Alzheimer Hastalığının Erken Teşhisinin Çoklu Değişken Kullanarak Tespiti

Öz

Alzheimer hastalığı (AD) Dementia’nın bir türü olup bilişsel bir rahatsızlıktır. Alzheimer Hastalığının teşhisi, özel olmayan çeşitli değerlendirme ve biyobelirteçlere dayanmaktadır. Erken teşhis konulmazsa, hastalığın ilerlemesi ile ölüme bile sonuçlanabilecek ya da yaşam süresini kısaltacak etkileri vardır. Kesin tanı için beyindeki amiloid plaklarına bakılarak teşhis konulsa da bu birikme hastalığın sebebi değil sonuçlarından biri değerlendirilmektedir. Hastalığın erken teşhisinde ve ilk safhalarında amiloid plaklarının birikimi gözlenmesi ile teşhis oldukca zor ve zahmetlidir. Bu çalışmada, bir açık kaynak veri tabanından alınan demanslı hastalara ait klinik, bilişsel ve biyobelirteç veriler ile önişlemeli makine öğrenmesi yöntemleri kullanılarak Alzheimer Hastalığının erken teşhisi için bir yöntem önerilmiştir. Kullanılan yöntemler Karar Ağaçları, Gradient Boost, Extreme Gradient Boost, Light Gradient Boost, Cat Boost ve Rasgele Orman yapılarıdır. Bu yöntemler arasında Gradient Boost %91,25 ile en iyi sonucu sergilemiştir.

Anahtar Kelimeler

• Alzheimer Hastalığı
• MR
• OASIS
• Boosting Yöntemleri

Early Diagnosis of Alzheimer’s Disease Using Multiple Variables

Abstract

Alzheimer's disease (AD) is a type of Dementia and is a cognitive disorder. Diagnosis of Alzheimer's Disease is based on a variety of nonspecific assessments and biomarkers. If not diagnosed early, it has effects that may result in the progression of the disease, even death, or shorten the life span. Although the diagnosis is made by looking at the amyloid plaques in the brain for a definitive diagnosis, this accumulation is considered as one of the results, not the cause of the disease. In the early diagnosis and early stages of the disease, the diagnosis is very difficult and troublesome with the observation of the accumulation of amyloid plaques. In this study, a method for early diagnosis of Alzheimer's Disease is proposed by using preprocessed clinical, cognitive and biomarker data of patients with dementia from an open-source database and machine learning methods. The methods used are Decision Trees, Gradient Boost, Extreme Gradient Boost, Light Gradient Boost, Cat Boost and Random Forest structures. Among these methods, Gradient Boost showed the best result with 91.25%.

Keywords

• Alzheimer Disease
• MR
• OASIS
• Boosting Methods.

References

1. Acharya, U. R., Fernandes, S. L., WeiKoh, J. E., Ciaccio, E. J., Fabell, M. K. M., Tanik, U. J., . . . Yeong, C. H. J. J. o. M. S. (2019). Automated detection of Alzheimer’s disease using brain MRI images–a study with various feature extraction techniques. 43(9), 1-14.
2. Albert, M. S., DeKosky, S. T., Dickson, D., Dubois, B., Feldman, H. H., Fox, N. C., . . . Petersen, R. C. J. F. (2013). The diagnosis of mild cognitive impairment due to Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease. 11(1), 96-106.
3. Altaf, T., Anwar, S. M., Gul, N., Majeed, M. N., Majid, M. J. B. S. P., & Control. (2018). Multi-class Alzheimer's disease classification using image and clinical features. 43, 64-74.
4. Alzheimer's, A. s. A. J., & Dementia. (2016). 2016 Alzheimer's disease facts and figures. 12(4), 459-509.
5. Barnes, J., Carmichael, O. T., Leung, K. K., Schwarz, C., Ridgway, G. R., Bartlett, J. W., . . . Biessels, G. J. J. N. o. a. (2013). Vascular and Alzheimer's disease markers independently predict brain atrophy rate in Alzheimer's Disease Neuroimaging Initiative controls. 34(8), 1996-2002.
6. Bhagwat, N., Viviano, J. D., Voineskos, A. N., Chakravarty, M. M., & biology, A. s. D. N. I. J. P. c. (2018). Modeling and prediction of clinical symptom trajectories in Alzheimer’s disease using longitudinal data. 14(9), e1006376.
7. Braskie, M. N., Toga, A. W., & Thompson, P. M. J. J. o. A. s. D. (2013). Recent advances in imaging Alzheimer's disease. 33(s1), S313-S327.
8. Chakraborty, D., Elhegazy, H., Elzarka, H., & Gutierrez, L. J. A. E. I. (2020). A novel construction cost prediction model using hybrid natural and light gradient boosting. 46, 101201.

