Skip to content
2000
Volume 22, Issue 10
  • ISSN: 1567-2050
  • E-ISSN: 1875-5828

Abstract

Introduction

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that currently affects over 55 million individuals worldwide. Conventional diagnostic approaches often rely on subjective clinical assessments and isolated biomarkers, limiting their accuracy and early-stage effectiveness. With the rising global burden of AD, there is an urgent need for objective, automated tools that enhance diagnostic precision using neuroimaging data.

Methods

This study proposes a novel diagnostic framework combining a fine-tuned VGG19 deep convolutional neural network with an eXtreme Gradient Boosting (XGBoost) classifier. The model was trained and validated on the OASIS MRI dataset (Dataset 2), which was manually balanced to ensure equitable class representation across the four AD stages. The VGG19 model was pre-trained on ImageNet and fine-tuned by unfreezing its last ten layers. Data augmentation strategies, including random rotation and zoom, were applied to improve generalization. Extracted features were classified using XGBoost, incorporating class weighting, early stopping, and adaptive learning. Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC-AUC.

Results

The proposed VGG19-XGBoost model achieved a test accuracy of 99.6%, with an average precision of 1.00, a recall of 0.99, and an F1-score of 0.99 on the balanced OASIS dataset. ROC curves indicated high separability across AD stages, confirming strong discriminatory power and robustness in classification.

Discussion

The integration of deep feature extraction with ensemble learning demonstrated substantial improvement over conventional single-model approaches. The hybrid model effectively mitigated issues of class imbalance and overfitting, offering stable performance across all dementia stages. These findings suggest the method’s practical viability for clinical decision support in early AD diagnosis.

Conclusion

This study presents a high-performing, automated diagnostic tool for Alzheimer’s disease based on neuroimaging. The VGG19-XGBoost hybrid architecture demonstrates exceptional accuracy and robustness, underscoring its potential for real-world applications. Future work will focus on integrating multimodal data and validating the model on larger and more diverse populations to enhance clinical utility and generalizability.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/car/10.2174/0115672050393604250904081342
2025-09-15
2026-03-02

