Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 5;15(3):377.
doi: 10.3390/diagnostics15030377.

Alzheimer's Prediction Methods with Harris Hawks Optimization (HHO) and Deep Learning-Based Approach Using an MLP-LSTM Hybrid Network

Raheleh Ghadami  1 , Javad Rahebi  2
Affiliations

Alzheimer's Prediction Methods with Harris Hawks Optimization (HHO) and Deep Learning-Based Approach Using an MLP-LSTM Hybrid Network

Raheleh Ghadami et al. Diagnostics (Basel). .

Abstract

Background/Objective: Alzheimer's disease is a progressive brain syndrome causing cognitive decline and, ultimately, death. Early diagnosis is essential for timely medical intervention, with MRI medical imaging serving as a primary diagnostic tool. Machine learning (ML) and deep learning (DL) methods are increasingly utilized to analyze these images, but accurately distinguishing between healthy and diseased states remains a challenge. This study aims to address these limitations by developing an integrated approach combining swarm intelligence with ML and DL techniques for Alzheimer's disease classification. Method: This proposal methodology involves sourcing Alzheimer's disease-related MRI images and extracting features using convolutional neural networks (CNNs) and the Gray Level Co-occurrence Matrix (GLCM). The Harris Hawks Optimization (HHO) algorithm is applied to select the most significant features. The selected features are used to train a multi-layer perceptron (MLP) neural network and further processed using a long short-term (LSTM) memory network in order to classify tumors as malignant or benign. The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset is utilized for assessment. Results: The proposed method achieved a classification accuracy of 97.59%, sensitivity of 97.41%, and precision of 97.25%, outperforming other models, including VGG16, GLCM, and ResNet-50, in diagnosing Alzheimer's disease. Conclusions: The results demonstrate the efficacy of the proposed approach in enhancing Alzheimer's disease diagnosis through improved feature extraction and selection techniques. These findings highlight the potential for advanced ML and DL integration to improve diagnostic tools in medical imaging applications.

Keywords: Alzheimer’s disease; Harris Hawks Optimization (HHO) algorithm; LSTM neural network; convolutional neural network (CNN); magnetic resonance images (MRI).

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Influences on the development of Alzheimer’s disease [29].
Figure 2
Figure 2
The regions of the brain affected by Alzheimer’s disease in MRI images [30].
Figure 3
Figure 3
The structure of the suggested method for diagnosing Alzheimer’s disease.
Figure 4
Figure 4
ResNet-50 residual block.
Figure 5
Figure 5
ResNet-50 neural network configuration.
Figure 6
Figure 6
Proposed feature selection flowchart.
Figure 7
Figure 7
Structure of the LSTM.
Figure 8
Figure 8
Two sample images from the ADNI and MIRIAD datasets: (a) MIRIAD dataset [46]; (b) slices from the ADNI Dataset [47].
Figure 9
Figure 9
Evaluation of the proposed method on the ADNI dataset.
Figure 10
Figure 10
Evaluation of the proposed method on the MIRIAD dataset.
Figure 11
Figure 11
Comparison of the proposed method with several classification methods of Alzheimer’s images with accuracy index.
Figure 12
Figure 12
Comparison of the proposed method with several classification methods of Alzheimer’s images with precision index.
Figure 13
Figure 13
Comparison of the proposed method with several classification methods of Alzheimer’s images with sensitivity index.
Figure 14
Figure 14
Comparison of the accuracy of the proposed method of DL methods in Alzheimer’s diagnosis.
Figure 15
Figure 15
Comparison of the sensitivity of the proposed method of DL methods in Alzheimer’s diagnosis.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Habuza T., Zaki N., Mohamed E.A., Statsenko Y. Deviation from model of normal aging in alzheimer’s disease: Application of deep learning to structural MRI data and cognitive tests. IEEE Access. 2022;10:53234–53249. doi: 10.1109/ACCESS.2022.3174601. - DOI
    1. Li K., Wang J., Li S., Yu H., Zhu L., Liu J., Wu L. Feature extraction and identification of Alzheimer’s disease based on latent factor of multi-channel EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 2021;29:1557–1567. doi: 10.1109/TNSRE.2021.3101240. - DOI - PubMed
    1. Bendl J., Hauberg M.E., Girdhar K., Im E., Vicari J.M., Rahman S., Fernando M.B., Townsley K.G., Dong P., Misir R. The three-dimensional landscape of cortical chromatin accessibility in Alzheimer’s disease. Nat. Neurosci. 2022;25:1366–1378. doi: 10.1038/s41593-022-01166-7. - DOI - PMC - PubMed
    1. Dubois B., Villain N., Frisoni G.B., Rabinovici G.D., Sabbagh M., Cappa S., Feldman H.H. Clinical diagnosis of Alzheimer’s disease: Recommendations of the International Working Group. Lancet Neurol. 2021;20:484–496. doi: 10.1016/S1474-4422(21)00066-1. - DOI - PMC - PubMed
    1. Kabir M.T., Uddin M.S., Begum M., Thangapandiyan S., Rahman M.S., Aleya L., Mathew B., Ahmed M., Barreto G.E., Ashraf G.M. Cholinesterase inhibitors for Alzheimer’s disease: Multitargeting strategy based on anti-Alzheimer’s drugs repositioning. Curr. Pharm. Des. 2019;25:3519–3535. doi: 10.2174/1381612825666191008103141. - DOI - PubMed

LinkOut - more resources