Project DetailsSpinal surgeries involve procedures near numerous nerves connected to various muscles. Therefore, it's crucial to identify potential injuries during surgery to prevent nerve damage.
A key monitoring tool is electromyography (EMG), which measures muscle activity through electrical potential differences. During surgeries under general anesthesia, minimal activity is expected. Significant irritation in the EMG signal indicates potential nerve damage.
This project aims to develop an algorithm that analyzes EMG signals recorded during surgery and alerts the medical team when there's a potential issue. The algorithm will categorize the signals into three groups: noise, quiet and irritation.
We chose an unsupervised, feature-based model. Initially, a rough separation occurs based on threshold criteria. Signals failing to meet these criteria are then processed through a two-step clustering model utilizing K-means and GMM algorithms.
This is an initial project with a limited set of features. However, our model exhibits excellent separation capabilities, and the promising initial results suggest the feasibility of further development and industry-ready applications.