  • From This Site

    /content/journals/car/10.2174/0115672050393604250904081342
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. BringasS. DuqueR. LageC. MontañaJ.L. CLADSI: Deep continual learning for Alzheimer’s disease stage identification using accelerometer data.IEEE J. Biomed. Health Inform.20242863401341010.1109/JBHI.2024.3392354 38648143
     [Google Scholar]
  2. Alzheimer’s disease facts and figures.Alzheimers Dement.20231941598169510.1002/alz.13016 36918389
     [Google Scholar]
  3. LiX. FengX. SunX. HouN. HanF. LiuY. Global, regional, and national burden of Alzheimer’s disease and other dementias, 1990–2019.Front. Aging Neurosci.202214193748610.3389/fnagi.2022.937486 36299608
     [Google Scholar]
  4. WongW. Economic burden of Alzheimer disease and managed care considerations.Am. J. Manag. Care2020268S177S183 32840331
     [Google Scholar]
  5. WangL ShengJ ZhangQ Functional brain network measures for Alzheimer’s disease classification.IEEE Access20231111183211184510.1109/ACCESS.2023.3323250
     [Google Scholar]
  6. ZhangJ. HeX. QingL. GaoF. WangB. BPGAN: Brain PET synthesis from MRI using generative adversarial network for multi-modal Alzheimer’s disease diagnosis.Comput. Methods Programs Biomed.202221710667610.1016/j.cmpb.2022.106676 35167997
     [Google Scholar]
  7. DoeringS. McCulloughA.A. GordonB.A. Evaluating regional importance for tau spatial spread in predicting cognitive impairment with machine learning.Alzheimers Dement.202319S24e08255310.1002/alz.082553
     [Google Scholar]
  8. RichhariyaB. TanveerM. RashidA.H. Diagnosis of Alzheimer’s disease using universum support vector machine based recursive feature elimination (USVM-RFE).Biomed. Signal Process. Control20205910190310.1016/j.bspc.2020.101903
     [Google Scholar]
  9. DuboisB.R. The rationale behind the IWG criteria for Alzheimer’s disease.Alzheimers Dement.202218S6e06052310.1002/alz.060523
     [Google Scholar]
  10. RallabandiV.P.S. TulpuleK. GattuM. Automatic classification of cognitively normal, mild cognitive impairment and Alzheimer’s disease using structural MRI analysis.Inform. Med. Unlocked20201810030510.1016/j.imu.2020.100305
     [Google Scholar]
  11. LiaoS HsiehF. Unraveling heterogeneity of ADNI’s time-to-event data using conditional entropy Part-I: Cross-sectional study.IEEE Access2023123292331410.1109/ACCESS.2023.3344319
     [Google Scholar]
  12. López-BuenoR. YangL. StamatakisE. del Pozo CruzB. Moderate and vigorous leisure time physical activity in older adults and Alzheimer’s disease-related mortality in the USA: A dose–response, population-based study.Lancet Healthy Longev.2023412e703e71010.1016/S2666‑7568(23)00212‑X 38042163
     [Google Scholar]
  13. YuanY. HuR. ChenS. ZhangX. LiuZ. ZhouG. CKG-IMC: An inductive matrix completion method enhanced by CKG and GNN for Alzheimer’s disease compound-protein interactions prediction.Comput. Biol. Med.2024177108612210.1016/j.compbiomed.2024.108612 38838556
     [Google Scholar]
  14. MahimSM AliMS HasanMO NafiAAN SadatA HasanSA Unlocking the potential of XAI for improved Alzheimer’s disease detection and classification using a ViT-GRU model.IEEE Access2024128390841210.1109/ACCESS.2024.3351809
     [Google Scholar]
  15. YinK.F. GuX.J. SuW.M. Causal association and mediating effect of blood biochemical metabolic traits and brain image-derived endophenotypes on Alzheimer’s disease.Heliyon2024108e2742210.1016/j.heliyon.2024.e27422 38644883
     [Google Scholar]
  16. Gómez-PascualA. NaccacheT. XuJ. Paired plasma lipidomics and proteomics analysis in the conversion from mild cognitive impairment to Alzheimer’s disease.Comput. Biol. Med.2024176108588810.1016/j.compbiomed.2024.108588 38761503
     [Google Scholar]
