Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jun 11;10(6):707.
doi: 10.3390/bioengineering10060707.

Identifying Intraoperative Spinal Cord Injury Location from Somatosensory Evoked Potentials' Time-Frequency Components

Hanlei Li  1 , Songkun Gao  1 , Rong Li  1 , Hongyan Cui  1 , Wei Huang  2 , Yongcan Huang  3 , Yong Hu  1   2   4
Affiliations

Identifying Intraoperative Spinal Cord Injury Location from Somatosensory Evoked Potentials' Time-Frequency Components

Hanlei Li et al. Bioengineering (Basel). .

Abstract

Excessive distraction in corrective spine surgery can lead to iatrogenic distraction spinal cord injury. Diagnosis of the location of the spinal cord injury helps in early removal of the injury source. The time-frequency components of the somatosensory evoked potential have been reported to provide information on the location of spinal cord injury, but most studies have focused on contusion injuries of the cervical spine. In this study, we established 19 rat models of distraction spinal cord injury at different levels and collected the somatosensory evoked potentials of the hindlimb and extracted their time-frequency components. Subsequently, we used k-medoid clustering and naive Bayes to classify spinal cord injury at the C5 and C6 level, as well as spinal cord injury at the cervical, thoracic, and lumbar spine, respectively. The results showed that there was a significant delay in the latency of the time-frequency components distributed between 15 and 30 ms and 50 and 150 Hz in all spinal cord injury groups. The overall classification accuracy was 88.28% and 84.87%. The results demonstrate that the k-medoid clustering and naive Bayes methods are capable of extracting the time-frequency component information depending on the spinal cord injury location and suggest that the somatosensory evoked potential has the potential to diagnose the location of a spinal cord injury.

Keywords: machine learning; naive Bayes; somatosensory evoked potentials; spinal cord injury; time-frequency components.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The data processing flow chart.
Figure 2
Figure 2
The surgical procedure of SCI rat model. (a) Dorsal ligament resection and facet arthrotomy; (b) fixation of the vertebral clamps; (c) return to initial position and data collection.
Figure 3
Figure 3
The waveform and MP-based TFD of an example SEP signal. (a1,a2) The normal group; (b1,b2) the cervical group; (c1,c2) the thoracic group; (d1,d2) the lumbar group.
Figure 4
Figure 4
Silhouette coefficient and classification accuracy for different numbers of clustering centers.
Figure 5
Figure 5
(a) TFD before feature selection and the probability density of TFCs in the direction of latency and frequency; (b) TFD after feature selection and the probability density of TFCs in the direction of latency and frequency. Red, blue, black, and green correspond to the normal, cervical, thoracic, and lumbar groups, respectively.
Figure 6
Figure 6
The overall accuracy of different methods. The clustering method of k-medoids and k-means indicates that feature selection was performed.
Figure 7
Figure 7
TFD of each group after deleting the common features. Red, blue, black, and green correspond to the normal, cervical, thoracic, and lumbar groups, respectively.
Figure 8
Figure 8
Statistical results of parameters of TFCs in ROI. (a) Latency, (b) frequency, and (c) data proportion of TFCs in each ROI. * p < 0.05 (rank sum test), ** p < 0.01 (rank sum test).
See this image and copyright information in PMC

References

    1. Schwartz D.M., Auerbach J.D., Dormans J.P., Flynn J., Drummond D.S., Bowe J.A., Laufer S., Shah S.A., Bowen J.R., Pizzutillo P.D., et al. Neurophysiological detection of impending spinal cord injury during scoliosis surgery. J. Bone Jt. Surg. Am. 2007;89:2440–2449. doi: 10.2106/00004623-200711000-00015. - DOI - PubMed
    1. Biscevic M., Sehic A., Krupic F. Intraoperative neuromonitoring in spine deformity surgery: Modalities, advantages, limitations, medicolegal issues-surgeons’ views. Efort Open Rev. 2020;5:9–16. doi: 10.1302/2058-5241.5.180032. - DOI - PMC - PubMed
    1. Chacko S., McCann M.E., Soriano S.G. Surgery for Scoliosis. In: Seubert C.N., Balzer J.R., editors. Koht, Sloan, Toleikis’s Monitoring the Nervous System for Anesthesiologists and Other Health Care Professionals. Springer International Publishing; Cham, Switzerland: 2023. pp. 591–601.
    1. Nuwer M.R., Emerson R.G., Galloway G., Legatt A.D., Lopez J., Minahan R., Yamada T., Goodin D.S., Armon C., Chaudhry V., et al. Evidence-based guideline update: Intraoperative spinal monitoring with somatosensory and transcranial electrical motor evoked potentials: Report of the Therapeutics and Technology Assessment Subcommittee of the American Academy of Neurology and the American Clinical Neurophysiology Society. Neurology. 2012;78:585–589. - PubMed
    1. Seifert J.L., Bell J.E., Elmer B.B., Sucato D.J., Romero M.I. Characterization of a novel bidirectional distraction spinal cord injury animal model. J. Neurosci. Methods. 2011;197:97–103. doi: 10.1016/j.jneumeth.2011.02.003. - DOI - PubMed

LinkOut - more resources