Artificial Intelligence for Cervical Spine Fracture Detection: A Systematic Review of Diagnostic Performance and Clinical Potential

Global Spine Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 12, 2025

Study Design Systematic review. Objective Artificial intelligence (AI) and deep learning (DL) models have recently emerged as tools to improve fracture detection, mainly through imaging modalities such computed tomography (CT) radiographs. This systematic review evaluates the diagnostic performance of AI DL in detecting cervical spine fractures assesses their potential role clinical practice. Methods A search PubMed/Medline, Embase, Scopus, Web Science was conducted for studies published between January 2000 July 2024. Studies that evaluated detection were included. Diagnostic metrics extracted included sensitivity, specificity, accuracy, area under curve. The PROBAST tool assessed bias, PRISMA criteria used study selection reporting. Results Eleven 2021 2024 demonstrated variable performance, with sensitivity ranging from 54.9% 100% specificity 72% 98.6%. Models applied CT generally outperformed those radiographs, convolutional neural networks (CNN) advanced architectures MobileNetV2 Vision Transformer (ViT) achieving highest accuracy. However, most lacked external validation, raising concerns about generalizability findings. Conclusions show significant improving particularly imaging. While these offer high further validation refinement are necessary before they can be widely integrated into should complement, rather than replace, human expertise workflows.

Language: Английский

---

Performance and clinical implications of machine learning models for detecting cervical ossification of the posterior longitudinal ligament: a systematic review

Asian Spine Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 20, 2025

Ossification of the posterior longitudinal ligament (OPLL) is a significant spinal condition that can lead to severe neurological deficits.Recent advancements in machine learning (ML) and deep (DL) have led development promising tools for early detection diagnosis OPLL.This systematic review evaluated diagnostic performance ML DL models clinical implications OPLL detection.A was conducted following Preferred Reporting Items Systematic Reviews Meta-Analyses guidelines.PubMed/Medline Scopus databases were searched studies published between January 2000 September 2024.Eligible included those utilizing or using imaging data.All assessed risk bias appropriate tools.The key metrics, including accuracy, sensitivity, specificity, area under curve (AUC), analyzed.Eleven studies, comprising total 6,031 patients, included.The demonstrated high performance, with accuracy rates ranging from 69.6% 98.9% AUC values up 0.99.Convolutional neural networks random forest most used approaches.The overall moderate, concerns primarily related participant selection missing data.In conclusion, show great potential accurate OPLL, particularly when integrated techniques.However, ensure applicability, further research warranted validate these findings more extensive diverse populations.

Language: Английский

---

The Role of Artificial Intelligence in Diagnostic Neurosurgery: A Systematic Review

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 4, 2025

Background: Artificial intelligence (AI) is increasingly applied in diagnostic neurosurgery, enhancing precision and decision-making neuro-oncology, vascular, functional, spinal subspecialties. Despite its potential, variability outcomes necessitates a systematic review of performance applicability. Methods: A comprehensive search PubMed, Cochrane Library, Embase, CNKI, ClinicalTrials.gov was conducted from January 2020 to 2025. Inclusion criteria comprised studies utilizing AI for reporting quantitative metrics. Studies were excluded if they focused on non-human subjects, lacked clear metrics, or did not directly relate applications neurosurgery. Risk bias assessed using the PROBAST tool. This study registered PROSPERO, number CRD42025631040 26^th, Results: Within 186 studies, neural networks (29%) hybrid models (49%) dominated. categorised into neuro-oncology (52.69%), vascular neurosurgery (19.89%), functional (16.67%), (11.83%). Median accuracies exceeded 85% most categories, with achieving high accuracy tumour detection, grading, segmentation. Vascular excelled stroke intracranial haemorrhage median AUC values 97%. Functional showed promising results, though sensitivity specificity underscores need standardised datasets validation. Discussion: The review’s limitations include lack data weighting, absence meta-analysis, limited collection timeframe, quality, risk some studies. Conclusion: AI shows potential improving across neurosurgical domains. Models used stroke, ICH, aneurysm conditions such as Parkinson’s disease epilepsy demonstrate results. However, sensitivity, specificity, further research model refinement ensure clinical viability effectiveness.

Language: Английский

---

From the Editor-in-Chief: Featured Articles in the September 2024 Issue

Neurospine, Journal Year: 2024, Volume and Issue: 21(3), P. 743 - 744

Published: Sept. 27, 2024

Language: Английский

---

Commentary on “Artificial Intelligence Detection of Cervical Spine Fractures Using Convolutional Neural Network Models”

Neurospine, Journal Year: 2024, Volume and Issue: 21(3), P. 842 - 844

Published: Sept. 27, 2024

Language: Английский

---