The neurological ICU (neuro ICU) often suffers from significant limitations due to scarce resource availability for their neurocritical care patients. Neuro ICU patients require frequent neurological evaluations, continuous monitoring of various physiological parameters, frequent imaging, and routine lab testing. This amasses large amounts of data specific to each patient. Neuro ICU teams are often overburdened by the resulting complexity of data for each patient. Machine Learning algorithms (ML), are uniquely capable of interpreting high-dimensional datasets that are too difficult for humans to comprehend. Therefore, the application of ML in the neuro ICU could alleviate the burden of analyzing big datasets for each patient. This review serves to (1) briefly summarize ML and compare the different types of MLs, (2) review recent ML applications to improve neuro ICU management and (3) describe the future implications of ML to neuro ICU management.
Background: 5-aminolevulinic acid (5-ALA) is a valuable surgical adjuvant used for the resection of glioblastoma multiforme (GBM). Since Food and Drug Administration approval in 2017, 5-ALA has been used in over 37,000 cases. The current recommendation for peak efficacy and intraoperative fluorescence is within 4 h after administration. This narrow time window imposes a perioperative time constraint which may complicate or preclude the use of 5-ALA in GBM surgery. Case Description: This case report describes the prolonged activity of 5-ALA in a 66-year-old patient with a newly diagnosed GBM lesion within the left supramarginal gyrus. An awake craniotomy with language and sensorimotor mapping was planned along with 5-ALA fluorescence guidance. Shortly, after receiving the preoperative 5-ALA dose, the patient developed a fever. Surgery was postponed for an infectious disease workup which proved negative. The patient was taken to surgery the following day, 36 h after 5-ALA administration. Despite the delay, intraoperative fluorescence within the tumor remained and was sufficient to guide resection. Postoperative imaging confirmed a gross total resection of the tumor. Conclusion: The use of 5-ALA as an intraoperative adjuvant may still be effective for patients beyond the recommended 4-h window after initial administration. Reconsideration of current use of 5-ALA is warranted.
BACKGROUND:Early ambulation is considered a key element to Enhanced Recovery After Surgery protocol after spine surgery. OBJECTIVE: To investigate whether ambulation less than 8 hours after elective spine surgery is associated with improved outcome. METHODS: The Michigan Spine Surgery Improvement Collaborative database was queried to track all elective cervical and lumbar spine surgery between July 2018 and April 2021. In total, 7647 cervical and 17 616 lumbar cases were divided into 3 cohorts based on time to ambulate after surgery: (1) <8 hours, (2) 8 to 24 hours, and (3) >24 hours. RESULTS: For cervical cases, patients who ambulated 8 to 24 hours (adjusted odds ratio [aOR] 1.38; 95% CI 1.11-1.70; P = .003) and >24 hours (aOR 2.20; 95% CI 1.20-4.03; P = .011) after surgery had higher complication rate than those who ambulated within 8 hours of surgery. Similar findings were noted for lumbar cases with patients who ambulated 8 to 24 hours (aOR 1.31; 95% CI 1.12-1.54; P < .001) and >24 hours (aOR 1.96; 95% CI 1.50-2.56; P < .001) after surgery having significantly higher complication rate than those ambulated <8 hours after surgery. Analysis of secondary outcomes for cervical cases demonstrated that <8-hour ambulation was associated with home discharge, shorter hospital stay, lower 90-day readmission, and lower urinary retention rate. For lumbar cases, <8hour ambulation was associated with shorter hospital stay, satisfaction with surgery, lower 30-day readmission, home discharge, and lower urinary retention rate. CONCLUSION: Ambulation within 8 hours after surgery is associated with significant improved outcome after elective cervical and lumbar spine surgery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.