Artificial intelligence-driven eye tracker models for Alzheimer's disease diagnosis: A systematic review and meta-analysis
The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Background: Diagnosis of Alzheimer's disease (AD) is crucial for effective intervention and care planning. Recently, artificial intelligence-driven eye-tracking (AI-driven ET) tools have emerged as promising diagnostic aids. Objective: To evaluate the diagnostic accuracy of AI-driven ET models for AD detection. Methods: A systematic review and meta-analysis were conducted according to PRISMA2020. Different database and grey literature were searched up to March 2025. Data were analyzed with Meta-Disc 1.4 and R software. This meta-analysis has been registered in PROSPERO (CRD420251020284). Results: Ten papers were included in the narrative synthesis and eight in the meta-analysis. Our systematic review found that most studies reported moderate to good accuracy of AI-driven ET tools in AD detection. The meta-analysis revealed that AI-driven ET tools achieved a sensitivity of 0.75 [95% CI: 0.67; 0.79], specificity of 0.75 [95% CI: 0.67; 0.81], positive likelihood ratio of 3.29 [95% CI: 2.36; 4.59], negative likelihood ratio of 0.36 [95% CI: 0.27; 0.48], diagnostic odds ratio of 10.40 [95% CI: 5.58; 19.39], and area under the ROC curve of 0.81. Deep learning seems to have better performance than supervised machine learning (SML). Among classification algorithms, support vector machines appear most robust across studies. The meta-regression identified population size, patient preparation, measurement systems, AI techniques, and SML algorithms as significant sources of heterogeneity. Conclusions: AI-driven ET tools suggest moderate to good diagnostic accuracy for distinguishing AD patients from healthy controls, based on available case-control studies. However, evidence for effective screening in broader populations is lacking. Further research is needed to confirm these results across diverse clinical settings and strengthen model robustness.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“the TabCAT-Brain Health Assessment developed at UCSF is an iPad-based in-clinic assessment that includes immediate scoring, outperforms traditional paper-based assessments, has had organic adoption across several UCSF-affiliated PCP clinics, and is free for primary care use.54–57”
From Review of Artificial Intelligence for Clinical Use in Alzheimer's Disease and Related Dementias (2026) · cites this paper as [55]
Citations
Cites
How to perform a meta-analysis with R: a practical tutorial
Balduzzi, S., Rücker, G., & Schwarzer, G. (2019) · Evidence Based Mental Health · doi:10.1136/ebmental-2019-300117 · Cited by 5,827 · cited 1×
“20 The signi fi cance level for the pooled effect was set at p 0.05.”
InfluentialAnalysing data and undertaking meta‐analyses
Deeks, J. J., Higgins, J. P., Altman, D. G., & on behalf of the Cochrane Statistical Methods Group (2019) · Cochrane Handbook for Systematic Reviews of Interventions · doi:10.1002/9781119536604.ch10 · Cited by 2,672
Advances in the early detection of Alzheimer's disease
Nestor, P. J., Scheltens, P., & Hodges, J. R. (2004) · Nature Medicine · doi:10.1038/nrn1433 · Cited by 463
Monaghan, T. F., Rahman, S. N., Agudelo, C. W., Wein, A. J., Lazar, J. M., Everaert, K., & Dmochowski, R. R. (2021) · Medicina · doi:10.3390/medicina57050503 · Cited by 442
Kaur, S., Singla, J., Nkenyereye, L., Jha, S., Prashar, D., Joshi, G. P., El-Sappagh, S., Islam, M. S., & Islam, S. M. R. (2020) · IEEE Access · doi:10.1109/access.2020.3042273 · Cited by 255 · cited 1×
“30 Likewise, it was identi fi ed to surpass ML in detecting AD and dementia based on brain imaging methods.”
