Objective: Loss of resistance (LOR) is a widely accepted method for performing epidural punctures in clinical settings. However, the risk of failure associated with LOR is still high. Solutions based either on Fiber Bragg grating sensors (FBG) or on artificial intelligence (AI) are gaining ground for supporting clinicians during this kind of procedure. Here, for the first time, we combined the mentioned two technologies to perform an AI-driven LOR identification based on data collected by a custom FBG sensor.
Methods: This study presented two contributions (i.e., automatic labeling and identification) based on machine learning to support epidural procedures by enhancing LOR detection. The methods were tested using data collected by a customized FBG-based flexible cap on 10 patients affected by chronic back pain.
Results: The automatic labeling can retrospectively identify every LOR event for each subject under consideration. This serves as the labeling for the automatic identification task, which emulates the real-time application of LOR detection. A Support Vector Machine, trained using a Leave-One-Out strategy, demonstrates high accuracy in identifying all LOR events while maintaining a minimal rate of false positives.
Conclusion: Our findings revealed the promising performance of the proposed AI-based approach for automatic LOR detection. Thus, their combination with FBG technology can potentially improve the level of support offered to clinicians in this application.
Significance: The integration of AI and FBG technologies holds the promise of revolutionizing LOR detection, reducing the likelihood of unsuccessful epidural punctures and advancing pain management.