The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review

Background: Artificial intelligence (AI) models have shown potential for diagnosing and prognosticating traumatic spinal cord injury (tSCI), but their clinical utility remains uncertain. Method: ology: The primary aim was to evaluate the performance of AI algorithms in diagnosing and prognosticating...

Full description

Saved in:
Bibliographic Details
Main Authors: Saran Singh Gill, Hariharan Subbiah Ponniah, Sho Giersztein, Rishi Miriyala Anantharaj, Srikar Reddy Namireddy, Joshua Killilea, DanieleS.C. Ramsay, Ahmed Salih, Ahkash Thavarajasingam, Daniel Scurtu, Dragan Jankovic, Salvatore Russo, Andreas Kramer, Santhosh G. Thavarajasingam
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Brain and Spine
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S277252942500027X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850197406364205056
author Saran Singh Gill
Hariharan Subbiah Ponniah
Sho Giersztein
Rishi Miriyala Anantharaj
Srikar Reddy Namireddy
Joshua Killilea
DanieleS.C. Ramsay
Ahmed Salih
Ahkash Thavarajasingam
Daniel Scurtu
Dragan Jankovic
Salvatore Russo
Andreas Kramer
Santhosh G. Thavarajasingam
author_facet Saran Singh Gill
Hariharan Subbiah Ponniah
Sho Giersztein
Rishi Miriyala Anantharaj
Srikar Reddy Namireddy
Joshua Killilea
DanieleS.C. Ramsay
Ahmed Salih
Ahkash Thavarajasingam
Daniel Scurtu
Dragan Jankovic
Salvatore Russo
Andreas Kramer
Santhosh G. Thavarajasingam
author_sort Saran Singh Gill
collection DOAJ
description Background: Artificial intelligence (AI) models have shown potential for diagnosing and prognosticating traumatic spinal cord injury (tSCI), but their clinical utility remains uncertain. Method: ology: The primary aim was to evaluate the performance of AI algorithms in diagnosing and prognosticating tSCI. Subsequent systematic searching of seven databases identified studies evaluating AI models. PROBAST and TRIPOD tools were used to assess the quality and reporting of included studies (PROSPERO: CRD42023464722). Fourteen studies, comprising 20 models and 280,817 pooled imaging datasets, were included. Analysis was conducted in line with the SWiM guidelines. Results: For prognostication, 11 studies predicted outcomes including AIS improvement (30%), mortality and ambulatory ability (20% each), and discharge or length of stay (10%). The mean AUC was 0.770 (range: 0.682–0.902), indicating moderate predictive performance. Diagnostic models utilising DTI, CT, and T2-weighted MRI with CNN-based segmentation achieved a weighted mean accuracy of 0.898 (range: 0.813–0.938), outperforming prognostic models. Conclusion: AI demonstrates strong diagnostic accuracy (mean accuracy: 0.898) and moderate prognostic capability (mean AUC: 0.770) for tSCI. However, the lack of standardised frameworks and external validation limits clinical applicability. Future models should integrate multimodal data, including imaging, patient characteristics, and clinician judgment, to improve utility and alignment with clinical practice.
format Article
id doaj-art-cd851b67d8944bbb8003d5e6309a6bbb
institution OA Journals
issn 2772-5294
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Brain and Spine
spelling doaj-art-cd851b67d8944bbb8003d5e6309a6bbb2025-08-20T02:13:10ZengElsevierBrain and Spine2772-52942025-01-01510420810.1016/j.bas.2025.104208The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic reviewSaran Singh Gill0Hariharan Subbiah Ponniah1Sho Giersztein2Rishi Miriyala Anantharaj3Srikar Reddy Namireddy4Joshua Killilea5DanieleS.C. Ramsay6Ahmed Salih7Ahkash Thavarajasingam8Daniel Scurtu9Dragan Jankovic10Salvatore Russo11Andreas Kramer12Santhosh G. Thavarajasingam13Imperial Brain & Spine Initiative, Imperial College London, London, United Kingdom; Faculty of Medicine, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United Kingdom; Faculty of Medicine, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United Kingdom; Faculty of Medicine, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United KingdomImperial Brain & Spine Initiative, Imperial College London, London, United KingdomDepartment of Neurosurgery, Universitätsmedizin Mainz, Mainz, GermanyDepartment of Neurosurgery, LMU University Hospital, LMU, Munich, GermanyImperial College Healthcare NHS Trust, London, United KingdomDepartment of Neurosurgery, LMU University Hospital, LMU, Munich, GermanyImperial Brain & Spine Initiative, Imperial College London, London, United Kingdom; Department of Neurosurgery, LMU University Hospital, LMU, Munich, Germany; Corresponding author. Department of Neurosurgery, LMU University Hospital, LMU, Munich, Germany.Background: Artificial intelligence (AI) models have shown potential for diagnosing and prognosticating