Previsão do comprometimento cognitivo leve: integrando variáveis cognitivas e motoras
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1258Palavras-chave:
Prognóstico, Aprendizado de Máquina, Comprometimento Cognitivo LeveResumo
Objetivo: O Comprometimento Cognitivo Leve (CCL) representa uma fase intermediária entre o envelhecimento normal e a demência, exigindo uma detecção precoce para impedir a sua progressão. Este estudo tem como objetivo desenvolver um modelo de classificação de aprendizado de máquina para prever com precisão o prognóstico de indivíduos com CCL, diferenciando-os dos saudáveis. Método: O método integra variáveis motoras e cognitivas, além de informações autorrelatadas. Foram aplicados os algoritmos SVM, KNN e XGBoost. A melhor previsão foi avaliada pelo método Shapley Value para determinação da importância de cada variável. Resultados: O SVM apresentou melhor resultado, alcançando 88% de sensibilidade e revelando que as variáveis do domínio motor e dos domínios cognitivo e motor são altamente relevantes para a classificação. Conclusão: O método desenvolvido, além de ser mais acessível, apresentou alta sensibilidade na classificação do CCL a partir da integração de variáveis cognitivas e motoras.
Referências
Petersen RC. Mild cognitive impairment. CONTINUUM: Lifelong Learning in Neurology. 2016;22(2 Dementia):404. DOI: https://doi.org/10.1212/CON.0000000000000313
Sabbagh MN, Boada M, Borson S, Chilukuri M, Doraiswamy PM, Dubois B, et al. Rationale for Early Diagnosis of Mild Cognitive Impairment (MCI) supported by Emerging Digital Technologies [Re- view]. Journal of Prevention of Alzheimer’s Disease. 2020;7(3):158 – 164. DOI: https://doi.org/10.14283/jpad.2020.19
de Oliveira Silva F, Ferreira JV, Plácido J, Chagas D, Praxedes J, Guimarães C, et al. Stages of mild cognitive impairment and Alzheimer’s disease can be differentiated by declines in timed up and go test: A systematic review and meta-analysis [Review]. Archives of Gerontology and Geriatrics. 2019;85. DOI: https://doi.org/10.1016/j.archger.2019.103941
Javeed A, Dallora AL, Berglund JS, Ali A, Ali L, Anderberg P. Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions [Article]. Journal of Medical Systems. 2023;47(1). DOI: https://doi.org/10.1007/s10916-023-01906-7
Gómez-Ramírez J, Ávila Villanueva M, Fernández-Blázquez MA. Selecting the most important self-assessed features for predicting conversion to mild cognitive impairment with random forest and permutation- based methods [Article]. Scientific Reports. 2020;10(1). DOI: https://doi.org/10.1038/s41598-020-77296-4
Twait EL, Andaur Navarro CL, Gudnason V, Hu YH, Launer LJ, Geer- lings MI. Dementia prediction in the general population using clinically accessible variables: a proof-of-concept study using machine learning. The AGES-Reykjavik study [Article]. BMC Medical Informatics and Decision Making. 2023;23(1). DOI: https://doi.org/10.1186/s12911-023-02244-x
Aljumaili M, McLeod R, Friesen M. Serious Games and ML for Detecting MCI. In: 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP); 2019. p. 1-5. DOI: https://doi.org/10.1109/GlobalSIP45357.2019.8969123
Grueso S, Viejo-Sobera R. Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer’s disease dementia: a systematic review. Alzheimer’s research & therapy. 2021;13:1- 29. DOI: https://doi.org/10.1186/s13195-021-00900-w
Plácido J, Ferreira JV, Araújo J, Silva FdO, Ferreira RB, Guimarães C, et al. Beyond the Mini-Mental State Examination: The use of physical and spatial navigation tests to help to screen for mild cognitive impairment and Alzheimer’s disease. Journal of Alzheimer’s Disease. 2021;81(3):1243-52.
