Vol. 1 No. 4 (2025), Original Article
Vol. 1 No. 4 (2025)

Human Readers versus AI-Based Systems in ASPECTS Scoring for Acute Ischemic Stroke: A Systematic Review and Meta-Analysis with Region-Specific Guidance

Original Article
Published 2025-05-17
Ahmed Y Azzam
Director of Clinical Research and Clinical Artificial Intelligence, American Society for Inclusion, Diversity, and Health Equity (ASIDE), Delaware, USA. image/svg+xml
https://orcid.org/0000-0002-4256-0159
Ibrahim Hadadi
Department of Radiological Sciences, College of Applied Medical Sciences, King Khalid University, Abha, Saudi Arabia. image/svg+xml
Leen M. Al-Shahrani
Department of Radiological Sciences, College of Applied Medical Sciences, King Khalid University, Abha, Saudi Arabia. image/svg+xml
Ummkulthum A. Shanqeeti
College of Medicine, Taibah University, Madinah, Saudi Arabia. image/svg+xml
Noor A. Alqurqush
College of Medicine, King Faisal University, Al-Ahsa, Saudi Arabia. image/svg+xml
Mohammed A. Alsehli
College of Medicine, Ummul Al Qura University, Makkah, Saudi Arabia. image/svg+xml
Rudaynah S. Alali
College of Medicine, King Faisal University, Al-Ahsa, Saudi Arabia. image/svg+xml
Mahmoud M. Morsy
American Society for Inclusion, Diversity, and Equity in Healthcare, Lewes, Delaware, USA.
https://orcid.org/0009-0001-4356-5306
Muhammed Amir Essibayi
Department of Neurological Surgery, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA. image/svg+xml
https://orcid.org/0000-0001-8325-2382
PDF
Supplementary File

Keywords

Ischemic Stroke
Artificial Intelligence
ASPECTS
Machine Learning
Imaging

Categories

How to Cite

1.
Azzam AY, Hadadi I, Al-Shahrani LM, et al. Human Readers versus AI-Based Systems in ASPECTS Scoring for Acute Ischemic Stroke: A Systematic Review and Meta-Analysis with Region-Specific Guidance. ASIDE Int Med. 2025;1(4):1-9. doi:10.71079/ASIDE.IM.05172573
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Funding data

Abstract

Introduction: The Alberta Stroke Program Early CT Score (ASPECTS) is widely used to evaluate early ischemic changes and guide thrombectomy decisions in acute stroke patients. However, significant interobserver variability in manual ASPECTS assessment presents a challenge. Recent advances in artificial intelligence have enabled the development of automated ASPECTS scoring systems; however, their comparative performance against expert interpretation remains insufficiently studied.

Methods: We conducted a systematic review and meta-analysis following PRISMA 2020 guidelines. We searched multiple scientific databases for studies comparing automated and manual ASPECTS on Non-Contrast Computed Tomography (NCCT). Interobserver reliability was assessed using pooled interclass correlation coefficients (ICCs). Subgroup analyses were made using software types, reference standards, time windows, and computed tomography-based factors.

Results: Eleven studies with a total of 1,976 patients were included. Automated ASPECTS demonstrated good reliability against reference standards (ICC: 0.72), comparable to expert readings (ICC: 0.62). RAPID ASPECTS performed highest (ICC: 0.86), especially for high-stakes decision-making. AI advantages were most significant with thin-slice CT (≤2.5mm; +0.16), intermediate time windows (120-240min; +0.16), and higher NIHSS scores (p=0.026).

Conclusion: AI-driven ASPECTS systems perform comparably or even better in some cases than human readers in detecting early ischemic changes, especially in specific scenarios. Strategic utilization focusing on high-impact scenarios and region-specific performance patterns offers better diagnostic accuracy, reduced interpretation times, and better and wiser treatment selection in acute stroke care.

PDF
Supplementary File

References

1. Global, regional, and national burden of stroke and its risk factors, 1990-2019: a systematic analysis for the Global Burden of Disease Study 2019. The Lancet Neurology. 2021: 795 [PMID: 34487721, https://doi.org/10.1016/s1474-4422(21)00252-0]

2. Steinmetz JD, Seeher KM, Schiess N, Nichols E, Cao B, Servili C, Cavallera V, Cousin E, Hagins H, Moberg MEJTLN. Global, regional, and national burden of disorders affecting the nervous system, 1990–2021: a systematic analysis for the Global Burden of Disease Study 20212024: 344

3. Sarraj A, Hassan AE, Abraham MG, Ortega-Gutierrez S, Kasner SE, Hussain MS, Chen M, Blackburn S, Sitton CW, Churilov LJNEJoM. Trial of endovascular thrombectomy for large ischemic strokes2023: 1259

4. Schröder J, Thomalla GJFin. A critical review of Alberta Stroke Program Early CT Score for evaluation of acute stroke imaging2017: 245