Arya, A. D., Verma, S. S., Chakarabarti, P., Chakrabarti, T., Elngar, A. A., Kamali, A.-M., & Nami, M. (2023) · Brain Informatics · doi:10.1186/s40708-023-00195-7 · Cited by 161
Explainable AI-based Alzheimer’s prediction and management using multimodal data
Jahan, S., Abu Taher, K., Kaiser, M. S., Mahmud, M., Rahman, M. S., Hosen, A. S. M. S., & Ra, I.-H. (2023) · PLOS ONE · doi:10.1371/journal.pone.0294253 · Cited by 122 · cited 2×
“35”
Heterogeneity in meta-analysis: a comprehensive overview
Stogiannis, D., Siannis, F., & Androulakis, E. (2023) · The International Journal of Biostatistics · doi:10.1515/ijb-2022-0070 · Cited by 111 · cited 1×
“24 While our results indicated the absence of threshold effect on our meta-analysis heterogeneity, some confounding factors were identi fi ed in the meta-regression, including sample size, patient preparation, measurement system, AI techniques, and SML algorithms.”
Eye-Tracking Feature Extraction for Biometric Machine Learning
Lim, J. Z., Mountstephens, J., & Teo, J. (2022) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2021.796895 · Cited by 97 · cited 1×
“34 SVM are particularly effective in early AD detection when the feature space is clear and well-de fi ned.”
Speech based detection of Alzheimer's disease: a survey of AI techniques, datasets and challenges
Ding, K., Chetty, M., Noori Hoshyar, A., Bhattacharya, T., & Klein, B. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10961-6 · Cited by 82 · cited 1×
“28 Indeed, these fi ndings could be due to the different algorithms used by SML and DL. ML relies on manually engineered features such as fi xation duration and saccade patterns.”
A novel deep learning approach for diagnosing Alzheimer's disease based on eye-tracking data
Sun, J., Liu, Y., Wu, H., Jing, P., & Ji, Y. (2022) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2022.972773 · Cited by 68 · cited 2×
“However, although the study conducted by Zuo et al. 14 used the same population source as Sun et al., 15 it was included in the meta-analysis because it employed different criteria of diagnosis of AD and various AI tools and analytical approaches, thereby providing independent and non-duplicative…”
Noninvasive automatic detection of Alzheimer's disease from spontaneous speech: a review
Qi, X., Zhou, Q., Dong, J., & Bao, W. (2023) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2023.1224723 · Cited by 63
Zhang, F., Wei, J., Li, X., Ma, C., & Gao, Y. (2018) · Journal of Alzheimer s Disease · doi:10.3233/jad-180412 · Cited by 57
Zuo, F., Jing, P., Sun, J., Duan, J., Ji, Y., & Liu, Y. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3365172 · Cited by 51 · cited 2×
“However, although the study conducted by Zuo et al. 14 used the same population source as Sun et al., 15 it was included in the meta-analysis because it employed different criteria of diagnosis of AD and various AI tools and analytical approaches, thereby providing independent and non-duplicative…”
Distinctive Oculomotor Behaviors in Alzheimer's Disease and Frontotemporal Dementia
Lage, C., López-García, S., Bejanin, A., Kazimierczak, M., Aracil-Bolaños, I., Calvo-Córdoba, A., Pozueta, A., García-Martínez, M., Fernández-Rodríguez, A., Bravo-González, M., et al. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2020.603790 · Cited by 49
Kaczorowska, M., Plechawska–Wójcik, M., & Tokovarov, M. (2021) · Brain Sciences · doi:10.3390/brainsci11020210 · Cited by 48
Non-invasive Biomarkers for Early Detection of Alzheimer’s Disease: a New-Age Perspective
Chimthanawala, N. M. A., Haria, A., & Sathaye, S. S. (2023) · Molecular Neurobiology · doi:10.1007/s12035-023-03578-3 · Cited by 47
Three-dimensional information in face recognition: An eye-tracking study
Chelnokova, O., & Laeng, B. (2011) · Journal of Vision · doi:10.1167/11.13.27 · Cited by 43 · cited 1×
“25 Boujelbane et al. highlighted the VPC task as a reliable alternative to conventional paper-based cognitive assessments.”
