An approximation to the risk factors linked to alzheimer’s disease

Main Article Content

Johan Sebastián Medina Cañizales
Octavio José Salcedo Parra
Juan Pablo Rodríguez Miranda

Keywords

P-value, Alzheimer, risk factors, scrum, artificial intelligent, machine learning, dataset

Abstract

The objective of this project is to develop an application that integrates AI, machine learning and cloud computing technologies to reduce the user’s chances of suffering from Alzheimer’s disease in the future. The expectations regarding the application include that it can collect data about the most common risk factors in Alzheimer patients such as education level, hormonal and nutritional levels and lifestyle habits (smoking, sedentary lifestyle, alcohol, etc.) to prevent Alzheimer. It is also expected that it can determine the level of danger and the main risk factors that the user should be aware of. This software will keep running in cloud computing to ensure that it is always synchronized with the databases containing the factors described above, such as MEDLINE, PubMed, AlzForum (ALZRISK) and ADNI. The latter collects different data sources such as AIBL and DoD-ADNI. It was found that the main risk factors that increase the probability of suffering the disease are: being overweight with a maximum value of 0.5 p-value when the diet followed is not balanced. A value of 0.3 p-value indicates that the diet is not followed. A deficit in physical activity is related to a p-value of 0.11. The years of formal studies also contribute by a significant value of 0.008 when said years are between 0 and 5. Stress from work can contribute with a maximum value of 0.006.

Abstract 499 | PDF en inglés Downloads 180

References

Why the number of Americans with Alzheimer’s could more than double by 2050, 2019. Disponible online https://to.pbs. org/2W5bBje

Factors associated with quality of life in patients with Alzheimer’s disease, Coralie Barbe, Damien Jolly, Isabella Monrrone, 2018. https://doi.org/10.1186/s12877-018-0855-7

The role of sleep deprivation and circadian rhythm disruption as risk factors of Alzheimer’s disease, Hao Wu, Sophie Dunnett, Yuen-Shan Ho, 2019. https://doi.org/10.1016/j. yfrne.2019.100764 [4] Increased Alzheimer’s risk during the menopause transition, Lisa Mosconi, Aneela Rahman, Ivan Diaz, Xian Wu, 2018. https://doi. org/10.1371/journal.pone.0207885

Alzheimer’s disease: nutritional status and cognitive aspects associated with disease severity, Lineau Correa, Gloria Souza, Julia Laura Delbue, Barbosa Nascimento, 2018. http://dx.doi.org/10.20960/nh.2067

Prevalencia de variantes en el gen de la apolipoproteína E (APOE) en adultos de la población general del área urbana de Medellín (Antioquia), Arango Viana Juan Carlos, Palacio Carlos, García Valencia, 2014. http://www. redalyc.org/articulo.oa?id=80631556004

Factores asociados con el declive cognitivo en población menor de 65 años. Una revisión, Lopera Restrepo Francisco, Aguirre Camilo, Giraldo Arango Diana, Jaimes Barragan Fabian, 2014. http://www.redalyc.org/articulo. oa?id=80631556008

Cholesterol, APOE genotype, and Alzheimer disease, K. Hall, J. Murrell, R. Evans, 2006. https://doi.org/10.1212/01. wnl.0000194507.39504.17

Midlife Work-Related Stress Increases Dementia Risk in Later Life: The CAIDE 30-Year Study, Shireen Sindi, Goran Hagman, Krister Hakansson, 2017. https://doi.org/10.1093/ geronb/gbw043

Detecting Alzheimer’s Disease on Small Dataset: A Knowledge Transfer Perspective, Wei Li, Yifei Zhao, Xi Chen, 2019. http://bit. ly/2xc6SkT

Deep Learning Framework for Alzheimer’s Disease Diagnosis, Chiyu Feng, Ahmed Elazab, Peng Yang, 2019. http://bit. ly/2Lh7le2

Learn Python Programming and Machine Learning, DataQuest, http://bit.ly/30sA5Vd

Find the largest three elements in an array, GeeksForGeeks, http://bit.ly/2Jv2nsM