5. Garg J, Anand K, Duggal A, Bhattacharya AJAJCD, Stroke. Relevance of Non-Contrast Computed Tomography (NCCT) Based Alberta Stroke Program Early CT Score (ASPECTS) in Predicting Severity of Acute Ischemic Stroke at Presentation and Its Functional and Cognitive Outcome at 90 Days2024: 1092

6. Brinjikji W, Abbasi M, Arnold C, Benson JC, Braksick SA, Campeau N, Carr CM, Cogswell PM, Klaas JP, Liebo GBJIN. e-ASPECTS software improves interobserver agreement and accuracy of interpretation of aspects score2021: 781

7. Goebel J, Stenzel E, Guberina N, Wanke I, Koehrmann M, Kleinschnitz C, Umutlu L, Forsting M, Moenninghoff C, Radbruch AJN. Automated ASPECT rating: comparison between the Frontier ASPECT Score software and the Brainomix software2018: 1267

8. Hoelter P, Muehlen I, Goelitz P, Beuscher V, Schwab S, Doerfler AJN. Automated ASPECT scoring in acute ischemic stroke: comparison of three software tools2020: 1231

9. Touati H, Alasiry A, Al-Junaid A, Sellami L, Hamida YB, Hamida AB, Mahfoudh KBJJoI, Graphics. Contribution to an Advanced Clinical Aided Tool Dedicated to Explore ASPECTS Score of Ischemic Stroke2024:

10. Kiththiworaphongkich W, Khamwongsa N, Chaimongkol PJTAJoR. Reliability and radiologists’ concordance of artificial intelligence (AI)-calculated Alberta Stroke Program Early CT Score (ASPECTS)2024: 256

11. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, Shamseer L, Tetzlaff JM, Akl EA, Brennan SE, Chou R, Glanville J, Grimshaw JM, Hrobjartsson A, Lalu MM, Li T, Loder EW, Mayo-Wilson E, McDonald S, McGuinness LA, Stewart LA, Thomas J, Tricco AC, Welch VA, Whiting P, Moher D. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. Revista espanola de cardiologia (English ed). 2021: 790 [PMID: 34446261, https://doi.org/10.1016/j.rec.2021.07.010]

12. Phan K, Saleh S, Dmytriw AA, Maingard J, Barras C, Hirsch JA, Kok HK, Brooks M, Chandra RV, Asadi H. Influence of ASPECTS and endovascular thrombectomy in acute ischemic stroke: a meta-analysis. Journal of neurointerventional surgery. 2019: 664 [PMID: 30415223, https://doi.org/10.1136/neurintsurg-2018-014250]

13. Mortimer A, Flood R, Dunkerton S, McClelland SB, Minks D, Crossley R, Wareham J, Smith A, Cox A, Bosnell R. Is there a simple and accessible solution to improve acute infarct core imaging? The utility of steady-state CT angiographic source images obtained from a delayed phase acquisition. Interventional neuroradiology : journal of peritherapeutic neuroradiology, surgical procedures and related neurosciences. 2025: 15910199251315790 [PMID: 39871790, https://doi.org/10.1177/15910199251315790]

14. Liu CF, Li J, Kim G, Miller MI, Hillis AE, Faria AV. Automatic comprehensive aspects reports in clinical acute stroke MRIs. Scientific reports. 2023: 3784 [PMID: 36882475, https://doi.org/10.1038/s41598-023-30242-6]

15. Adamou A, Beltsios ET, Bania A, Gkana A, Kastrup A, Chatziioannou A, Politi M, Papanagiotou PJJoNS. Artificial intelligence-driven ASPECTS for the detection of early stroke changes in non-contrast CT: a systematic review and meta-analysis2023: e298

16. Delio PR, Wong ML, Tsai JP, Hinson H, McMenamy J, Le TQ, Prabhu D, Mann BS, Copeland K, Kwok KJJoS, Diseases C. Assistance from automated ASPECTS software improves reader performance2021: 105829

17. Kuang H, Qiu W, Najm M, Dowlatshahi D, Mikulik R, Poppe AY, Puig J, Castellanos M, Sohn SI, Ahn SHJIjos. Validation of an automated ASPECTS method on non-contrast computed tomography scans of acute ischemic stroke patients2020: 528

18. Wolff L, Berkhemer OA, van Es AC, van Zwam WH, Dippel DW, Majoie CB, van Walsum T, van der Lugt A, Neuroradiology MCIJ. Validation of automated Alberta Stroke Program Early CT Score (ASPECTS) software for detection of early ischemic changes on non-contrast brain CT scans2021: 491

19. Neuhaus A, Seyedsaadat SM, Mihal D, Benson JC, Mark I, Kallmes DF, Brinjikji WJJons. Region-specific agreement in ASPECTS estimation between neuroradiologists and e-ASPECTS software2020: 720

