New AI-enabled fiber optic sensor could help monitor brain damage | Imperial News


A new AI-enabled fiber optic sensor device developed at Imperial College London can simultaneously measure key biomarkers of traumatic brain injury

“Promising” results from animal brain tissue testing suggest it could help clinicians better monitor both disease progression and patient response to treatment than is currently possible, indicating the high potential for future diagnostic trials in humans.

People who sustain a severe blow to the head, such as in road traffic accidents, can suffer from traumatic brain injury (TBI) – a leading cause of death and disability worldwide that can lead to long-term hardship. term with memory, concentration and problem solving.

Our promising results […] after further development, could help clinicians monitor both patients’ brain health and their response to treatment. Dr. Yubing Hu

Head injuries should be continuously monitored during treatment. For this reason, intracranial probes are used in neurocritical care settings to monitor key indicators of injury progression, called biomarkers, such as pressure and oxygen in the brain.

Some of these probes can only measure one biomarker at a time. Others can monitor multiple biomarkers, but require multiple tubes inserted into the brain to do so, risking further tissue damage or infection.

Imperial researchers have now developed a patient monitoring system to monitor multiple biomarkers after traumatic brain injury. The device combines the ability to monitor four biomarkers at once with machine learning algorithms that use previous data to predict biomarker concentrations based on data obtained in real time. If optimized and proven for use in humans, the device could help hospitals monitor TBI more effectively.

Lead author Dr Yubing Hu, from Imperial’s Department of Chemical Engineering, said: “This is a promising breakthrough. Our promising results point to both accurate biomarker monitoring and accurate predictions of injury progression that, after further development, could help clinicians monitor both patients’ brain health and their response to treatment.

The research is published in Question.

Test the device

The device includes a flexible, silica-based optical fiber that is inserted into brain tissue to monitor cerebrospinal fluid (CSF) – the fluid that surrounds the brain and spinal cord. Attached to the end of the fiber, four detection films simultaneously and continuously measure the levels of one biomarker each in the CSF: pH, temperature, dissolved oxygen and glucose. Films are coated with a black sheath to reduce background noise and improve data accuracy.

To test the device, the researchers continuously monitored the levels of these biomarkers in a lamb brain under various states. The lamb’s brain, which had not undergone TBI and was therefore healthy, was suspended in artificial CSF that the researchers could modify at will to mimic the brain chemistry of mild and severe TBIs.

Illustration of the device in the brain connected to a light source, a spectrometer and a microcomputer via Y-type fiber cables

They first measured biomarkers in healthy CSF, before moving on to measuring them in mild and then severe TBI states. To mimic the scenario when TBI patients improve from medical treatments, they then measured again in the mild TBI state.

First author Yuqian Zhang, a PhD candidate from the Department of Chemical Engineering, said, “Our device collects a range of medical data that is currently only achievable with many different sensors. The fiber optic sensor device integrated with artificial intelligence (AI) to reduce interference. »

Co-author Dr Nan Jiang from Sichuan University said: “The device demonstrated high accuracy in the continuous measurement of each biomarker during healthy, mild and severe TBI.

Dynamic monitoring

Its high performance included high sensitivity (ability to detect minute amounts of biomarkers), selectivity (ability to discern between biomarkers), stability (ability to provide long-term monitoring with minimal signal drift), biocompatibility (ability for the sensor to safely interact with brain tissue during long-term implantation) and robustness.

Machine learning models were able to accurately predict biomarker concentrations in real time using readings from a library of previous measurements. It was also able to identify the transition between the different stages of the TBI simulated by the researchers.

Dr Ali Yetisen, who led the research team from the Department of Chemical Engineering, said: “Our study showed the ability of the device to dynamically monitor multiple biomarkers to assess metabolic changes in the brain. It continuously reflects the state of the injury, which could help neurosurgeons accurately track disease progression to make evidence-based clinical decisions and treatment.

Researchers are continuing to develop the sensor using optical beams to expand the range of testable biomarkers, such as inflammatory agents and neurotransmitters. They are also developing a more complex machine learning system to make the most of available data and predictive mechanisms. They also note that more tests using live animals are needed to assess whole-body response to the probe and to test the capability of the fiber sensor in real-world applications.

This research was funded by the Royal Society and the Royal Society of Chemistry.

“Multiplexed Fiber Optic Sensors for Dynamic Brain Monitoring” by Yuqian Zhang, Yubing Hu, Qiao Liu, Kai Lou, Shuhan Wang, Naihan Zhang, Nan Jiang, and Ali K. Yetisen is published in Question.


About Author

Comments are closed.