At long last, stroke patients can be monitored at home, using a sensor suit

As many as 33 million people throughout the world suffered strokes in 2010. With our aging population, it seems logical to expect a further increase in these numbers in the upcoming years. Stroke survivors often have to cope with physical limitations. They generally take part in rehabilitation programmes, which are intended to help patients function as effectively as possible in their everyday lives. In practice, however, rehabilitation mainly takes place in rehabilitation clinics. Not enough is known about how, after completing such programmes, patients cope with their limitations in a daily life setting. Yet it is known that a better understanding of how these people function in everyday life could lead to more effective rehabilitation, at a lower cost. In the context of a European FP7 research project, Bart Klaassen (a PhD student at the University of Twente) and a large team of researchers developed a system for accurately measuring and modelling these patients' movement quality, and for transmitting the relevant information to the therapist. This project is a world first. Never before have researchers used systems like this to analyse these patients' every movement in a daily life setting. "There has long been a great need for systems like this, but the technology simply was not ready," says Klaassen. "That is now changing rapidly, thanks to rapid developments in the fields of battery technology, wearables, smart e-textiles and big data analysis."

41 sensors

Together with a large consortium of engineers and healthcare professionals, Bart Klaassen developed the INTERACTION System. This consists of a suit that study subjects had to wear under their clothing for three months, as well as the entire technical infrastructure needed to transmit, store and process the data collected. The suit contains no less than 41 sensors, including sensors on a large number of body segments, sensors that measure muscle strength, stretch sensors on the back and the hands, and force sensors in the soles of the shoes. In addition, the suit is equipped with a portable transmitter that can transmit all of the information gathered through the internet to data processing servers at the University of Twente.

In the course of his PhD research, Klaassen showed that the system works well in practice. "We have been able to demonstrate that all the information is transmitted successfully, that this process is very efficient, and much more besides. We have succeeded in modelling all of the relevant movements, and in cleaning up the data that is relevant for the therapist by filtering out the rest.Our project has delivered new techniques and methods that can be used to monitor patients at home for extended periods of time, and to identify any differences with structured clinical measurements. We are currently engaged in further research to obtain final verification that these methods are indeed an ideal way of supervising rehabilitation."

When developing this system, Bart Klaassen and the team adopted a user-centred design approach. This enabled them to continually incorporate feedback from the patients involved into the development of the system. Other relevant parties -- such as insurance companies and healthcare professionals -- were also involved in the design and research work at an early stage.

PhD defence

As part of his PhD research, Klaassen worked closely with what he calls 'world leaders in the field of rehabilitation technology'. These included Cereneo A.G. (a Swiss rehabilitation centre), the Department of Neurology at the University Hospital of Zurich in Switzerland and Roessingh Research and Development BV. Bart Klaassen conducted his research at the Biomedical Signals and Systems Department in the University of Twente's MIRA research institute. Klaassen will defend his PhD thesis in the Prof. G. van Berkhoff hall, in the Waaier Building on the University of Twente campus at 16:30 on Wednesday 30 November. Bart Klaassen is currently working as a coordinator at the University of Twente's tech4People BMS lab.