Early Prediction of Alzheimer’s Disease using Random Forest and E-SS Algorithm

Victor Valentino; Jimmy Tjen; Genrawan Hoendarto; Kevin Chaily

doi:10.18535/sshj.v9i01.1456

Abstract

Alzheimer Disease (AD) is a neurogenerative disorder that progressively damages the nervous system. Early detection of AD is crucial, as it allows patients to receive therapy at an earlier stage, helping to slow the progression of the disease. This research proposes a model with improved effectiveness and accuracy by combining Random Forest with Entropy-based Subset Selection (E-SS). E-SS is used to identify subsets of parameters that correlate with each other based on entropy. The results show that the combination of Random Forest and E-SS outperforms traditional Random Forest, Decision Tree, SVM, and k-NN models, achieving an accuracy of 95.81% while reducing the number of parameters from 33 to 29. This demonstrates that the proposed algorithm could be applied in the medical field, improving predictive accuracy by eliminating parameters with weak correlations to the disease.

Keywords

Alzheimer DiseaseRandom ForestEntropy-based Subset SelectionMachine Learning.

References

E. Area-Gomez and E. A. Schon, “Alzheimer disease,” Adv Exp Med Biol, vol. 997, no. 1, pp. 149–156, 2017, doi: 10.1007/978-981-10-4567-7_11.DOI ↗Google Scholar ↗
R. Brookmeyer, E. Johnson, K. Ziegler-Graham, and H. M. Arrighi, “Forecasting the global burden of Alzheimer’s disease,” Alzheimer’s and Dementia, vol. 3, no. 3, pp. 186–191, 2007,Google Scholar ↗
doi: 10.1016/j.jalz.2007.04.381.DOI ↗Google Scholar ↗
R. A. Armstrong, “Risk factors for Alzheimer’s disease,” Folia Neuropathol, vol. 57, no. 2, pp. 87–105, 2019,Google Scholar ↗
doi: 10.5114/fn.2019.85929.DOI ↗Google Scholar ↗
R. Green, RC; Clarke, VC; Thompson, NJ; Woodard, JL; Letz, “Early detection of Alzheimer disease: methods, markers, and misgivings,” Alzheimer Dis Assoc Disord, vol. 11, no. 5, p. S1, 1997,Google Scholar ↗
doi: 10.2217/fnl.10.31.DOI ↗Google Scholar ↗
J. Rasmussen and H. Langerman, “Alzheimer’s Disease – Why We Need Early Diagnosis,” Degener Neurol Neuromuscul Dis, vol. Volume 9, pp. 123–130, 2019, doi: 10.2147/dnnd.s228939.DOI ↗Google Scholar ↗
I. Konenko, “Machine learning for medical diagnosis: History, state of the art and perspective,” Artif Intell Med, vol. 23, no. 1, pp. 89–109, 2001, [Online]. Available: http://ovidsp.ovid.com/ovidweb.cgi?T=JS&PAGE=reference&D=emed5&NEWS=N&AN=2001260608Google Scholar ↗
M. Pal, “Random forest classifier for remote sensing classification,” Int J Remote Sens, vol. 26, no. 1, pp. 217–222, 2005,Google Scholar ↗
doi: 10.1080/01431160412331269698.DOI ↗Google Scholar ↗
L. Breiman, “Random Forests,” 2001.Google Scholar ↗
M. Pal and S. Parija, “Prediction of Heart Diseases using Random Forest,” J Phys Conf Ser, vol. 1817, no. 1, 2021,Google Scholar ↗
doi: 10.1088/1742-6596/1817/1/012009.DOI ↗Google Scholar ↗
O. Shobayo, O. Zachariah, M. O. Odusami, and B. Ogunleye, “Prediction of Stroke Disease with Demographic and Behavioural Data Using Random Forest Algorithm,” Analytics, vol. 2, no. 3, pp. 604–617, 2023,Google Scholar ↗
doi: 10.3390/analytics2030034.DOI ↗Google Scholar ↗
M. T. Islam, M. Raihan, F. Farzana, N. Aktar, P. Ghosh, and S. Kabiraj, “Typical and Non-Typical Diabetes Disease Prediction using Random Forest Algorithm,” 2020 11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020, pp. 1–6, 2020,Google Scholar ↗
doi: 10.1109/ICCCNT49239.2020.9225430.DOI ↗Google Scholar ↗
R. S. Walse, G. D. Kurundkar, S. D. Khamitkar, A. A. Muley, P. U. Bhalchandra, and S. N. Lokhande, “Effective Use of Naïve Bayes, Decision Tree, and Random Forest Techniques for Analysis of Chronic Kidney Disease,” in Information and Communication Technology for Intelligent Systems, T. Senjyu, P. N. Mahalle, T. Perumal, and A. Joshi, Eds., Springer Singapore, 2021, pp. 237–245.Google Scholar ↗
A. Smarra; Francesco; Tjen, Jimmy; D’Innocenzo, “Learning methods for structural damage detection via entropy-based sensors selection,” International Journal of Robust and Nonlinear Control, vol. 32, no. 10, pp. 6035–6067, 2022, doi: 10.1002/rnc.6124.DOI ↗Google Scholar ↗
G. Biau and E. Scornet, “A random forest guided tour,” Test, vol. 25, no. 2, pp. 197–227, 2016, doi: 10.1007/s11749-016-0481-7.DOI ↗Google Scholar ↗
J. Tjen, “Identifikasi Parameter Kualitas Bahan Pangan dengan Metode Entropy-Based Subset Selection (E-SS) (Studi Kasus: Minuman Anggur),” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 1, pp. 47–54, 2024, doi: 10.25126/jtiik.20241116850.DOI ↗Google Scholar ↗
R. El Kharoua, “Alzheimer’s Disease Dataset,” 2024, Kaggle.Google Scholar ↗
R. A. Armstrong, “What causes Alzheimer’s disease?,” Folia Neuropathol, vol. 51, no. 3, pp. 169–188, 2013, doi: 10.5114/fn.2013.37702.DOI ↗Google Scholar ↗
M. Kamiya, A. Osawa, I. Kondo, and T. Sakurai, “Factors associated with cognitive function that cause a decline in the level of activities of daily living in Alzheimer’s disease,” Geriatr Gerontol Int, vol. 18, no. 1, pp. 50–56, 2018,Google Scholar ↗
doi: 10.1111/ggi.13135.DOI ↗Google Scholar ↗

