You are on page 1of 4

Literature survey

1.Chuanchuan Zheng, Yong Xia, Yongsheng Pan, Jinhu Chen


We summarized the automated dementia identification algorithms in the literature from a
pattern classification perspective. Since most of those algorithms consist of both feature
extraction and classification, we provide a survey on three categories of feature extraction
methods, including the voxel-, vertex- and ROI-based ones, and four categories of classifiers,
including the linear discriminant analysis, Bayes classifiers, support vector machines, and
artificial neural networks. Our comparison shows that many algorithms can differentiate the
Alzheimer’s disease (AD) from elderly normal with a largely satisfying accuracy, whereas
distinguishing the mild cognitive impairment from AD or elderly normal still remains a major
challenge.They concluded that, for AD versus CN, whole-brain methods achieved high
accuracies (up to 81 % sensitivity and 95 % specificity)

2. Gloria Castellazzi , Maria Giovanna Cuzzoni, Daniele Martinelli


We investigated, first, whether different kinds of ML algorithms, combined with advanced
MRI features, could be supportive in classifying VD from AD and, second, whether the
developed approach might help in predicting the prevalent disease in subjects with an unclear
profile of AD or VD. Three ML categories of algorithms were tested: artificial neural network
(ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS)

3. Sivakani Rajayyan,This paper focused on feature engineering and the prediction of dementia disease
using the machine learning models Gaussian NB, SVM, and LR. The feature engineering focus tasks are
feature creation, feature transformation, feature selection, and feature extraction. In feature creation,
data creation and data imputation have been done; mean imputation has been applied for generating
the missing values. Label encoding has been done for feature transformation. CFS Subset Evaluator
along with the best first search method and the info gain attribute evaluator along with the ranker
method has been applied for selecting the best attributes. Initially, there are 15 features in the oasis
dataset and 12 features are selected as the best attributes for the prediction. The evaluation
parameters considered for validating the models are precision, recall, F1-score, and accuracy; for all
the metrics the Gaussian NB was given the highest values as given 95%, 97%, 95%, and 95%.

4.G Priyanka,In this research the effort is to experiment with Alzheimer's data with machine learning
algorithms to diagnose dementia. In total, 15 data attributes are taken into account. The work began
with 373 Alzheimer's data and with the deployment of algorithms such as SVM, LDA, KNN, RF,
AdaBoost and XGBoost, which is evidence that machine learning algorithms are now used to identify
brain diseases. This form of diagnosis aims to save time for neurologists and patients to get the correct
diagnosis at the right time. Nearly 90% accuracy of Alzheimer's patient data is demonstrated by the
outcome of implementation. The implementation involves 373 Alzheimer's disease details. Similarly,
the diagnosis of brain disorders such as frontotemporal dementia can be extended.
5. congling Wu,shengwen guo,yajia hong,benheng xiao,yupeng wu,qin zhangWe exploited two
different architectures of CNN framework, CaffeNet and GoogleNet, to differentiate sMCI and
cMCI from the NC group, and extensively evaluated the conversion risk from MCI to AD. The
CaffeNet and GoogleNet architectures, using the proposed transfer learning strategy, achieved
87.78% and 83.23% average accuracy scores in three-way classification respectively.
Moreover, conversion time point was effectively predicted with an overall accuracy of 96.18%.
To conclude, these findings open up a new perspective in risk assessment of patients with MCI
in early stages. As they exhibited great potential in differentiating 3 groups, and assessing the
conversion risk at assigned time points of MCI, our proposed pipelines could serve as
promising algorithms in characterizing objective biomarkers.
6. In this paper, the authors introduced a novel DL method based on PSD for the brain states
classification of patients affected by AD, MCI and HC individuals. The originality of the method
proposed lies in mapping the power spectrum of each subject into a 2-d gray scale image and
developing a Convolutional Neural Network (CNN) able to automatically extract latent features
automatically from simple and sparse images representative of the power spectra. The proposed CNN1
consisted of: a convolutional layer (+ ReLu), a max pooling layer, and a fully connected layer followed
by a softmax layer. The experimental results indicate that the CNN provided high performances in
epochs classification also when compared with standard learning algorithms (MLP, SVM, LDA, Table 4,
5). Nevertheless, the proposed classification system remains deficient in the patient-based
classification. (Table 6). The findings suggest that the power spectral analysis is not enough to detect
the anomalies of EEG recording, but we believe that DL techniques can identify a significant set of
variables that may support clinicians in the diagnosis of AD.

refrences

[1] Nivedita Manohar Mathkunti, ShantaRangaswamy Machine Learning Techniques to


Identify Dementia SN Computer Science volume 1, Article number: 118 (2020)