Ghoraani B, Boettcher LN, Hssayeni MD, Rosenfeld A, Tolea MI, Galvin JE. Detection of mild cognitive impairment and Alzheimer’s dis- ease using dual-task gait assessments and machine learning. Biomedical signal processing and control. 2021;64:102249. DOI: https://doi.org/10.1016/j.bspc.2020.102249
Okpara C, Edokwe C, Ioannidis G, Papaioannou A, Adachi JD, Thabane L. The reporting and handling of missing data in longitudinal studies of older adults is suboptimal: a methodological survey of geriatric journals. BMC medical research methodology. 2022;22(1):122. DOI: https://doi.org/10.1186/s12874-022-01605-w
Minhas S, Khanum A, Riaz F, Khan SA, Alvi A. Predicting Progression From Mild Cognitive Impairment to Alzheimer’s Disease Using Autoregressive Modelling of Longitudinal and Multimodal Biomarkers. IEEE Journal of Biomedical and Health Informatics. 2018;22(3):818-25. DOI: https://doi.org/10.1109/JBHI.2017.2703918
Sarker IH. Machine learning: Algorithms, real-world applications and research directions. SN computer science. 2021;2(3):160. DOI: https://doi.org/10.1007/s42979-021-00592-x
Bloice MD, Holzinger A. A tutorial on machine learning and data science tools with python. Machine Learning for Health Informatics: State-of-the-Art and Future Challenges. 2016:435-80. DOI: https://doi.org/10.1007/978-3-319-50478-0_22
Wang J, Wang Z, Liu N, Liu C, Mao C, Dong L, et al. Random forest model in the diagnosis of dementia patients with normal mini- mental state examination scores. Journal of personalized medicine. 2022;12(1):37. DOI: https://doi.org/10.3390/jpm12010037
Tatiyama Miyamoto S, Júnior I, Berg K, Ramos L, Natour J. Brazilian version of the Berg Balance Scale. Brazilian journal of medical and biological research = Revista brasileira de pesquisas médicas e biológicas / Sociedade Brasileira de Biofísica [et al]. 2004 09;37:1411- 21. DOI: https://doi.org/10.1590/S0100-879X2004000900017
Teixeira I, de Oliveira Silva F, Ferreira J, Plácido J, Marinho V, Deslandes A. Utility of handgrip strength cut-offs for identification of weakness and disability in community-dwelling older people with mild cognitive impairment and Alzheimer’s disease. Jornal Brasileiro de Psiquiatria. 2019 12;68:208-14. DOI: https://doi.org/10.1590/0047-2085000000248
Plácido J, Ferreira J, Araújo J, de Oliveira Silva F, Ferreira R, Guimarães C, et al. Beyond the Mini-Mental State Examination: The Use of Physical and Spatial Navigation Tests to Help to Screen for Mild Cognitive Impairment and Alzheimer’s Disease. Journal of Alzheimer’s Disease. 2021 04;81:1-10. DOI: https://doi.org/10.3233/JAD-210106
Whitson HE, Potter GG, Feld JA, Plassman BL, Reynolds K, Sloane R, et al. Dual-task gait and Alzheimer’s disease genetic risk in cognitively Normal adults: a pilot study. Journal of Alzheimer’s Disease. 2018;64(4):1137-48. DOI: https://doi.org/10.3233/JAD-180016
Han G, Maruta M, Ikeda Y, Ishikawa T, Tanaka H, Koyama A, et al. Relationship between Performance on the Mini-Mental State Examination Sub-Items and Activities of Daily Living in Patients with Alzheimer’s Disease. Journal of Clinical Medicine. 2020 05;9:1537. DOI: https://doi.org/10.3390/jcm9051537
Carvalho G, Caramelli P. Normative data for middle-aged Brazilians in Verbal Fluency (animals and FAS), Trail Making Test (TMT) and Clock Drawing Test (CDT). Dementia Neuropsychologia. 2020 03;14:14-23. DOI: https://doi.org/10.1590/1980-57642020dn14-010003
Lichtenberger EO, Kaufman AS. Essentials of WAIS-IV assessment. vol. 50. John Wiley & Sons; 2009.
Ha J, Kambe M, Pe J. Data Mining: Concepts and Techniques. Elsevier; 2011.
Snoek J, Larochelle H, Adams RP. Practical Bayesian optimization of machine learning algorithms. vol. 4; 2012. p. 2951 – 2959.
Lundberg SM, Lee SI. A unified approach to interpreting model predictions. vol. 2017-December; 2017. p. 4766 – 4775.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
A submissão de um artigo ao Journal of Health Informatics é entendida como exclusiva e que não está sendo considerada para publicação em outra revista. A permissão dos autores para a publicação de seu artigo no J. Health Inform. implica na exclusiva autorização concedida aos editores para incluí-lo na revista. Ao submeter um artigo, ao autor será solicitada a permissão eletrônica de um Termo de Transferência de Direitos Autorais. Uma mensagem eletrônica será enviada ao autor correspondente confirmando o recibo do manuscrito e o aceite da Declaração de Direito Autoral.