Visual Search Efficiency in Mild Cognitive Impairment and Alzheimer’s Disease: An Eye Movement Study
Pereira, M. L. G. D. F., Camargo, M. V. Z. D. A., Bellan, A. F. R., Tahira, A. C., dos Santos, B., dos Santos, J., Machado‐Lima, A., Nunes, F. L. S., & Forlenza, O. V. (2020) · Journal of Alzheimer s Disease · doi:10.3233/jad-190690 · Cited by 41
Eye movement behavior identification for Alzheimer’s disease diagnosis
Biondi, J. A., Fernández, G., Castro, S. M., & Agamennoni, O. E. (2018) · Journal of Integrative Neuroscience · doi:10.31083/j.jin.2018.04.0416 · Cited by 40
Yin, Y., Wang, H., Liu, S., Sun, J., Jing, P., & Liu, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3245067 · Cited by 34 · cited 1×
“The studies conducted by Yin et al. 22 and Liu et al. 23 were excluded because they involved the same population and AI methods as those used by Sun et al., 15 to avoid duplication of data and potential bias in the analysis.”
Quek, L. J., Heikkonen, M. R., & Lau, Y. (2023) · Journal of Clinical Nursing · doi:10.1111/jocn.16699 · Cited by 25
Raynowska, J., Rizzo, J., Rucker, J. C., Dai, W., Birkemeier, J., Hershowitz, J., Selesnick, I., Balcer, L. J., Galetta, S. L., & Hudson, T. E. (2017) · Brain Injury · doi:10.1080/02699052.2017.1374469 · Cited by 21 · cited 1×
“27 Indeed, future research should explore the potential of AI combined to the EyeLink 1000 Plus, which captures at up to 2000 Hz with exceptional precision.”
Boujelbane, M. A., Trabelsi, K., Salem, A., Ammar, A., Glenn, J. M., Boukhris, O. F., AlRashid, M. M., Jahrami, H., & Chtourou, H. (2024) · Journal of Alzheimer s Disease · doi:10.3233/jad-240028 · Cited by 14 · cited 2×
“26 Furthermore, some studies in our meta-analysis used high-frequency eye trackers (Song et al. (2024) 12 and Pereira et al. (2020) 7 ), while others relied on low-frequency static cameras (Li et al. (2024) 16 ), contributing to variability in AI tool accuracy.”
Li, Q., Yan, J., Ye, J., Lv, H., Zhang, X., Tu, Z., Li, Y., & Guo, Q. (2024) · Aging Clinical and Experimental Research · doi:10.1007/s40520-024-02882-9 · Cited by 13 · cited 4×
“7 – 16 Indeed, recent studies have demonstrated that AD patients exhibit distinct patterns in eye movement behaviors, like dif fi culties in maintaining stable fi xation, de fi cient smooth pursuit, impaired saccades, and delayed vergence.”
InfluentialChavan, A. B., Patil, S. R., Patel, A. M., Chaugule, S. V., & Gharal, S. K. (2023) · Journal for Research in Applied Sciences and Biotechnology · doi:10.55544/jrasb.2.4.8 · Cited by 10
Diagnostic Potential of Eye Movements in Alzheimer’s Disease via a Multiclass Machine Learning Model
Song, J., Huang, H., Liu, J., Wu, J., Chen, Y., Wang, L., Zhong, F., Wang, X., Lin, Z., Yan, M., et al. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10346-5 · Cited by 10 · cited 1×
“26 Furthermore, some studies in our meta-analysis used high-frequency eye trackers (Song et al. (2024) 12 and Pereira et al. (2020) 7 ), while others relied on low-frequency static cameras (Li et al. (2024) 16 ), contributing to variability in AI tool accuracy.”
Discovery of novel metabolic biomarkers in blood serum for diagnosis of Alzheimer's disease
Zhao, Y., Tezanos, A. G. V., Miranda-Morales, E. G., Pappolla, M. A., & Fang, X. (2024) · Journal of Alzheimer s Disease · doi:10.3233/jad-240280 · Cited by 6
Heidarzadeh, N., & Ratté, S. (2023) · Journal of Alzheimer s Disease · doi:10.3233/jad-220711 · Cited by 5
Norouzi, M., Kafieh, R., Chazot, P. L., Smith, D. T., & Amini, Z. (2025) · Aging & Mental Health · doi:10.1080/13607863.2025.2464704 · Cited by 4
Liu, Y., Zhang, W., Wang, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.10124 · Cited by 2 · cited 1×
“The studies conducted by Yin et al. 22 and Liu et al. 23 were excluded because they involved the same population and AI methods as those used by Sun et al., 15 to avoid duplication of data and potential bias in the analysis.”
