AUTHOR=Jiang Wenbin , Zhan Qijia , Wang Junlu , Wei Min , Li Sen , Mei Rong , Xiao Bo 

TITLE=Quantitative identification of ventral/dorsal nerves through intraoperative neurophysiological monitoring by supervised machine learning

JOURNAL=Frontiers in Pediatrics

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/pediatrics/articles/10.3389/fped.2023.1118924

DOI=10.3389/fped.2023.1118924

ISSN=2296-2360

ABSTRACT=Objective: To investigate the electro-neurophysiological characteristics of the motor and sensory nerves at L2 segment in a quantitative manner.
Methods: Medical records of consecutive patients who underwent single-level approach selective dorsal rhizotomy (SDR) from Jun. 2019 to Jan. 2022 were retrospectively reviewed. Intraoperative electro-neurophysiological data were analyzed. 
Results: 74 male and 27 female were included in the current study with a mean age of 6.2 years old. Quadriceps and adductors were two main muscle groups innervated by L2 nerve roots in both motor and sensory fibers. A significant difference could be found in the latency of adductors with abnormal/normal muscle tension. Sensory roots have higher threshold than motor ones, and muscles first reached 200 μV innervated by sensory roots have longer latency and smaller CMAP than by motor ones. Supervised machine learning can distinguish motor/sensory roots using threshold + latency or threshold + CMAP as predictors efficiently. 
Conclusions: Electro-neurophysiological parameters could be used to differentiate motor/sensory fibers during SDR efficiently.