Predicting depressive symptoms in middle-aged and elderly adults using sleep data and clinical health markers: A machine learning approach

Bayesian Networks for Prescreening in Depression: Algorithm Development and Validation

BACKGROUND

Identifying individuals with depressive symptomatology (DS) promptly and effectively is of paramount importance for providing timely treatment. Machine learning models have shown promise in this area; however, studies often fall short in demonstrating the practical benefits of using these models and fail to provide tangible real-world applications.

OBJECTIVE

This study aims to establish a novel methodology for identifying individuals likely to exhibit DS, identify the most influential features in a more explainable way via probabilistic measures, and propose tools that can be used in real-world applications.

METHODS

The study used 3 data sets: PROACTIVE, the Brazilian National Health Survey (Pesquisa Nacional de Saúde [PNS]) 2013, and PNS 2019, comprising sociodemographic and health-related features. A Bayesian network was used for feature selection. Selected features were then used to train machine learning models to predict DS, operationalized as a score of ≥10 on the 9-item Patient Health Questionnaire. The study also analyzed the impact of varying sensitivity rates on the reduction of screening interviews compared to a random approach.

RESULTS

The methodology allows the users to make an informed trade-off among sensitivity, specificity, and a reduction in the number of interviews. At the thresholds of 0.444, 0.412, and 0.472, determined by maximizing the Youden index, the models achieved sensitivities of 0.717, 0.741, and 0.718, and specificities of 0.644, 0.737, and 0.766 for PROACTIVE, PNS 2013, and PNS 2019, respectively. The area under the receiver operating characteristic curve was 0.736, 0.801, and 0.809 for these 3 data sets, respectively. For the PROACTIVE data set, the most influential features identified were postural balance, shortness of breath, and how old people feel they are. In the PNS 2013 data set, the features were the ability to do usual activities, chest pain, sleep problems, and chronic back problems. The PNS 2019 data set shared 3 of the most influential features with the PNS 2013 data set. However, the difference was the replacement of chronic back problems with verbal abuse. It is important to note that the features contained in the PNS data sets differ from those found in the PROACTIVE data set. An empirical analysis demonstrated that using the proposed model led to a potential reduction in screening interviews of up to 52% while maintaining a sensitivity of 0.80.

CONCLUSIONS

This study developed a novel methodology for identifying individuals with DS, demonstrating the utility of using Bayesian networks to identify the most significant features. Moreover, this approach has the potential to substantially reduce the number of screening interviews while maintaining high sensitivity, thereby facilitating improved early identification and intervention strategies for individuals experiencing DS.

Depressive symptoms and all-cause mortality among middle-aged and older people in China and associations with chronic diseases

Introduction

It remains unclear whether depressive symptoms are associated with increased all-cause mortality and to what extent depressive symptoms are associated with chronic disease and all-cause mortality. The study aims to explore the relationship between depressive symptoms and all-cause mortality, and how depressive symptoms may, in turn, affect all-cause mortality among Chinese middle-aged and older people through chronic diseases.

Methods

Data were collected from the China Health and Retirement Longitudinal Study (CHARLS). This cohort study involved 13,855 individuals from Wave 1 (2011) to Wave 6 (2020) of the CHARLS, which is a nationally representative survey that collects information from Chinese residents ages 45 and older to explore intrinsic mechanisms between depressive symptoms and all-cause mortality. The Center for Epidemiological Studies Depression Scale (CES-D-10) was validated through the CHARLS. Covariates included socioeconomic variables, living habits, and self-reported history of chronic diseases. Kaplan-Meier curves depicted mortality rates by depressive symptom levels, with Cox proportional hazards regression models estimating the hazard ratios (HRs) of all-cause mortality.

Results

Out of the total 13,855 participants included, the median (Q1, Q3) age was 58.00 (51.00, 63.00) years. Adjusted for all covariates, middle-aged and older adults with depressive symptoms had a higher all-cause mortality rate (HR = 1.20 [95% CI, 1.09-1.33]). An increased rate was observed for 55-64 years old (HR = 1.23 [95% CI, 1.03-1.47]) and more than 65 years old (HR = 1.32 [95% CI, 1.18-1.49]), agricultural Hukou (HR = 1.44, [95% CI, 1.30-1.59]), and nonagricultural workload (HR = 1.81 [95% CI, 1.61-2.03]). Depressive symptoms increased the risks of all-cause mortality among patients with hypertension (HR = 1.19 [95% CI, 1.00-1.40]), diabetes (HR = 1.41[95% CI, 1.02-1.95]), and arthritis (HR = 1.29 [95% CI, 1.09-1.51]).