[refR-1] E. Area-Gomez and E. A. Schon, “Alzheimer disease,” Adv Exp Med Biol, vol. 997, no. 1, pp. 149–156, 2017, doi: 10.1007/978-981-10-4567-7_11.DOI ↗Google Scholar ↗

[refR-2] R. Brookmeyer, E. Johnson, K. Ziegler-Graham, and H. M. Arrighi, “Forecasting the global burden of Alzheimer’s disease,” Alzheimer’s and Dementia, vol. 3, no. 3, pp. 186–191, 2007,Google Scholar ↗

[refR-3] doi: 10.1016/j.jalz.2007.04.381.DOI ↗Google Scholar ↗

[refR-4] R. A. Armstrong, “Risk factors for Alzheimer’s disease,” Folia Neuropathol, vol. 57, no. 2, pp. 87–105, 2019,Google Scholar ↗

[refR-5] doi: 10.5114/fn.2019.85929.DOI ↗Google Scholar ↗

[refR-6] R. Green, RC; Clarke, VC; Thompson, NJ; Woodard, JL; Letz, “Early detection of Alzheimer disease: methods, markers, and misgivings,” Alzheimer Dis Assoc Disord, vol. 11, no. 5, p. S1, 1997,Google Scholar ↗

[refR-7] doi: 10.2217/fnl.10.31.DOI ↗Google Scholar ↗

[refR-8] J. Rasmussen and H. Langerman, “Alzheimer’s Disease – Why We Need Early Diagnosis,” Degener Neurol Neuromuscul Dis, vol. Volume 9, pp. 123–130, 2019, doi: 10.2147/dnnd.s228939.DOI ↗Google Scholar ↗

