Clinical predictions using artificial intelligence in neurosurgery and its subspecialties: a systematic review and meta-analysis
Abstract
Artificial intelligence models for clinical prediction are proliferating across neurosurgery, but their aggregate discriminative performance, distribution along the care pathway and methodological quality are unclear. We systematically reviewed and meta-analysed these studies in neurosurgery and its subspecialities along with their risk of bias appraisal. We performed a PRISMA search for peer-reviewed original studies using AI to predict a clinical outcome in neurosurgical populations. Metrics were pooled using random effects modelling. Each study was classified as diagnostic, prognostic or forecasting and was assigned an evidence level. Clinical prediction task sub-stratification analysis was performed. Risk-of-bias was assessed using PROBAST. 1063 studies were included. Across 451 studies reporting AUC, pooled discrimination was 0.86, ranging from 0.84 (spine) to 0.87 (neuro-oncology), with extreme heterogeneity. Performance varied by clinical pathway stage, highest for diagnosis, grading and molecular tasks and lowest for post-operative tasks. Only 51 studies were using prospective data with external validation, whereas 619 rested on internal validation alone or no validation. 89 percent studies were at high risk-of-bias, driven by the analysis domain. AI models report high performance across all the neurosurgical subspecialities, concordant across AUC, accuracy, sensitivity and specificity and robust to risk-of-bias stratification. Performance is highest for imaging-anchored diagnostic tasks and lowest at decision-facing post-operative stage. However, the literature is dominated by optimism-prone, internally-validated and poorly calibrated models with extreme heterogeneity. External validation, calibration analysis and reporting guidelines adherence remain prerequisites for clinical adoption.
Versions
Related
- Artificial intelligence in cardiology: an evidence map across subspecialties, 2014-26.
- From digital reminders to artificial intelligence–enabled understanding: can personalized treatment predictions improve therapeutic adherence?
- Generative Artificial Intelligence Models in Breast Cancer Diagnosis: A Systematic Review
- Utility of Artificial Intelligence in Detecting Lymph Node Metastasis in Oral Cancer: A Systematic Review
- External validation of artificial intelligence-guided electrocardiogram (AI-ECG) in detecting asymptomatic left ventricular dysfunction: A systematic review and meta-analysis
BibTeX
@misc{ghimire2026clinical,
title = {{Clinical predictions using artificial intelligence in neurosurgery and its subspecialties: a systematic review and meta-analysis}},
author = {Prajwal Ghimire and Aswin Chari and Jonathan Shapey and Keyoumars Ashkan},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.12385},
eprint = {2611.12385},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.12385},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Clinical predictions using artificial intelligence in neurosurgery and its subspecialties: a systematic review and meta-analysis
AU - Prajwal Ghimire
AU - Aswin Chari
AU - Jonathan Shapey
AU - Keyoumars Ashkan
PY - 2026
DA - 2026/11/09
PB - arXiv
DO - 10.48550/arxiv.2611.12385
UR - https://arxiv.org/abs/2611.12385
AB - Artificial intelligence models for clinical prediction are proliferating across neurosurgery, but their aggregate discriminative performance, distribution along the care pathway and methodological quality are unclear. We systematically reviewed and meta-analysed these studies in neurosurgery and its subspecialities along with their risk of bias appraisal. We performed a PRISMA search for peer-reviewed original studies using AI to predict a clinical outcome in neurosurgical populations. Metrics were pooled using random effects modelling. Each study was classified as diagnostic, prognostic or forecasting and was assigned an evidence level. Clinical prediction task sub-stratification analysis was performed. Risk-of-bias was assessed using PROBAST. 1063 studies were included. Across 451 studies reporting AUC, pooled discrimination was 0.86, ranging from 0.84 (spine) to 0.87 (neuro-oncology), with extreme heterogeneity. Performance varied by clinical pathway stage, highest for diagnosis, grading and molecular tasks and lowest for post-operative tasks. Only 51 studies were using prospective data with external validation, whereas 619 rested on internal validation alone or no validation. 89 percent studies were at high risk-of-bias, driven by the analysis domain. AI models report high performance across all the neurosurgical subspecialities, concordant across AUC, accuracy, sensitivity and specificity and robust to risk-of-bias stratification. Performance is highest for imaging-anchored diagnostic tasks and lowest at decision-facing post-operative stage. However, the literature is dominated by optimism-prone, internally-validated and poorly calibrated models with extreme heterogeneity. External validation, calibration analysis and reporting guidelines adherence remain prerequisites for clinical adoption.
ER -