9. Chang, Y.-C., Chang, K.-H., & Wu, G.-J. J. A. S. C. (2018). Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions. 73, 914-920.
10. Charbuty, B., Abdulazeez, A. J. J. o. A. S., & Trends, T. (2021). Classification based on decision tree algorithm for machine learning. 2(01), 20-28.
11. Dev, V. A., Eden, M. R. J. C., & engineering, c. (2019). Formation lithology classification using scalable gradient boosted decision trees. 128, 392-404.
12. Doecke, J. D., Laws, S. M., Faux, N. G., Wilson, W., Burnham, S. C., Lam, C.-P., . . . Brown, B. J. A. o. n. (2012). Blood-based protein biomarkers for diagnosis of Alzheimer disease. 69(10), 1318-1325.
13. Eke, C. S., Jammeh, E., Li, X., Carroll, C., Pearson, S., Ifeachor, E. J. I. J. o. B., & Informatics, H. (2020). Early Detection of Alzheimer's Disease with Blood Plasma Proteins Using Support Vector Machines. 25(1), 218-226.
14. Factsheet, W. J. G. W. H. O. (2020). The top 10 causes of death.
15. Ferri, C. P., Prince, M., Brayne, C., Brodaty, H., Fratiglioni, L., Ganguli, M., . . . Huang, Y. J. T. l. (2005). Global prevalence of dementia: a Delphi consensus study. 366(9503), 2112-2117.
16. Gupta, H., Kumar, P., Saurabh, S., Mishra, S. K., Appasani, B., Pati, A., . . . Srinivasulu, A. J. R. R. D. S. T.-S. E. E. E. (2021). CATEGORY BOOSTING MACHINE LEARNING ALGORITHM FOR BREAST CANCER PREDICTION. 66(1), 201-206.
17. Huang, G., Wu, L., Ma, X., Zhang, W., Fan, J., Yu, X., . . . Zhou, H. J. J. o. H. (2019). Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions. 574, 1029-1041.
18. Krauss, C., Do, X. A., & Huck, N. J. E. J. o. O. R. (2017). Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. 259(2), 689-702.
19. LaMontagne, P. J., Benzinger, T. L., Morris, J. C., Keefe, S., Hornbeck, R., Xiong, C., . . . Vlassenko, A. J. M. (2019). OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease.
20. Lancet, T. J. T. L. (2011). The three stages of Alzheimer's disease. In (Vol. 377, pp. 1465): Elsevier.
21. Makin, S. J. N. (2018). The amyloid hypothesis on trial. 559(7715), S4-S4.
22. Malik, G. A., & Robertson, N. P. J. J. o. n. (2017). Treatments in Alzheimer’s disease. 264(2), 416-418.
23. Marcus, D. S., Fotenos, A. F., Csernansky, J. G., Morris, J. C., & Buckner, R. L. (2010). Open Access Series of Imaging Studies: Longitudinal MRI Data in Nondemented and Demented Older Adults. Journal of Cognitive Neuroscience, 22(12), 2677-2684. doi:10.1162/jocn.2009.21407 %J Journal of Cognitive Neuroscience
24. Marcus, D. S., Wang, T. H., Parker, J., Csernansky, J. G., Morris, J. C., & Buckner, R. L. (2007). Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults. Journal of Cognitive Neuroscience, 19(9), 1498-1507. doi:10.1162/jocn.2007.19.9.1498 %J Journal of Cognitive Neuroscience
25. McKhann, G. M., Knopman, D. S., Chertkow, H., Hyman, B. T., Jack Jr, C. R., Kawas, C. H., . . . dementia. (2011). The diagnosis of dementia due to Alzheimer's disease: recommendations from the National Institute on Aging‐Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease. 7(3), 263-269.
26. Merlo Pich, E., Jeromin, A., Frisoni, G. B., Hill, D., Lockhart, A., Schmidt, M. E., . . . Therapy. (2014). Imaging as a biomarker in drug discovery for Alzheimer’s disease: is MRI a suitable technology? , 6(4), 1-7.
27. Mismetti, P., Laporte, S., Pellerin, O., Ennezat, P.-V., Couturaud, F., Elias, A., . . . Roy, P.-M. J. J. (2015). Effect of a retrievable inferior vena cava filter plus anticoagulation vs anticoagulation alone on risk of recurrent pulmonary embolism: a randomized clinical trial. 313(16), 1627-1635.
28. Morris, G. P., Clark, I. A., & Vissel, B. J. A. n. (2018). Questions concerning the role of amyloid-β in the definition, aetiology and diagnosis of Alzheimer’s disease. 136(5), 663-689.
29. Peña-Bautista, C., Vigor, C., Galano, J.-M., Oger, C., Durand, T., Ferrer, I., . . . Medicine. (2018). Plasma lipid peroxidation biomarkers for early and non-invasive Alzheimer Disease detection. 124, 388-394.
30. Perrin, R. J., Fagan, A. M., & Holtzman, D. M. J. N. (2009). Multimodal techniques for diagnosis and prognosis of Alzheimer's disease. 461(7266), 916-922.
31. Prince, M., Comas-Herrera, A., Knapp, M., Guerchet, M., & Karagiannidou, M. (2016). World Alzheimer report 2016: improving healthcare for people living with dementia: coverage, quality and costs now and in the future.
32. Toğaçar, M., Ergen, B., Cömert, Z. J. C. i. b., & medicine. (2020). COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches. 121, 103805.
33. Tse, K. H., & Herrup, K. J. J. o. n. (2017). Re‐imagining Alzheimer's disease–the diminishing importance of amyloid and a glimpse of what lies ahead. 143(4), 432-444.
34. Wang, T., Qiu, R. G., & Yu, M. J. S. r. (2018). Predictive modeling of the progression of Alzheimer’s disease with recurrent neural networks. 8(1), 1-12.
35. Zhang, F., Wei, J., Li, X., Ma, C., & Gao, Y. J. J. o. A. s. D. (2018). Early candidate urine biomarkers for detecting Alzheimer’s disease before amyloid-β plaque deposition in an APP (swe)/PSEN1 dE9 transgenic mouse model. 66(2), 613-637.
36. Zhang, Y., Zhao, Z., & Zheng, J. J. J. o. H. (2020). CatBoost: A new approach for estimating daily reference crop evapotranspiration in arid and semi-arid regions of Northern China. 588, 125087.
37. Zhao, J., Feng, Q., Wu, P., Lupu, R. A., Wilke, R. A., Wells, Q. S., . . . Wei, W.-Q. J. S. r. (2019). Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction. 9(1), 1-10.