Analysis of Risk Factors in Dementia Through Machine Learning

Abstract

Background: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer’s disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. Objective: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). Methods: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. Results: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. Conclusion: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

“…These conditions include injuries, diet, sepsis, and drug overdose. Eight studies were on mental and cognitive health problems including various forms of depression and dementia ( 37 , 50 , 53 , 57 , 84 , 101 ). These studies were conducted in EUR, AMR, and SEAR.…”

Identifying a group of factors predicting cognitive impairment among older adults

“…We applied different methods (traditional logistic regression and SVM models) to derive robust and stable models. Though a systematic review found no benefit in machine learning over logistic regression in clinical prediction [ 34 ], machine learning may perform better than logistic regression in smaller samples [ 35 ], and with high dimension data [ 36 ]. The reason for using both logistic regression and SVM models was to increase the chances that important variables would be included in the final prediction model.…”

Evaluating the use of Hyperspectral Imaging as Complementary Blood Sample Tests

“…Originally, the participants involved in the study were divided into two groups (control and case subjects), where the control group involved healthy subjects and the case group involved subjects with Alzheimer's disease [18]. In this study, all the participants have been included in the same group since the aim is to find a correlation between the spectral properties of the blood plasma HS images and the results of their respective blood tests.…”