiënten met een abdominaal aorta-aneurysma te transformeren. Je implementeert en valideert geavanceerde multimodal deep learning-modellen die beeldvorming en klinische data integreren om behandel en follow-up strategieën te personaliseren. Daarnaast voer je een vroege HTA analyse uit van de ontwikkelde modellen.

In Nederland wordt ongeveer 75% van de patiënten met een abdominaal aorta-aneurysma endovasculair behandeld, waarbij een stent wordt geplaatst (EVAR). Hoewel EVAR goede korte-termijn resultaten oplevert, hebben deze patiënten op de lange termijn een verhoogd risico op complicaties en heringrepen. Dit maakt levenslange follow-up noodzakelijk.

Binnen het door ZonMW gefinancierde AI for EVAR-project ontwikkelen we multimodale modellen voor een optimale keuze voor behandeling en voor follow-up ná EVAR. Je implementeert en valideert multimodal deep learning-modellen die CT-beelden en klinische data combineren, getraind op de unieke RADAR-consortiumdatabase.

Je wordt onderdeel van de leerstoel M3i, naast een aanstelling in het Rijnstate ziekenhuis (afdeling Chirurgie). Gecombineerd hebben beide centra ruime expertise in de ontwikkeling van betrouwbare en robuuste deep learning-methoden (in samenwerking met de UT-vakgroep MIA) met klinische impact. Het project is sterk interdisciplinair, en van de succesvolle kandidaat wordt verwacht dat hij/zij intensief samenwerkt met technische en industriële partners.

Ervaren Business Developer Novel-T

Jouw uitdaging

Twente staat bekend als ondernemende en innovatieve regio. Binnen zowel het MKB als vanuit studenten en onderzoekers bruist het van nieuwe ideeën en businessconcepten. Het is jouw uitdaging om deze op te sporen en te verrijken. Met behulp van onze programma’s en instrumenten coach je de ondernemer en het bedrijf richting de markt of naar verdere groei. Hiervoor schakel je met relevante partijen in de markt en benut je het innovatie-ecosysteem waarin Novel-T een centrale rol speelt. Als ervaren business developer ben je een inspiratiebron voor zowel ondernemers als je collega’s.

Naast het begeleiden en coachen van bedrijven, geef je trainingen en workshops aan groepen ondernemers. Dit doe je binnen de programma’s die Novel-T uitvoert over onderwerpen zoals marktvalidatie, klantinterviews en teamvorming. Je bent in staat om dit op een enthousiaste en inspirerende wijze te doen.