Active Brain & Nervous System Mental Health

PaiNeuro: Towards objective PAIn measurement using NEUROphysiological signals

In plain English

AI plain-English summary

A patient undergoing a colonoscopy will wear a lightweight EEG cap that records their brain's electrical signals in real time, as part of a systematic effort to build the first objective, machine-readable measure of pain. Pain is currently assessed through self-reporting scales, which are subjective and can lead to under-treatment, over-reliance on opioids, and unequal care across different patient groups. This project tackles that gap by collecting EEG data during a standardised medical procedure—colonoscopy—where pain occurs predictably. Machine learning will then sift through the brain's electrical patterns to identify reliable biomarkers that signal pain, independent of a patient's verbal report. If successful, the work could give clinicians a real-time, objective pain gauge, enabling more personalised treatment plans and reducing opioid prescriptions. It would also help address long-standing disparities in pain assessment, where subjective reports can be biased by a patient's background or communication ability. Beyond the clinic, the EEG-based biomarkers could transform fundamental pain research, offering a window into the neural dynamics of pain perception that self-reports cannot provide.

View original technical description
The "PaiNeuro" project aims to advance pain management by developing objective measure of pain using electroencephalography (EEG). Pain, a complex and subjective experience, is traditionally assessed through self-reporting methods like the visual-analogue scale (VAS), which can be influenced by various factors. This subjectivity often leads to inadequate pain management and contributes to opioid overprescription, while also perpetuating health disparities in pain assessment. The project addresses the challenge of creating an objective, reliable, and clinically applicable method for pain assessment. A key component is the systematic collection of EEG data during colonoscopies, which provides an ideal setting due to its standardized nature and predictable pain occurrences. This approach facilitates the application of advanced machine learning techniques to identify reliable EEG biomarkers of pain, with the potential to generalize across patients. EEG is a non-invasive, cost-effective, portable and easy to perform method that records electrical signals from the brain using electrodes placed on the scalp. These electrodes detect the brain’s electrical activity which is commonly used to diagnose conditions such as epilepsy, brain injuries and sleep disorders. The time resolution of EEG is very high and allows capturing the dynamics of pain perception in real-time. This makes EEG the ideal method for developing an objective measure of pain. Previous studies have shown that pain perception changes the electrical activity of the brain. However further research is needed to standardise EEG-based measures of pain and realise their potential in clinical settings. The project's objectives include (1) collecting comprehensive EEG data during colonoscopies, (2) using machine learning to identify pain biomarkers, and (3) facilitating the translation of objective pain measurements into clinical practice by obtaining feedback from clinicians and patients and immersing the project lead Dr. Halder in the clinical environment. The potential benefits are significant, including enhanced pain management practices, more personalized treatment plans, reduced reliance on opioids, and addressing health disparities. Beyond clinical applications, the project promises to advance pain research by improving our understanding of neural mechanisms underlying pain. The proposed team is ideally suited for this project. Dr. Halder brings expertise in EEG signal processing and brain-computer interfaces. Dr. Juel's experience in EEG recording techniques during anaesthesia ensures high-quality data collection in clinical settings. Dr. Ernst's clinical insights and role in patient recruitment are essential for integrating these methodologies into clinical practice. This project is particularly ideal for Dr. Halder's career development. It aligns with his research interests in EEG and pain, positioning him as a leader in this emerging field. The interdisciplinary nature of the project will enhance his collaboration skills across neuroscience, neural engineering, and clinical practice. Working in a clinical environment at Vestre Viken will provide valuable insights into practical challenges, informing the development research that can be translated into clinical practice. The project's potential for high-impact publications and future grant applications will significantly boost Dr. Halder's research profile. Moreover, the skills developed in clinical research and patient interaction will be invaluable for his career progression, aligning well with EPSRC's emphasis on fostering innovative health technologies and interdisciplinary approaches. Overall, the "PaiNeuro" project represents a significant advancement in pain management, with implications for policymakers, the wider research community, and the public. By addressing a critical gap in current healthcare practices, it aims to improve patient outcomes and contribute to broader societal benefits.

View the original record at the funder ↗

Researchers

Bjørn Juel (Co-Investigator)Gernot Ernst (Co-Investigator)Sebastian Halder (Principal Investigator)

Related Research

Grants with similar aims, by meaning.

A Novel Artificial Intelligence Powered Neuroimaging Biomarker for Chronic Pain.
EPIONE: Effective Pain Interventions with Neural Engineering
Multimodal assessment of post-operative, ongoing pain in infants utilising video analytics, audio data,vital signs and EEG
The Role of Learning in Chronic Musculoskeletal Pain
Multiplex microneurography: a pathway to stratified pain generator diagnostics.

Original classification

Research and Innovation

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.