Machine Learning for Prediction of Cognitive Health in Adults Using Sociodemographic, Neighbourhood Environmental, and Lifestyle Factors

Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods

OBJECTIVES

Over-the-counter (OTC) antibiotic use can cause antibiotic resistance, threatening global public health gains. To counter OTC use, this study used machine learning (ML) methods to identify predictors of OTC antibiotic use in rural Pune, India.

METHODS

The features of OTC antibiotic use were selected using stepwise logistic, lasso, random forest, XGBoost, and Boruta algorithms. Regression and tree-based models with all confirmed and tentatively important features were built to predict the use of OTC antibiotics. Five-fold cross-validation was used to tune the models' hyperparameters. The final model was selected based on the highest area under the curve (AUROC) with a 95% confidence interval (CI) and the lowest log-loss.

RESULTS

In rural Pune, the prevalence of OTC antibiotic use was 35.9% (95% CI, 31.6 to 40.5). The perception that buying medicines directly from a medicine shop/pharmacy is useful, using antibiotics for eye-related complaints, more household members consuming antibiotics, and longer duration and higher doses of antibiotic consumption in rural blocks and other social groups were confirmed as important features by the Boruta algorithm. The final model was the XGBoost+Boruta model with 7 predictors (AUROC, 0.934; 95% CI, 0.891 to 0.978; log-loss, 0.279) log-loss.

CONCLUSIONS

XGBoost+Boruta, with 7 predictors, was the most accurate model for predicting OTC antibiotic use in rural Pune. Using OTC antibiotics for eye-related complaints, higher consumption of antibiotics and the perception that buying antibiotics directly from a medicine shop/pharmacy is useful were identified as key factors for planning interventions to improve awareness about proper antibiotic use.

Empirically derived psychosocial-behavioral phenotypes in Black/African American and Hispanic/Latino older adults enrolled in HABS-HD: Associations with AD biomarkers and cognitive outcomes

INTRODUCTION

Identification of psychosocial-behavioral phenotypes to understand within-group heterogeneity in risk and resiliency to Alzheimer's disease (AD) within Black/African American and Hispanic/Latino older adults is essential for the implementation of precision health approaches.

METHODS

A cluster analysis was performed on baseline measures of socioeconomic resources (annual income, social support, occupational complexity) and psychiatric distress (chronic stress, depression, anxiety) for 1220 racially/ethnically minoritized adults enrolled in the Health and Aging Brain Study-Health Disparities (HABS-HD). Analyses of covariance adjusting for sociodemographic factors examined phenotype differences in cognition and plasma AD biomarkers.

RESULTS

The cluster analysis identified (1) Low Resource/High Distress (n = 256); (2) High Resource/Low Distress (n = 485); and (3) Low Resource/Low Distress (n = 479) phenotypes. The Low Resource/High Distress phenotype displayed poorer cognition and higher plasma neurofilament light chain; differences between the High Resource/Low Distress and Low Resource/Low Distress phenotypes were minimal.

DISCUSSION

The identification of psychosocial-behavioral phenotypes within racially/ethnically minoritized older adults is crucial to the development of targeted AD prevention and intervention efforts.

Are retired persons fitter in their psychological capacities than unemployed? A cross-sectional representative study in Germany

OBJECTIVES

Beyond specific aspects of numerical or verbal intelligence or cognitive speed, a broad range of psychological capacities are generally important in school, job and social life for all age groups. People have to quit the labour market up from a certain age about 65, whereas (younger) unemployed are motivated for return to work. The question is which psychological capacity profiles can be found in different employment groups (employed, mini-jobbers, voluntary service, retired, unemployed).

DESIGN

A representative cross-sectional survey was conducted in Germany, reaching 2528 persons.

SETTING

Republic of Germany.

PARTICIPANTS

Randomly selected inhabitants throughout Germany.

PRIMARY AND SECONDARY OUTCOME MEASURES

Participants reported their sociodemographic and work characteristics, as well as their psychological capacity profiles (Mini-ICF-APP-S) and work-related specific mental health problems (work-anxiety, embitterment).

RESULTS

The unemployed had-compared with all other groups-highest rates of work-anxiety and embitterment (16.3%). In contrast to the unemployed, the 'older' (70 aged) retired group, who were no longer working on the labour market, seldomly reported work-anxiety (2.6%) or embitterment (4.2%). The unemployed had the worst capacity profiles, most frequently no school degree (11.5%), most unemployment in their history (four times, as compared with once in the older retired). The psychological capacity profiles of the retired were similar to employed persons.

CONCLUSIONS

Keeping older persons with high psychological capacity levels in working life could be an alternative to forced reintegration of people with chronic participation problems into the competitive labour market. Unemployed persons with chronic health and participation problems might benefit from other social inclusion means.