  17. JoeE. Segal-GidanF. CummingsJ.L. GalaskoD. Tomaszewski FariasS. JohnsonD.K. Association between self- and proxy-reported depression and quality of life in mild-moderate Alzheimer’s disease.Am. J. Geriatr. Psychiatry2024321586710.1016/j.jagp.2023.08.004 37827916
     [Google Scholar]
  18. SekharJ.C. RajyalakshmiCh. NagarajS. SankarS. Deep generative adversarial networks with marine predators algorithm for classification of Alzheimer’s disease using electroencephalogram.J King Saud Univ Comput Inf Sci2023351010184810.1016/j.jksuci.2023.101848
     [Google Scholar]
  19. Díaz-ÁlvarezJ. García-GutiérrezF. Bueso-InchaustiP. Data-driven prediction of regional brain metabolism using neuropsychological assessment in Alzheimer’s disease and behavioral variant Frontotemporal dementia.Cortex202518330932510.1016/j.cortex.2024.11.022 39793260
     [Google Scholar]
  20. KarimA. KhvostikovA. AndreiK. Benois-PineauJ. KarimA. GwénaëlleC. Classification of Alzheimer disease on imaging modalities with deep CNNs using cross-modal transfer learning.2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS)Karlstad, Sweden, 18–21 June 2018, pp. 345–350.10.1109/CBMS.2018.00067
     [Google Scholar]
  21. JhaD. KimJ.I. KwonG.R. Diagnosis of Alzheimer’s disease using dual-tree complex wavelet transform, PCA, and feed-forward neural network.J. Healthc. Eng.2017201711310.1155/2017/9060124 29065663
     [Google Scholar]
  22. RavikantiD. S S. EEGAlzheimer’sNet: Development of transformer-based attention long short term memory network for detecting Alzheimer disease using EEG signal.Biomed. Signal Process. Control20238610531810.1016/j.bspc.2023.105318
     [Google Scholar]
  23. FaisalM. AlharbiA. AlhamadiA. Robot-based solution for helping Alzheimer patients.SLAS Technol.2024293100140010.1016/j.slast.2024.100140 38729525
     [Google Scholar]
  24. MyszczynskaM.A. OjamiesP.N. LacosteA.M.B. Applications of machine learning to diagnosis and treatment of neurodegenerative diseases.Nat. Rev. Neurol.202016844045610.1038/s41582‑020‑0377‑8 32669685
     [Google Scholar]
  25. MengX. LiuJ. FanX. Multi-modal neuroimaging neural network-based feature detection for diagnosis of Alzheimer’s disease.Front. Aging Neurosci.20221491122010.3389/fnagi.2022.911220 35651528
     [Google Scholar]
  26. SukH.I. LeeS.W. ShenD. Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis.Neuroimage201410156958210.1016/j.neuroimage.2014.06.077 25042445
     [Google Scholar]
  27. BasheerS BhatiaS SakriSB Computational modeling of dementia prediction using deep neural network: Analysis on OASIS dataset.IEEE Access20219424494246210.1109/ACCESS.2021.3066213
     [Google Scholar]
  28. RyuSE ShinDH ChungK Prediction model of dementia risk based on xgboost using derived variable extraction and hyper parameter optimization.IEEE Access2020817770817772010.1109/ACCESS.2020.3025553
     [Google Scholar]
  29. BangyalW.H. RehmanN.U. NawazA. Constructing domain ontology for Alzheimer disease using deep learning based approach.Electronics20221112189010.3390/electronics11121890
     [Google Scholar]
  30. SharmaS. GuptaS. GuptaD. HTLML: Hybrid AI based model for detection of Alzheimer’s disease.Diagnostics20221281833310.3390/diagnostics12081833 36010183
     [Google Scholar]
  31. BasaiaS. AgostaF. WagnerL. Automated classification of Alzheimer’s disease and mild cognitive impairment using a single MRI and deep neural networks.Neuroimage Clin.20192110164510.1016/j.nicl.2018.101645 30584016
     [Google Scholar]
  32. QiuS. MillerM.I. JoshiP.S. Multimodal deep learning for Alzheimer’s disease dementia assessment.Nat. Commun.2022131340410.1038/s41467‑022‑31037‑5 35725739
     [Google Scholar]
  33. HuZ. WangZ. JinY. HouW. VGG-TSwinformer: Transformer-based deep learning model for early Alzheimer’s disease prediction.Comput. Methods Programs Biomed.202322910729110.1016/j.cmpb.2022.107291 36516516
     [Google Scholar]
