Technology Imroves Odds for Critically Ill

CLINICIPLarge numbers of unnecessary deaths and avoidable medical complications in intensive care units (ICU) are attributable to the difficulties of treating high glucose levels in critically ill patients' blood. That is about to change for the better thanks to a new automated insulin delivery system developed by European researchers.

A common side effect of stress and trauma in critically ill patients is a rapid increase in blood glucose levels. As with diabetes, the levels can be reduced and controlled by the infusion of insulin. But glucose levels peak and change much more quickly in the ICU environment and there is little room for trial and error. If the situation is not normalised, then complications and even deaths can and do occur.

Twice in the past, Europe-wide studies and trials were put in place to try and come up with a solution to the problem. But in both cases they were prematurely halted because researchers could not solve the problem of overcompensating and patients developing hypoglycaemia, or abnormally low blood sugar levels.

"What these studies did clearly indicate is that the establishment of normal glucose levels in critically ill patients is very difficult to achieve without some sort of automated system to help the nurses," says Dr Martin Ellmerer, scientific coordinator of the CLINICIP project which has developed just such a system.

Nurses' no-nonsense approach
CLINICIP started by surveying ICUs in a number of European hospitals and interviewing nursing staff. "We found out that ICU staff did not want to see additional catheters in patients, they did not want extra equipment taking up space, and costs had to be kept right down so as not to eat into funds for other vital equipment," says Ellmerer. "So, right from the start the requirements were really tough."

Partners in this EU-funded project, academic medical institutions plus one private-sector medical equipment manufacturer, decided they needed to develop a two-step approach. "We first developed a decision-support system which met all the criteria outlined by the ICU staff, and later developed a fully automated system," he tells ICT Results.

At the heart of both systems is a sophisticated bit of computer software (an algorithm) written especially for this project.

With the decision-support system, nurses still have to draw blood from patients in the traditional way and test it for glucose levels. They enter the information via the user interface - a touch screen - the researchers have developed. The algorithm takes over at this stage, calculates how much insulin is needed and automatically administers it. It also alerts the nurse when a new blood sample needs to be taken and analysed - half an hour in the worst cases and up to four hours in less severe cases.

"We have fully functioning prototypes of the decision-support system which we successfully trialled in ICUs at different hospitals around Europe," Ellmerer says. The project's industrial partner, B. Braun Melsungen AG, is ready to go into commercial production of the system working together with the clinical partners.

"We will first have to go through an approval process and the systems should be commercially available to hospitals in mid-2009," Ellmerer says. B. Braun is one of the leading manufacturers of infusion systems used in hospitals, and the CLINICIP technology will be incorporated into these as it was during the trials.

Developing the real deal
At the same time the prototype was being developed and tested, CLINICIP researchers were working on sensors for a fully automated, closed-loop control system to both monitor glucose levels and administer insulin with no involvement from a nurse.

The drawback of this is that a dedicated needle is necessary. "Unfortunately, this is unavoidable for a fully automated system," Ellmerer points out. Using fibre-optic technology the needle draws blood, sends it for analysis and then returns it to the patient's vein as well as administering the necessary dose of insulin.

"We have performed a proof-of-concept study to show we are able to establish glucose control in a clinical setting," Ellmerer says.

To develop the sensor technology further and then commercialise it, a spin-off company will be set up with Ellmerer as CEO and one of the shareholders. The other shareholders are individuals from project partners in CLINICIP. The spin-off will work closely with B. Braun and the partners, although they are not stakeholders in it.

Ellmerer expects the fully automated two-step system to be commercially available in 2011.

"Our research and the products which result from it should have a pretty fundamental impact on ICUs," he says. "They should improve survival chances, reduce complications, such as sepsis and organ failure, and reduce the time patients need to spend in ICUs."

For further information, please visit:
http://www.clinicip.org

Source: ICT Results

Related news articles:

Most Popular Now

Most Advanced Artificial Touch for Brain…

For the first time ever, a complex sense of touch for individuals living with spinal cord injuries is a step closer to reality. A new study published in Science, paves...

Predicting the Progression of Autoimmune…

Autoimmune diseases, where the immune system mistakenly attacks the body's own healthy cells and tissues, often have a preclinical stage before diagnosis that’s characterized by mild symptoms or certain antibodies...

Major EU Project to Investigate Societal…

A new €3 million EU research project led by University College Dublin (UCD) Centre for Digital Policy will explore the benefits and risks of Artificial Intelligence (AI) from a societal...

Using AI to Uncover Hospital Patients�…

Across the United States, no hospital is the same. Equipment, staffing, technical capabilities, and patient populations can all differ. So, while the profiles developed for people with common conditions may...

New AI Tool Uses Routine Blood Tests to …

Doctors around the world may soon have access to a new tool that could better predict whether individual cancer patients will benefit from immune checkpoint inhibitors - a type of...

New Method Tracks the 'Learning Cur…

Introducing Annotatability - a powerful new framework to address a major challenge in biological research by examining how artificial neural networks learn to label genomic data. Genomic datasets often contain...

Picking the Right Doctor? AI could Help

Years ago, as she sat in waiting rooms, Maytal Saar-Tsechansky began to wonder how people chose a good doctor when they had no way of knowing a doctor's track record...

From Text to Structured Information Secu…

Artificial intelligence (AI) and above all large language models (LLMs), which also form the basis for ChatGPT, are increasingly in demand in hospitals. However, patient data must always be protected...

AI Innovation Unlocks Non-Surgical Way t…

Researchers have developed an artificial intelligence (AI) model to detect the spread of metastatic brain cancer using MRI scans, offering insights into patients’ cancer without aggressive surgery. The proof-of-concept study, co-led...

Deep Learning Model Helps Detect Lung Tu…

A new deep learning model shows promise in detecting and segmenting lung tumors, according to a study published in Radiology, a journal of the Radiological Society of North America (RSNA)...

One of the Largest Global Surveys of Soc…

As leaders gather for the World Economic Forum Annual Meeting 2025 in Davos, Leaps by Bayer, the impact investing arm of Bayer, and Boston Consulting Group (BCG) announced the launch...

New Study Reveals AI's Transformati…

Intensive care units (ICUs) face mounting pressure to effectively manage resources while delivering optimal patient care. Groundbreaking research published in the INFORMS journal Information Systems Research highlights how a novel...