traumatic spinal cord injury (tSCI), but their clinical utility remains uncertain. Method: ology: The primary aim was to evaluate the performance of AI algorithms in diagnosing and prognosticating tSCI. Subsequent systematic searching of seven databases identified studies evaluating AI models. PROBAST and TRIPOD tools were used to assess the quality and reporting of included studies (PROSPERO: CRD42023464722). Fourteen studies, comprising 20 models and 280,817 pooled imaging datasets, were included. Analysis was conducted in line with the SWiM guidelines. Results: For prognostication, 11 studies predicted outcomes including AIS improvement (30%), mortality and ambulatory ability (20% each), and discharge or length of stay (10%). The mean AUC was 0.770 (range: 0.682–0.902), indicating moderate predictive performance. Diagnostic models utilising DTI, CT, and T2-weighted MRI with CNN-based segmentation achieved a weighted mean accuracy of 0.898 (range: 0.813–0.938), outperforming prognostic models. Conclusion: AI demonstrates strong diagnostic accuracy (mean accuracy: 0.898) and moderate prognostic capability (mean AUC: 0.770) for tSCI. However, the lack of standardised frameworks and external validation limits clinical applicability. Future models should integrate multimodal data, including imaging, patient characteristics, and clinician judgment, to improve utility and alignment with clinical practice.http://www.sciencedirect.com/science/article/pii/S277252942500027XtSCISpinal cord injurySpineAIDiagnosisPrognosis
spellingShingle Saran Singh Gill
Hariharan Subbiah Ponniah
Sho Giersztein
Rishi Miriyala Anantharaj
Srikar Reddy Namireddy
Joshua Killilea
DanieleS.C. Ramsay
Ahmed Salih
Ahkash Thavarajasingam
Daniel Scurtu
Dragan Jankovic
Salvatore Russo
Andreas Kramer
Santhosh G. Thavarajasingam
The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review
Brain and Spine
tSCI
Spinal cord injury
Spine
AI
Diagnosis
Prognosis
title The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review
title_full The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review
title_fullStr The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review
title_full_unstemmed The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review
title_short The diagnostic and prognostic capability of artificial intelligence in spinal cord injury: A systematic review
title_sort diagnostic and prognostic capability of artificial intelligence in spinal cord injury a systematic review
topic tSCI
Spinal cord injury
Spine
AI
Diagnosis
Prognosis
url http://www.sciencedirect.com/science/article/pii/S277252942500027X
work_keys_str_mv AT saransinghgill thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT hariharansubbiahponniah thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT shogiersztein thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT rishimiriyalaanantharaj thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT srikarreddynamireddy thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT joshuakillilea thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT danielescramsay thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT ahmedsalih thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT ahkashthavarajasingam thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT danielscurtu thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT draganjankovic thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT salvatorerusso thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT andreaskramer thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT santhoshgthavarajasingam thediagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT saransinghgill diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT hariharansubbiahponniah diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT shogiersztein diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT rishimiriyalaanantharaj diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT srikarreddynamireddy diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT joshuakillilea diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT danielescramsay diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT ahmedsalih diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT ahkashthavarajasingam diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT danielscurtu diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT draganjankovic diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT salvatorerusso diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT andreaskramer diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview
AT santhoshgthavarajasingam diagnosticandprognosticcapabilityofartificialintelligenceinspinalcordinjuryasystematicreview