Related Experiment Video
Updated: Jun 6, 2025
08:41
A MRI-Based Toolbox for Neurosurgical Planning in Nonhuman Primates
Published on: July 17, 2020
4.9K
Machine Learning Algorithms for Neurosurgical Preoperative Planning: A Scoping Review
Jhon E Bocanegra-Becerra1, Julia Sader Neves Ferreira2, Gabriel Simoni3
1Academic Department of Surgery, School of Medicine, Universidad Peruana Cayetano Heredia, Lima, Peru.
World Neurosurgery
|November 22, 2024
Summary
Machine learning (ML) algorithms are emerging for preoperative neurosurgical planning, offering automated data processing and individualized patient approaches. Further validation is needed to ensure robustness and transparency for clinical integration.
Area of Science:
- Neurosurgery
- Medical Informatics
- Artificial Intelligence
Background:
- Preoperative neurosurgical planning is critical for patient safety and reducing complications.
- Machine learning (ML) offers advantages in processing large datasets for improved surgical planning.
- The application of ML in brain and spine surgery preoperative planning is an evolving area of research.
Purpose of the Study:
- To explore the evolving applications of ML algorithms in preoperative planning for brain and spine surgery.
- To review the current state of ML in neurosurgical preoperative planning.
Main Methods:
- A scoping review was conducted using PubMed, Embase, and Web of Science databases.
- Included studies described ML for preoperative planning in brain and spine surgery.
- Data extracted included neurosurgical field, patient features, ML technology, and algorithm advantages/limitations.
Main Results:
- Eight studies met inclusion criteria, involving 518 patients and various ML algorithms (e.g., CNNs, logistic regression, random forest).
- ML applications spanned functional neurosurgery, tumor surgery, and spine surgery.
- Key advantages included automated data processing and individualized treatment support, while limitations involved processing time, bias, and generalizability.
Conclusions:
- ML algorithms show potential for efficient, automated, and safe neurosurgical planning.
- Further validation is required to assess objective performance across diverse clinical settings.
- Enhancing ML robustness, transparency, and understanding is crucial for neurosurgical practice integration.