  34. HazarikaR.A. MajiA.K. KandarD. An approach for classification of Alzheimer’s disease using deep neural network and brain magnetic resonance imaging (MRI).Electronics202312367610.3390/electronics12030676
     [Google Scholar]
  35. KadriR. BouazizB. TmarM. GargouriF. Efficient multimodel method based on transformers and CoAtNet for Alzheimer’s diagnosis.Digit. Signal Process.2023143104229910.1016/j.dsp.2023.104229
     [Google Scholar]
  36. MuruganS VenkatesanC SumithraMG DEMNET: A deep learning model for early diagnosis of Alzheimer diseases and dementia from MR images.IEEE Access20219903199032910.1109/ACCESS.2021.3090474
     [Google Scholar]
  37. SalehA.W. GuptaG. KhanS.B. AlkhaldiN.A. VermaA. An Alzheimer’s disease classification model using transfer learning densenet with embedded healthcare decision support system.Decision Anal J2023910034810.1016/j.dajour.2023.100348
     [Google Scholar]
  38. IslamJ. ZhangY. Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks.Brain Inform.201852210.1186/s40708‑018‑0080‑3 29881892
     [Google Scholar]
  39. FarooqA. AnwarS. AwaisM. RehmanS. A deep CNN based multi-class classification of Alzheimer’s disease using MRI.2017 IEEE International Conference on Imaging Systems and Techniques (IST)Beijing, China, 2017, pp. 1–6.10.1109/IST.2017.8261460
     [Google Scholar]
  40. MehmoodA. MaqsoodM. BashirM. ShuyuanY. A deep siamese convolution neural network for multi-class classification of Alzheimer disease.Brain Sci.20201028410.3390/brainsci10020084 32033462
     [Google Scholar]
  41. NawazH. MaqsoodM. AfzalS. AadilF. MehmoodI. RhoS. A deep feature-based real-time system for Alzheimer disease stage detection.Multimedia Tools Appl.20218028-29357893580710.1007/s11042‑020‑09087‑y
     [Google Scholar]
  42. MuksimovaS. UmirzakovaS. IskhakovaN. KhaitovA. ChoY.I. Advanced convolutional neural network with attention mechanism for Alzheimer’s disease classification using MRI.Comput. Biol. Med.202519011009510.1016/j.compbiomed.2025.11009540158456
     [Google Scholar]
  43. OlaimatM.A. BozdagS. SaeedF. TA-RNN: An attention-based time-aware recurrent neural network architecture to predict progression of Alzheimer’s disease.Alzheimer’s Dement202420S1
     [Google Scholar]
  44. JackC.R. BennettD.A. BlennowK. NIA‐AA Research Framework: Toward a biological definition of Alzheimer’s disease.Alzheimers Dement.201814453556210.1016/j.jalz.2018.02.018 29653606
     [Google Scholar]
  45. Kaggle. Alzheimer MRI Dataset.2022Available at: https://www.kaggle.com/datasets/sachinkumar413/alzheimer-mri-dataset(accessed May 10, 2025).
  46. OASIS Alzheimer's detection.2023 https://www.kaggle.com/datasets/ninadaithal/imagesoasis
  47. FerdousiJ. LincolnS.I. AlomM.K. FoysalM. A deep learning approach for white blood cells image generation and classification using SRGAN and VGG19.Telemat Inform Rep20241610016310.1016/j.teler.2024.100163
     [Google Scholar]
  48. BeheshtiI. DemirelH. FarokhianF. YangC. MatsudaH. Structural MRI-based detection of Alzheimer’s disease using feature ranking and classification error.Comput. Methods Programs Biomed.201613717719310.1016/j.cmpb.2016.09.019 28110723
     [Google Scholar]
  49. NeshatM. AhmedM. AskariH. ThilakaratneM. MirjaliliS. Hybrid inception architecture with residual connection: Fine-tuned inception-resnet deep learning model for lung inflammation diagnosis from chest radiographs.Procedia Comput. Sci.20242351841185010.1016/j.procs.2024.04.175
     [Google Scholar]
  50. AsifS. ZhaoM. TangF. ZhuY. DCDS-Net: Deep transfer network based on depth-wise separable convolution with residual connection for diagnosing gastrointestinal diseases.Biomed. Signal Process. Control20249010586610.1016/j.bspc.2023.105866
     [Google Scholar]
  51. HeatonJ. IanG. YoshuaB. AaronC. Deep learning.Genet Program Evolvable2018191-230530710.1007/s10710‑017‑9314‑z
     [Google Scholar]
