A Hybrid Knowledge- and Data-driven Model for Automatic Assessment of Chemically Induced Spiking Patterns in C-fiber Microneurography

Analyzing temporal spike patterns in nociceptors recorded via microneurography is challenging due to the use of a single recording electrode, waveform variability, and high similarity of spike shapes across neurons limiting interpretation of sensory coding such as pain and itch. We present a data-driven, supervised spike sorting approach to improve the analysis of nociceptive discharges, identified through activity-dependent conduction velocity changes. Our method integrates three feature sets and applies machine learning models including one-class SVM, SVM, and XGBoost. Validation used experimentally derived ground truth data acquired by controlled electrical stimulation, allowing precise spike time-locking. Compared to Spike2 software, our approach achieved higher F1-scores and reduced false positives, indicating improved spike sorting. Although XGBoost achieved the highest median F1-scores, optimal performance was dependent on individual combinations of feature sets and models for each recording. In some recordings with many nerve fibers and a low signal-to-noise ratio, reliable sorting was not feasible. This highlights the necessity to determine sortability and optimal configures using a ground truth protocol for each recording. These findings represent an important step toward reliable analysis of nociceptive activity. The openly accessible framework supports analyzing pruritogen-induced and spontaneous activity in neuropathic pain patients, advancing tools for peripheral neural decoding.