Aston works with Isansys to co-develop the ‘Life touch’ device

Aston works with Isansys to co-develop the ‘Life touch’ device which will reduce hospital stays and save lives

Why is this research needed?

Young patients in hospitals require consistent care and monitoring to assess any changes or deterioration in health. Monitoring these signals is essential because it alerts clinicians to when early intervention and treatments are required to save patient’s lives. At times, the methods used to measure patient’s health can be very expensive, time consuming and intrusive, causing discomfort for the young patients.

The research team 

After a career in academia, Professor David Lowe left to pursue a curiosity in developing new approaches for fast and resilient algorithms and a novel type of machine learning. Joined by Dr Randa Herzallah, senior lecturer and PhD student Christina Kozia, the team at Aston utilised their joint expertise in mathematics, engineering and applied sciences to develop methods to improve current patient monitoring practices.

The research process

Academics at Aston University worked to create new and innovative algorithms for patient monitoring through two industrially funded projects, the RAPID (Real-Time Adaptive and Predictive Indicator of Deterioration) and the ECG-Derived Biosignals project.

The newly developed algorithms work by consistently collecting, processing and analysing data from children on their cardiac activity taken through electrocardiogram (ECG) recordings. Extracted physiological indicators include breathing distress, respiratory rate, heart rate and many other important signals such as the R, Q and T peaks (biomarkers found in the blood that alert doctors to various factors).

With these physiological indicators recorded, personalised predictions of deterioration are then given through the system’s Paediatric Early Warning Score (PEWS). This system allows clinicians to obtain consistent updates to patient’s health that can be acted upon quickly if rapid changes occur.

These algorithms were tested at Birmingham Children’s Hospital on 1000 patients through Isansys life touch instruments. In testing, the devices provided real time information on the status of patients as part of their regular patient observations and were proven to be accurate.

Impact

These algorithms significantly improved clinician’s methods for patient monitoring in a way that does not require expensive techniques or medical tools. Instead, a simple lifetouch device (designed by Isansys) is attached to the patient’s chest and ankle to measure and analyse vital signs in real time. This non-invasive method also means that substantial discomfort is not caused to patients when monitoring their health.

The algorithms successfully developed at Aston to obtain cardiac physiological data are innovative, accurate and new. Currently no other off-the-shelf solutions exist and the PEWS data is a first in the medical world.

The accurate methods were adopted by Isansys, a world leading digital healthcare company and integrated to their devices. This led to development of their Patient Status Engine device, which is currently the most complete, scalable and simple-to-use advanced patient monitoring platform.

This research is vital because the individual, real-time monitoring that the algorithm provides means that signals that are usually recorded every one to four hours can now be monitored consistently. This will ensure clinicians have access to more accurate information, leading to faster treatment of patients. Helping to save lives with a high potential to significantly reduce hospital stays. Importantly, the standard of patient care is maintained without the discomfort of traditional, invasive methods.

In observing evidence from the clinical trials, the algorithms were proven to be accurate and reliable in the hospital wards.

Why is this research relevant today?

With the development of the Isansys device, more expensive, specialised equipment are not needed which serves to reduce the costs of treatment and the number of staff required to manage patient monitoring.