Construction of a classification model for dementia among Brazilian adults aged 50 and over
arXiv:2602.16887v1 Announce Type: new Abstract: To build a dementia classification model for middle-aged and elderly Brazilians, implemented in Python, combining variable selection and multivariable analysis, using low-cost variables with modification potential. Observational study with a predictive modeling approach using a cross-sectional design, aimed at estimating the chances of developing dementia, using data from the Brazilian Longitudinal Study of Aging (ELSI-Brazil), involving 9,412 participants. Dementia was determined based on neuropsychological assessment and informant-based cognitive function. Analyses were performed using Random Forest (RF) and multivariable logistic regression to estimate the risk of dementia in the middle-aged and elderly populations of Brazil. The prevalence of dementia was 9.6%. The highest odds of dementia were observed in illiterate individuals (Odds Ratio (OR) = 7.42), individuals aged 90 years or older (OR = 11.00), low weight (OR = 2.11), low han
arXiv:2602.16887v1 Announce Type: new Abstract: To build a dementia classification model for middle-aged and elderly Brazilians, implemented in Python, combining variable selection and multivariable analysis, using low-cost variables with modification potential. Observational study with a predictive modeling approach using a cross-sectional design, aimed at estimating the chances of developing dementia, using data from the Brazilian Longitudinal Study of Aging (ELSI-Brazil), involving 9,412 participants. Dementia was determined based on neuropsychological assessment and informant-based cognitive function. Analyses were performed using Random Forest (RF) and multivariable logistic regression to estimate the risk of dementia in the middle-aged and elderly populations of Brazil. The prevalence of dementia was 9.6%. The highest odds of dementia were observed in illiterate individuals (Odds Ratio (OR) = 7.42), individuals aged 90 years or older (OR = 11.00), low weight (OR = 2.11), low handgrip strength (OR = 2.50), self-reported black skin color (OR = 1.47), physical inactivity (OR = 1.61), self-reported hearing loss (OR = 1.65), and presence of depressive symptoms (OR = 1.72). Higher education (OR=0.44), greater life satisfaction (OR=0.72), and being employed (OR=0.78) were protective factors. The RF model outperformed logistic regression, achieving an area under the ROC curve of 0.776, with a sensitivity of 0.708, a specificity of 0.702, an F1-score of 0.311, a G-means of 0.705, and an accuracy of 0.703. Conclusion: The findings reinforce the multidimensional nature of dementia and the importance of accessible factors for identifying vulnerable individuals. Strengthening public policies focused on promoting brain health can contribute significantly to the efficient allocation of resources in primary care and dementia prevention in Brazil
Executive Summary
This article presents a novel classification model for dementia among Brazilian adults aged 50 and over, leveraging data from the Brazilian Longitudinal Study of Aging (ELSI-Brazil). Employing a Random Forest (RF) algorithm and multivariable logistic regression, the study identifies key predictors of dementia, including demographic, health, and lifestyle factors. The findings underscore the importance of accessible factors in identifying vulnerable individuals and underscore the potential for strengthening public policies focused on promoting brain health. The model's predictive performance is impressive, with an area under the ROC curve of 0.776. The study's contributions to dementia prevention and public health policy are significant, with far-reaching implications for resource allocation in primary care and dementia prevention in Brazil.
Key Points
- ▸ The study employs a Random Forest (RF) algorithm and multivariable logistic regression to identify predictors of dementia among Brazilian adults aged 50 and over.
- ▸ Key predictors of dementia include demographic, health, and lifestyle factors, such as education level, handgrip strength, physical inactivity, and self-reported hearing loss.
- ▸ The model's predictive performance is impressive, with an area under the ROC curve of 0.776.
Merits
Strength of Predictive Model
The study's use of a Random Forest (RF) algorithm and multivariable logistic regression yields a robust and accurate predictive model, with impressive performance metrics.
Identification of Accessible Factors
The study highlights the importance of accessible factors, such as education level and handgrip strength, in identifying vulnerable individuals at risk of dementia.
Policy-Relevant Findings
The study's findings have significant implications for public health policy, emphasizing the need for strengthening policies focused on promoting brain health and resource allocation in primary care and dementia prevention.
Demerits
Limited Generalizability
The study's findings may not be generalizable to other populations, due to the specificity of the dataset and the study's focus on Brazilian adults aged 50 and over.
Need for Longitudinal Study
A longitudinal study design would provide more insight into the temporal relationships between predictors and dementia outcomes, rather than relying on a cross-sectional design.
Expert Commentary
The study's contributions to dementia prevention and public health policy are significant, with far-reaching implications for resource allocation in primary care and dementia prevention in Brazil. The use of a Random Forest (RF) algorithm and multivariable logistic regression yields a robust and accurate predictive model, with impressive performance metrics. However, the study's findings may not be generalizable to other populations, and a longitudinal study design would provide more insight into the temporal relationships between predictors and dementia outcomes. Despite these limitations, the study provides valuable insights into the importance of accessible factors in identifying vulnerable individuals at risk of dementia and underscores the need to address health disparities in public health policy.
Recommendations
- ✓ Future studies should aim to replicate the study's findings in other populations and explore the use of machine learning algorithms in dementia prevention and public health policy.
- ✓ Public health policymakers should prioritize strengthening policies focused on promoting brain health and resource allocation in primary care and dementia prevention, and incorporate accessible factors into their assessments of patients at risk of dementia.
