BackgroundLumbar interbody spinal fusion (LIF) surgeries are performed to treat or prevent back pain in patients with degenerated intervertebral discs and a variety of spinal diseases. However, post-operative neurological complications may ensue. Intraoperative monitoring techniques have been used to predict and potentially reduce the risk of complications. MethodsThis study examined the diagnostic accuracy of significant changes of somatosensory evoked potentials (SSEPs) to evaluate and predict post-operative neurological deficits after LIF. All patients underwent LIF at UPMC from 2010 to 2012. One thousand fifty-seven patients had pre-operative baseline and continuous intraoperative SSEP monitoring. Statistical analysis was completed using SPSS version 22. No relevant disclosure. ResultsPatient outcomes were not significantly affected by age over 65, gender, obesity, and abnormal baselines. Lower extremity (LE) significant changes in SSEPs and LE loss of responses resulted in a sensitivity/specificity of 0.03/0.99 and 0.03/0.99; they had an AUC of 0.54/0.73 with a 95% confidence interval (CI) of [0.34, 0.74]/[0.29, 1.00]. ConclusionsSignificant SSEP changes during LIF are a very specific but poorly sensitive indicator of perioperative neurological deficits. The odds ratio for LE loss of responses was 29.14 with a 95% CI of 1.79-475.5, so LE SSEP loss of responses can serve as a biomarker of perioperative neurological deficits after LIF.