20. Goebel J, Stenzel E, Zuelow S, Kleinschnitz C, Forsting M, Moenninghoff C, Radbruch AJAR. Computer aided diagnosis for ASPECT rating: initial experiences with the Frontier ASPECT score software2019: 1673

21. Li L, Chen Y, Bao Y, Jia X, Wang Y, Zuo T, Zhu FJCR. Comparison of the performance between Frontier ASPECTS software and different levels of radiologists on assessing CT examinations of acute ischaemic stroke patients2020: 358

22. Albers GW, Wald MJ, Mlynash M, Endres J, Bammer R, Straka M, Maier A, Hinson HE, Sheth KN, Taylor Kimberly WJS. Automated calculation of Alberta Stroke Program Early CT Score: validation in patients with large hemispheric infarct2019: 3277

23. Guberina N, Dietrich U, Radbruch A, Goebel J, Deuschl C, Ringelstein A, Köhrmann M, Kleinschnitz C, Forsting M, Mönninghoff CJN. Detection of early infarction signs with machine learning-based diagnosis by means of the Alberta Stroke Program Early CT score (ASPECTS) in the clinical routine2018: 889

24. Kuang H, Najm M, Chakraborty D, Maraj N, Sohn S, Goyal M, Hill M, Demchuk A, Menon B, Qiu WJAjon. Automated ASPECTS on noncontrast CT scans in patients with acute ischemic stroke using machine learning2019: 33

25. Cagnazzo F, Derraz I, Dargazanli C, Lefevre P-H, Gascou G, Riquelme C, Bonafe A, Costalat VJJoNS. Mechanical thrombectomy in patients with acute ischemic stroke and ASPECTS≤ 6: a meta-analysis2020: 350

26. Lei C, Zhou X, Chang X, Zhao Q, Zhong LJJoS, Diseases C. Mechanical thrombectomy in patients with acute ischemic stroke and ASPECTS≤ 52021: 105748

27. Orscelik A, Matsukawa H, Elawady SS, Sowlat MM, Cunningham C, Zandpazandi S, Kasem RA, Maier I, Jabbour P, Kim J-TJJos, diseases c. Comparative outcomes of mechanical thrombectomy in acute ischemic stroke patients with ASPECTS 2-3 vs. 4-52024: 107528

28. Mihalicz P, Herweh C, Nagel S, Ringleb PA, Bendszus M, Mohlenbruch M, Neuberger UJCN. [190] Clinical utility of automatically derived acute ischemic volumes on native computed tomography in patients with anterior acute ischemic stroke and endovascular therapy2021: S37

29. Brugnara G, Neuberger U, Mahmutoglu MA, Foltyn M, Herweh C, Nagel S, Schönenberger S, Heiland S, Ulfert C, Ringleb PAJS. Multimodal predictive modeling of endovascular treatment outcome for acute ischemic stroke using machine-learning2020: 3541

30. Dvorníková K, Kunešová V, Ostrý S, Mikulík R, Bar M. The e-STROKE Study: The Design of a Prospective Observational Multicentral Study. Journal of cardiovascular development and disease. 2025: [PMID: 39852295, https://doi.org/10.3390/jcdd12010017]

31. Mair G, White P, Bath PM, Muir KW, Al-Shahi Salman R, Martin C, Dye D, Chappell FM, Vacek A, von Kummer R, Macleod M, Sprigg N, Wardlaw JM. External Validation of e-ASPECTS Software for Interpreting Brain CT in Stroke. Annals of neurology. 2022: 943 [PMID: 36053916, https://doi.org/10.1002/ana.26495]

32. Potreck A, Weyland CS, Seker F, Neuberger U, Herweh C, Hoffmann A, Nagel S, Bendszus M, Mutke MA. Accuracy and Prognostic Role of NCCT-ASPECTS Depend on Time from Acute Stroke Symptom-onset for both Human and Machine-learning Based Evaluation. Clinical neuroradiology. 2022: 133 [PMID: 34709408, https://doi.org/10.1007/s00062-021-01110-5]

33. Ferreti LA, Leitao CA, Teixeira BCA, Lopes Neto FDN, ZÉtola VF, Lange MC. The use of e-ASPECTS in acute stroke care: validation of method performance compared to the performance of specialists. Arquivos de neuro-psiquiatria. 2020: 757 [PMID: 33331512, https://doi.org/10.1590/0004-282x20200072]

34. Nagel S, Sinha D, Day D, Reith W, Chapot R, Papanagiotou P, Warburton EA, Guyler P, Tysoe S, Fassbender KJIJoS. e-ASPECTS software is non-inferior to neuroradiologists in applying the ASPECT score to computed tomography scans of acute ischemic stroke patients2017: 615

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2025 ASIDE Internal Medicine

Most read articles by the same author(s)

Similar Articles

You may also start an advanced similarity search for this article.