Decoding pain relief: Electrophysiological markers of chronic pain in spinal cord stimulation

Where

Thomas W. Keating Bioresearch Building (BIO5), Room 103
1657 E. Helen St., Tucson, AZ 85719

Lunch will be provided.

Seminar Objectives:

• Describe neural signatures in chronic pain patients with and without spinal cord stimulation, or SCS.
• Evaluate machine learning models in prediction of SCS outcomes.
• Explore the effective utilization of electrophysiological signals for the advancement of novel SCS technologies.

Abstract:

Chronic pain has been estimated to affect more than 50 million adult Americans and remains one of the most common reasons that patients seek health care. Spinal cord stimulation SCS is an FDA-approved neuromodulation treatment to relieve chronic refractory pain. While SCS can be used effectively in many patients with refractory chronic pain conditions, a significant portion of the patients receive suboptimal pain suppression. Predicting responders also remains a challenge due to a lack of objective pain biomarkers. The utility of machine learning ML models for clinical prediction has become increasingly prevalent in neurosurgical literature recently. Previous work has indicated that electroencephalogram, or EEG, patterns may be correlated with patient-reported outcome measures. Given that SCS treatment of chronic pain still carries challenges and there remains a lack of clear understanding of which patient respond to treatment well, developing predictive models using objective measures would augment the patient selection and pain management approaches. Thus, we aimed to characterize the neural signatures of SCS-induced pain relief and explore the functional utility of peri-operative EEG features to predict which pain patients will be responders to SCS. Our findings suggest that combination of subjective self-reports, pre-operatively and intra-operatively obtained EEGs under SCS on/off conditions and well-designed ML algorithms might be potentially used to distinguish responders and non-responders resulting in refined patient selection and improved patient outcomes.