  52. KimJ. KimS. ChoiK. ParkI.C. Hardware-efficient SoftMax architecture with bit-wise exponentiation and reciprocal calculation.IEEE Trans. Circuits Syst. I Regul. Pap.202471104574458510.1109/TCSI.2024.3443270
     [Google Scholar]
  53. MahjoubiM.A. LamraniD. SalehS. Optimizing ResNet50 performance using stochastic gradient descent on MRI images for Alzheimer’s disease classification.Intell. Based Med.20251110021910.1016/j.ibmed.2025.100219
     [Google Scholar]
  54. GharagozM.M. NoureldinM. KimJ. Explainable machine learning (XML) framework for seismic assessment of structures using Extreme Gradient Boosting (XGBoost).Eng. Struct.202532711962110.1016/j.engstruct.2025.119621
     [Google Scholar]
  55. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks.Commun. ACM2017606849010.1145/3065386
     [Google Scholar]
  56. LitjensG. KooiT. BejnordiB.E. A survey on deep learning in medical image analysis.Med. Image Anal.201742608810.1016/j.media.2017.07.005 28778026
     [Google Scholar]
  57. HochinT. MaedaT. Interpretation method of transformation matrix clarifying relationships between impression factors of multimedia data.Int J Affect Eng202019211111710.5057/ijae.IJAE‑D‑19‑00010
     [Google Scholar]
  58. AngelE ShreinerD An interactive introduction to computer graphics using WebGL.ACM SIGGRAPH 2022 CoursesVancouver, British Columbia, Canada, 2022, pp. 1–91.10.1145/3532720.3535630
     [Google Scholar]
  59. RonnebergerO. FischerP. BroxT. U-net: Convolutional networks for biomedical image segmentationLect Notes Comput Sci2015935123424110.1007/978‑3‑319‑24574‑4_28
     [Google Scholar]
  60. EstevaA. KuprelB. NovoaR.A. Dermatologist-level classification of skin cancer with deep neural networks.Nature2017542763911511810.1038/nature21056 28117445
     [Google Scholar]
  61. RumelhartD.E. HintonG.E. WilliamsR.J. Learning representations by back-propagating errors.Nature1986323608853353610.1038/323533a0
     [Google Scholar]
  62. RamsayJ. The elements of statistical learning: Data mining, inference, and prediction.Psychometrika200368461161210.1007/BF02295616
     [Google Scholar]
  63. SokolovaM. LapalmeG. A systematic analysis of performance measures for classification tasks.Inf. Process. Manage.200945442743710.1016/j.ipm.2009.03.002
     [Google Scholar]
  64. SaitA.R.W. NagarajR. A feature-fusion technique-based Alzheimer’s disease classification using magnetic resonance imaging.Diagnostics20241421236310.3390/diagnostics14212363 39518331
     [Google Scholar]
  65. LahmiriS. Integrating convolutional neural networks, kNN, and Bayesian optimization for efficient diagnosis of Alzheimer’s disease in magnetic resonance images.Biomed. Signal Process. Control20238010437510.1016/j.bspc.2022.104375
     [Google Scholar]
  66. ChuiK.T. GuptaB.B. AlhalabiW. AlzahraniF.S. An MRI scans-based Alzheimer’s disease detection via Convolutional neural network and transfer learning.Diagnostics2022127153110.3390/diagnostics12071531 35885437
     [Google Scholar]
  67. JabasonE. AhmadM.O. SwamyM. Classification of Alzheimer’s disease from MRI data using an ensemble of hybrid deep Convolutional neural networks.2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS) Dallas, TX, USA, 2019, pp. 481-484.10.1109/MWSCAS.2019.8884939
     [Google Scholar]
  68. FultonL. DolezelD. HarropJ. YanY. FultonC. Classification of Alzheimer’s disease with and without imagery using gradient boosted machines and resnet-50.Brain Sci.20199921210.3390/brainsci9090212 31443556
     [Google Scholar]
  69. Ghassan Al RahbaniR. IoannouA. WangT. Alzheimer’s disease multiclass detection through deep learning models and post-processing heuristics.Comput. Methods Biomech. Biomed. Eng. Imaging Vis.2024121238321910.1080/21681163.2024.2383219
     [Google Scholar]