Liu, Y., Zhang, W., Zuo, F., Jing, P., Ji, Y. X., & Kung, S. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3686608 · Cited by 2
Regression and Classification: Basic Machine Learning Tools
Tsironis, G. (2025) · Understanding complex systems · doi:10.1007/978-3-031-81946-9_2 · Cited by 1
Research works printed but not linked: 5
- Dokholyan NV, Mohs RC, Bateman RJ. Challenges and progress in research, diagnostics, and therapeutics in Alzheimer’s disease and related dementias. Alzheimers Dement (N Y) 2022; 8: e12330.
- Field T, Newton-Mason S, Shajan S, et al. Machine learning analysis of speech and eye tracking data to distinguish Alzheimer’s clinic patients from healthy controls: biomarkers: searching for Alzheimer’s through the eyes. Alzheimers Dement 2020; 16(Suppl 5): e046742.
- Lin YC, Huang LK, Wu JC, et al. Early detection of Alzheimer’s disease through eye movement analysis: a digital diagnostic approach. In: 2024 IEEE international workshop on electromagnetics: applications and student innovation competition, iWEM 2024 – Taoyuan, Taiwan. Piscataway, NJ: Institute of Electrical and Electronics Engineers Inc., 2024.
- Liu Z, Yang Z, Gu Y, et al. The effectiveness of eye tracking in the diagnosis of cognitive disorders: a systematic review and meta-analysis. PLoS One 2021; 16: e0254059.
- Stamate D, Kim M, Proitsi P, et al. A metabolite-based machine learning approach to diagnose Alzheimer-type dementia in blood: results from the European medical information framework for Alzheimer disease biomarker discovery cohort. Alzheimers Dement 2019; 5: 933–938.
Cited by
Review of Artificial Intelligence for Clinical Use in Alzheimer's Disease and Related Dementias
Breithaupt, A. G., Tang, A., Paolillo, E. W., Bibars, M., Johnson, E. C. B., Saloner, R., Possin, K. L., Windon, C. C., Hill-Jarrett, T. G., Giorgio, J., et al. (2026) · Seminars in Neurology · doi:10.1055/a-2744-9871 · Cited by 6
Ndionuka, I. B. (2026) · Journal of Alzheimer s Disease · doi:10.1177/13872877261424254 · Cited by 1
Zhang, W., Jing, P., Li, X., Ji, Y., Liu, Y., & Kung, S. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104718
Ellouz, E., & Ketata, I. (2026) · Revue Neurologique · doi:10.1016/j.neurol.2026.02.054
Self-citationOculomotor Abnormalities in Rare Neurological Disorders: Potential Biomarkers for Diagnosis
Gamsa, A. H., & Gamsa, A. H. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-5171-9.ch001
Metadata
- Authors
- Ketata, I., & Ellouz, E.
- Affiliations
- University of Sfax (TN)
- Corresponding author
- Ketata, Imen
- Venue
- Journal of Alzheimer’s Disease
- Publisher
- SAGE Publications
- Published
- 2025-10-24
- Volume
- 108
- Issue
- 4
- Pages
- 1488-1506
- ISSN
- 1387-2877 (ISSN-L)
- 1875-8908
- OpenAlex
- W4415526088
- Cited by
- 3
- References
- 32
- Citations by year
- 2026: 2 · 2025: 1
- FWCI
- 0.54
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- Journal of Alzheimer s Disease (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- Alzheimer's disease, eye tracking
- MeSH terms
- Eye-Tracking Technology, Alzheimer Disease, Artificial Intelligence, Humans, Sensitivity and Specificity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.