Characteristics of urban neighbourhood environments and cognitive age in mid-age and older adults

In this cross-sectional study, we examined the extent to which features of the neighbourhood natural, built, and socio-economic environments were related to cognitive age in adults (N = 3418, Mage = 61 years) in Australia. Machine learning estimated an individual's cognitive age from assessments of processing speed, verbal memory, premorbid intelligence. A 'cognitive age gap' was calculated by subtracting chronological age from predicted cognitive age and was used as a marker of cognitive age. Greater parkland availability and higher neighbourhood socio-economic status were associated with a lower cognitive age gap score in confounder- and mediator-adjusted regression models. Cross-sectional design is a limitation. Living in affluent neighbourhoods with access to parks maybe beneficial for cognitive health, although selection mechanisms may contribute to the findings.

Predicting Multimorbidity Using Saudi Health Indicators (Sharik) Nationwide Data: Statistical and Machine Learning Approach

The Saudi population is at high risk of multimorbidity. The risk of these morbidities can be reduced by identifying common modifiable behavioural risk factors. This study uses statistical and machine learning methods to predict factors for multimorbidity in the Saudi population. Data from 23,098 Saudi residents were extracted from the "Sharik" Health Indicators Surveillance System 2021. Participants were asked about their demographics and health indicators. Binary logistic models were used to determine predictors of multimorbidity. A backpropagation neural network model was further run using the predictors from the logistic regression model. Accuracy measures were checked using training, validation, and testing data. Females and smokers had the highest likelihood of experiencing multimorbidity. Age and fruit consumption also played a significant role in predicting multimorbidity. Regarding model accuracy, both logistic regression and backpropagation algorithms yielded comparable outcomes. The backpropagation method (accuracy 80.7%) was more accurate than the logistic regression model (77%). Machine learning algorithms can be used to predict multimorbidity among adults, particularly in the Middle East region. Different testing methods later validated the common predicting factors identified in this study. These factors are helpful and can be translated by policymakers to consider improvements in the public health domain.

Machine learning techniques for identifying mental health risk factor associated with schoolchildren cognitive ability living in politically violent environments

Introduction

Mental health and cognitive development are critical aspects of a child's overall well-being; they can be particularly challenging for children living in politically violent environments. Children in conflict areas face a range of stressors, including exposure to violence, insecurity, and displacement, which can have a profound impact on their mental health and cognitive development.

Methods

This study examines the impact of living in politically violent environments on the mental health and cognitive development of children. The analysis was conducted using machine learning techniques on the 2014 health behavior school children dataset, consisting of 6373 schoolchildren aged 10-15 from public and United Nations Relief and Works Agency schools in Palestine. The dataset included 31 features related to socioeconomic characteristics, lifestyle, mental health, exposure to political violence, social support, and cognitive ability. The data was balanced and weighted by gender and age.

Results

This study examines the impact of living in politically violent environments on the mental health and cognitive development of children. The analysis was conducted using machine learning techniques on the 2014 health behavior school children dataset, consisting of 6373 schoolchildren aged 10-15 from public and United Nations Relief and Works Agency schools in Palestine. The dataset included 31 features related to socioeconomic characteristics, lifestyle, mental health, exposure to political violence, social support, and cognitive ability. The data was balanced and weighted by gender and age.

Discussion

The findings can inform evidence-based strategies for preventing and mitigating the detrimental effects of political violence on individuals and communities, highlighting the importance of addressing the needs of children in conflict-affected areas and the potential of using technology to improve their well-being.

Machine Learning Models for Data-Driven Prediction of Diabetes by Lifestyle Type

The prevalence of diabetes has been increasing in recent years, and previous research has found that machine-learning models are good diabetes prediction tools. The purpose of this study was to compare the efficacy of five different machine-learning models for diabetes prediction using lifestyle data from the National Health and Nutrition Examination Survey (NHANES) database. The 1999-2020 NHANES database yielded data on 17,833 individuals data based on demographic characteristics and lifestyle-related variables. To screen training data for machine models, the Akaike Information Criterion (AIC) forward propagation algorithm was utilized. For predicting diabetes, five machine-learning models (CATBoost, XGBoost, Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM)) were developed. Model performance was evaluated using accuracy, sensitivity, specificity, precision, F1 score, and receiver operating characteristic (ROC) curve. Among the five machine-learning models, the dietary intake levels of energy, carbohydrate, and fat, contributed the most to the prediction of diabetes patients. In terms of model performance, CATBoost ranks higher than RF, LG, XGBoost, and SVM. The best-performing machine-learning model among the five is CATBoost, which achieves an accuracy of 82.1% and an AUC of 0.83. Machine-learning models based on NHANES data can assist medical institutions in identifying diabetes patients.