Conclusion

Depressive symptoms raise all-cause mortality risk, particularly in those aged 55 and above, rural household registration (agricultural Hukou), nonagricultural workers, and middle-aged and older people with hypertension, diabetes, and arthritis. Our findings through the longitudinal data collected in this study offer valuable insights for interventions targeting depression, such as early detection, integrated chronic disease care management, and healthy lifestyles; and community support for depressive symptoms may help to reduce mortality in middle-aged and older people.

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Major Depressive Disorder (MDD) and Generalized Anxiety Disorder (GAD) pose significant burdens on individuals and society, necessitating accurate prediction methods. Machine learning (ML) algorithms utilizing electronic health records and survey data offer promising tools for forecasting these conditions. However, potential bias and inaccuracies inherent in subjective survey responses can undermine the precision of such predictions. This research investigates the reliability of five prominent ML algorithms-a Convolutional Neural Network (CNN), Random Forest, XGBoost, Logistic Regression, and Naive Bayes-in predicting MDD and GAD. A dataset rich in biomedical, demographic, and self-reported survey information is used to assess the algorithms' performance under different levels of subjective response inaccuracies. These inaccuracies simulate scenarios with potential memory recall bias and subjective interpretations. While all algorithms demonstrate commendable accuracy with high-quality survey data, their performance diverges significantly when encountering erroneous or biased responses. Notably, the CNN exhibits superior resilience in this context, maintaining performance and even achieving enhanced accuracy, Cohen's kappa score, and positive precision for both MDD and GAD. This highlights the CNN's superior ability to handle data unreliability, making it a potentially advantageous choice for predicting mental health conditions based on self-reported data. These findings underscore the critical importance of algorithmic resilience in mental health prediction, particularly when relying on subjective data. They emphasize the need for careful algorithm selection in such contexts, with the CNN emerging as a promising candidate due to its robustness and improved performance under data uncertainties.

Major Depressive Disorder Prediction Based on Sleep-Wake Disorders Symptoms in US Adolescents: A Machine Learning Approach from National Sleep Research Resource

Background

There is substantial evidence from previous studies that abnormalities in sleep parameters associated with depression are demonstrated in almost all stages of sleep architecture. Patients with symptoms of sleep-wake disorders have a much higher risk of developing major depressive disorders (MDD) compared to those without.

Objective

The aim of the present study is to establish and compare the performance of different machine learning models based on sleep-wake disorder symptoms data and to select the optimal model to interpret the importance of sleep-wake disorder symptoms to predict MDD occurrence in adolescents.

Methods

We derived data for this work from 2020 to 2021 Assessing Nocturnal Sleep/Wake Effects on Risk of Suicide Phase I Study from National Sleep Research Resource. Using demographic and sleep-wake disorder symptoms data as predictors and the occurrence of MDD measured base on the center for epidemiologic studies depression scale as an outcome, the following six machine learning predictive models were developed: eXtreme Gradient Boosting model (XGBoost), Light Gradient Boosting mode, AdaBoost, Gaussian Naïve Bayes, Complement Naïve Bayes, and multilayer perceptron. The models' performance was assessed using the AUC and other metrics, and the final model's predictor importance ranking was explained.

Results

XGBoost is the optimal predictive model in comprehensive performance with the AUC of 0.804 in the test set. All sleep-wake disorder symptoms were significantly positively correlated with the occurrence of adolescent MDD. The insomnia severity was the most important predictor compared with the other predictors in this study.

Conclusion

This machine learning predictive model based on sleep-wake disorder symptoms can help to raise the awareness of risk of symptoms between sleep-wake disorders and MDD in adolescents and improve primary care and prevention.

Chlorogenic Acids, Acting via Calcineurin, Are the Main Compounds in Centella asiatica Extracts That Mediate Resilience to Chronic Stress in Drosophila melanogaster

Common symptoms of depressive disorders include anhedonia, sleep problems, and reduced physical activity. Drugs used to treat depression mostly aim to increase serotonin signaling but these can have unwanted side effects. Depression has also been treated by traditional medicine using plants like Centella asiatica (CA) and this has been found to be well tolerated. However, very few controlled studies have addressed CA's protective role in depression, nor have the active compounds or mechanisms that mediate this function been identified. To address this issue, we used Drosophila melanogaster to investigate whether CA can improve depression-associated symptoms like anhedonia and decreased climbing activity. We found that a water extract of CA provides resilience to stress induced phenotypes and that this effect is primarily due to mono-caffeoylquinic acids found in CA. Furthermore, we describe that the protective function of CA is due to a synergy between chlorogenic acid and one of its isomers also present in CA. However, increasing the concentration of chlorogenic acid can overcome the requirement for the second isomer. Lastly, we found that chlorogenic acid acts via calcineurin, a multifunctional phosphatase that can regulate synaptic transmission and plasticity and is also involved in neuronal maintenance.