  70. OhK. ChungY.C. KimK.W. KimW.S. OhI.S. Classification and visualization of Alzheimer’s disease using volumetric convolutional neural network and transfer learning.Sci. Rep.2019911815010.1038/s41598‑019‑54548‑6 31796817
     [Google Scholar]
  71. LazliL. Improved Alzheimer disease diagnosis with a machine learning approach and neuroimaging: Case study development.JMIRx Med20256v6i2e6086610.2196/6086640257754
     [Google Scholar]
  72. HoangG-M. LeeY. KimJ.G. A reproducible 3D convolutional neural network with dual attention module (3D-DAM) for Alzheimer’s disease classification.arXiv 2023; arXiv:2310.12574v3.10.48550/arXiv.2310.12574
     [Google Scholar]
  73. MarcusD.S. WangT.H. ParkerJ. CsernanskyJ.G. MorrisJ.C. BucknerR.L. Open Access Series of Imaging Studies (OASIS): cross-sectional MRI data in young, middle aged, nondemented, and demented older adults.J. Cogn. Neurosci.20071991498150710.1162/jocn.2007.19.9.1498 17714011
     [Google Scholar]
  74. LiuS. LiuS. CaiW. Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer’s disease.IEEE Trans. Biomed. Eng.20156241132114010.1109/TBME.2014.2372011 25423647
     [Google Scholar]
  75. JumailiM.L.F. SonuçE. An attention-based CNN framework for Alzheimer’s disease staging with multi-technique XAI visualization.Comput. Mater. Continua20258322947296910.32604/cmc.2025.062719
     [Google Scholar]
  76. KhatriU. KwonG.R. Diagnosis of Alzheimer’s disease via optimized lightweight convolution-attention and structural MRI.Comput. Biol. Med.202417110811610.1016/j.compbiomed.2024.108116 38346370
     [Google Scholar]
  77. TimsinaJ. AliM. DoA. Harmonization of CSF and imaging biomarkers in Alzheimer’s disease: Need and practical applications for genetics studies and preclinical classification.Neurobiol. Dis.202419010637310.1016/j.nbd.2023.106373 38072165
     [Google Scholar]
  78. SukH.I. LeeS.W. ShenD. Deep sparse multi-task learning for feature selection in Alzheimer’s disease diagnosis.Brain Struct. Funct.201622152569258710.1007/s00429‑015‑1059‑y 25993900
     [Google Scholar]
  79. UpadhyayP. TomarP. YadavS.P. Advancements in Alzheimer’s disease classification using deep learning frameworks for multimodal neuroimaging: A comprehensive review.Comput. Electr. Eng.202412010979610.1016/j.compeleceng.2024.109796
     [Google Scholar]
  80. AbdelazizM. WangT. AnwaarW. ElazabA. Multi-scale multimodal deep learning framework for Alzheimer’s disease diagnosis.Comput. Biol. Med.202518410943810.1016/j.compbiomed.2024.109438 39579666
     [Google Scholar]
  81. ZhouW. LuoW. GongL. PengB. Enhanced early diagnosis of Alzheimer’s disease with HybridCA-Net: A multimodal fusion approach.Expert Syst. Appl.202529212858010.1016/j.eswa.2025.128580
     [Google Scholar]
  82. VieiraS PinayaWHL MechelliA Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications.Neurosci Biobehav Rev201774Pt A587510.1016/j.neubiorev.2017.01.00228087243
     [Google Scholar]
  83. BelkezizR. ChefiraR. SamiriM.Y. RakrakS. Conversational AI system for enhancing autonomy in individuals with Alzheimer’s disease.Procedia Comput. Sci.202425175275710.1016/j.procs.2024.11.180
     [Google Scholar]
  84. ChakrabortyM. NaoalN. MomenS. MohammedN. Analyze-AD: A comparative analysis of novel AI approaches for early Alzheimer’s detection.Array20242210035210.1016/j.array.2024.100352
     [Google Scholar]
/content/journals/car/10.2174/0115672050393604250904081342
Loading
Advancing Alzheimer's Disease Diagnosis Using VGG19 and XGBoost: A Neuroimaging-Based Method
Curr Alzheimer Res 22, 757 (2025); https://doi.org/10.2174/0115672050393604250904081342
/content/journals/car/10.2174/0115672050393604250904081342
/content/journals/car/10.2174/0115672050393604250904081342
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Alzheimer's disease; classification; MRI; OASIS dataset; VGG19; XGBoost

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test