[refR-9] I. Konenko, “Machine learning for medical diagnosis: History, state of the art and perspective,” Artif Intell Med, vol. 23, no. 1, pp. 89–109, 2001, [Online]. Available: http://ovidsp.ovid.com/ovidweb.cgi?T=JS&PAGE=reference&D=emed5&NEWS=N&AN=2001260608Google Scholar ↗

[refR-10] M. Pal, “Random forest classifier for remote sensing classification,” Int J Remote Sens, vol. 26, no. 1, pp. 217–222, 2005,Google Scholar ↗

[refR-11] doi: 10.1080/01431160412331269698.DOI ↗Google Scholar ↗

[refR-12] L. Breiman, “Random Forests,” 2001.Google Scholar ↗

[refR-13] M. Pal and S. Parija, “Prediction of Heart Diseases using Random Forest,” J Phys Conf Ser, vol. 1817, no. 1, 2021,Google Scholar ↗

[refR-14] doi: 10.1088/1742-6596/1817/1/012009.DOI ↗Google Scholar ↗

[refR-15] O. Shobayo, O. Zachariah, M. O. Odusami, and B. Ogunleye, “Prediction of Stroke Disease with Demographic and Behavioural Data Using Random Forest Algorithm,” Analytics, vol. 2, no. 3, pp. 604–617, 2023,Google Scholar ↗

[refR-16] doi: 10.3390/analytics2030034.DOI ↗Google Scholar ↗

[refR-17] M. T. Islam, M. Raihan, F. Farzana, N. Aktar, P. Ghosh, and S. Kabiraj, “Typical and Non-Typical Diabetes Disease Prediction using Random Forest Algorithm,” 2020 11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020, pp. 1–6, 2020,Google Scholar ↗

[refR-18] doi: 10.1109/ICCCNT49239.2020.9225430.DOI ↗Google Scholar ↗

[refR-19] R. S. Walse, G. D. Kurundkar, S. D. Khamitkar, A. A. Muley, P. U. Bhalchandra, and S. N. Lokhande, “Effective Use of Naïve Bayes, Decision Tree, and Random Forest Techniques for Analysis of Chronic Kidney Disease,” in Information and Communication Technology for Intelligent Systems, T. Senjyu, P. N. Mahalle, T. Perumal, and A. Joshi, Eds., Springer Singapore, 2021, pp. 237–245.Google Scholar ↗

[refR-20] A. Smarra; Francesco; Tjen, Jimmy; D’Innocenzo, “Learning methods for structural damage detection via entropy-based sensors selection,” International Journal of Robust and Nonlinear Control, vol. 32, no. 10, pp. 6035–6067, 2022, doi: 10.1002/rnc.6124.DOI ↗Google Scholar ↗

[refR-21] G. Biau and E. Scornet, “A random forest guided tour,” Test, vol. 25, no. 2, pp. 197–227, 2016, doi: 10.1007/s11749-016-0481-7.DOI ↗Google Scholar ↗

[refR-22] J. Tjen, “Identifikasi Parameter Kualitas Bahan Pangan dengan Metode Entropy-Based Subset Selection (E-SS) (Studi Kasus: Minuman Anggur),” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 1, pp. 47–54, 2024, doi: 10.25126/jtiik.20241116850.DOI ↗Google Scholar ↗

[refR-23] R. El Kharoua, “Alzheimer’s Disease Dataset,” 2024, Kaggle.Google Scholar ↗

[refR-24] R. A. Armstrong, “What causes Alzheimer’s disease?,” Folia Neuropathol, vol. 51, no. 3, pp. 169–188, 2013, doi: 10.5114/fn.2013.37702.DOI ↗Google Scholar ↗

[refR-25] M. Kamiya, A. Osawa, I. Kondo, and T. Sakurai, “Factors associated with cognitive function that cause a decline in the level of activities of daily living in Alzheimer’s disease,” Geriatr Gerontol Int, vol. 18, no. 1, pp. 50–56, 2018,Google Scholar ↗

[refR-26] doi: 10.1111/ggi.13135.DOI ↗Google Scholar ↗