[2] Yunus Miah, Chowdhury NaziaEnam Prima, Sharmeen Jahan Seema, Mufti Mahmud, M
Shamim Kaiser Performance Comparison of Machine Learning Techniques in Identifying
Dementia from Open Access Clinical Datasets Part of the Advances in Intelligent Systems and
Computing book series (AISC, volume 1188)
[3] Daniel Stamate, Richard Smith, Ruslan Tsygancov, RostislavVorobev, John Langham,
Daniel Stahl, David Reeves Applying Deep Learning to Predicting Dementia and Mild
Cognitive Impairment Part of the IFIP Advances in Information and Communication
Technology book series (IFIPAICT, volume 584)
[4] Shankle, W. R., Datta, P., Dillencourt, M., &Pazzani, M. (1996) Improving dementia
screening tests with machine learning methods, Alzheimer's Research.
[5] Maroco, J., Silva, D., Rodrigues, A., Guerreiro, M., Santana, I., & de Mendonça, A. (2011)
Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy,
sensitivity and specificity of linear discriminant analysis, logistic regression, neural Networks,
support vector machines, classification trees and random forests, BMC research notes
[6] D. Bansal, R. Chhikara, K. Khanna, and P. Gupta, Comparative analysis of various machine
learning algorithms for detecting dementia, Procedia Computer Science, vol. 132, pp. 1497–
1502, 2018.
[7] Fubao Zhu, Xiaonan Li, Haipeng Tang, Zhuo He, Chaoyang Zhang, Guang-Uei Hung, Pai-
Yi Chiu, and WeihuaZhou Machine Learning for the Preliminary Diagnosis of Dementia,
Hindawi Scientific Programming Volume 2020
[8] Farhan, S., Fahiem, M.A., Tauseef, H.: An ensemble-of-classifiers based approach for early
diagnosis of Alzheimer’s disease: classification using structural features of brain images.
Comput. Math. Methods Med.2014(2014)
[9] D. W. Desmond, Vascular dementia, Clin. Neurosci. Res., vol. 3, pp. 437_448,
Mar./Apr.2004

[10] E. C.W. van Straaten,W. de Haan, H. deWaal, P. Scheltens,W. M. van der Flier, F. Barkhof,
T.Koene, and C. J. Stam, Disturbed oscillatory brain dynamics in subcortical ischemic vascular
dementia, BMC Neurosci., vol. 13, p. 85, Jul. 2012.
[11] E. C. W. van Straaten, J. den Haan, H. de Waal, W. M. van der Flier, F. Barkhof, N. D.
Prins, and C. J. Stam, Disturbed phase relations in white matter hyperintensity based vascular
dementia: An EEG directed connectivity study, Clin. Neurophysiol., vol. 126, pp. 497_504,
Mar. 2015.
[12] J. Xu, W. Lou, S. Zhao, and C. Wang, Altered directed connectivity in patients with early
vascular dementia during a visual oddball task, Brain Topogr., vol. 28, pp. 330_339, Mar. 2015.
[13] S. Tak, S. J. Yoon, J. Jang, K. Yoo, Y. Jeong, and J. C. Ye, Quantitative analysis of
hemodynamic and metabolic changes in subcortical vascular dementia using simultaneous
near-infrared spectroscopy and fMRI measurements, NeuroImage, vol. 55, pp. 176_184, Mar.
2011.
[14] PrakashDuraisamy, XiaohuiYuan, ElSaba,A. and Sumithra Palanisamy, Contrast
enhancement and assessment of OCT images, Proceedings of International Conference on
Informatics, Electronics & Vision (ICIEV), 2012 Date: 18-19 May 2012 pp.91-95(Location
:Dhaka, Print ISBN: 978-1-4673-1153-3,INSPEC Accession Number: 13058449,Digital
Object Identifier :10.1109/ICIEV.2012.6317381)
[15] Sumithra M. G., Thanushkodi, K. and Helan Jenifer Archana ,A. A New Speaker
Recognition System with Combined Feature Extraction Techniques , Journal of Computer
Science, Vol. 7, Issue 4, pp.459- 465, 2011. (With impact factor SNIP of 0.162 and SJR
of0.034).
[16] Balasaraswathi, M., Srinivasan, K., Udayakumar, L., Sivasakthiselvan, S. and Sumithra,
M.G., 2020. Big data analytic of contexts and cascading tourism for smart city. Materials
Today: Proceedings.
[17] Sivakumar, P., Boopathi, C.S., Sumithra, M.G., Singh, M., Malhotra, J. and Grover, A.,
2020. Ultra-high capacity long-haul PDM-16-QAM-based WDM-FSO transmission system
using coherent detection and digital signal processing. Optical and Quantum Electronics,
52(11), pp.1-18.
[18] F. Pereira, T. Mitchell, and M. Botvinick, Machine learning classifiers and fMRI: A
tutorial overview, NeuroImage, vol. 45, pp. S199_S209, Mar. 2009.
[19] S. Klöppel, A. Abdulkadir, C. R. Jack, Jr., N. Koutsouleris, J. Mourão-Miranda, and P.
Vemuri, Diagnostic neuroimaging across diseases, NeuroImage, vol. 61, pp. 457_463, Jun.
2012.
[20] F. X. Castellanos, A. Di Martino, R. C. Craddock, A. D. Mehta, and M. P. Milham, Clinical
applications of the functional connectome, NeuroImage, vol. 80, pp. 527_540, Oct. 2013.
[21] C.-Y. Wee, P.-T. Yap, W. Li, K. Denny, J. N. Browndyke, G. G. Potter, K. A. Welsh-
Bohmer, L. Wang, and D. Shen, Enriched white matter connectivity networks for accurate
identification of MCI patients, NeuroImage, vol. 54, no. 3, pp. 1812_1822, 2011.
[22] C.-Y. Wee, P.-T. Yap, D. Zhang, K. Denny, J. N. Browndyke, G. G. Potter, K. A.
WelshBohmer, L. Wang, and D. Shen, Identification of MCI individuals using structural and
functional connectivity networks, NeuroImage, vol. 59, no. 3, pp. 2045_2056, 2012.

You might also like