The reciprocal relationship between physical activity and depression: Does age matter?

Using machine learning models to identify the risk of depression in middle-aged and older adults with frequent and infrequent nicotine use: A cross-sectional study

BACKGROUND

Depression is very prevalent in middle-aged and older smokers. Therefore, we aimed to identify the risk of depression among middle-aged and older adults with frequent and infrequent nicotine use, as this is quite necessary for supporting their well-being.

METHODS

This study included a total of 10,821 participants, which were derived from the China Health and Retirement Longitudinal Study Wave 5, 2020 (CHARLS-5). Five machine learning (ML) algorithms were employed. Some metrics were used to evaluate the performance of models, including area under the receiver operating characteristic curve (AUC), positive predictive value (PPV), specificity, accuracy.

RESULTS

10,821 participants (6472 males, 4349 females) had a mean age of 60.47 ± 8.98, with a score of 8.90 ± 6.53 on depression scale. For middle-aged and older adults with frequent nicotine use, random forest (RF) achieved the highest AUC value, PPV and specificity (0.75, 0.74 and 0.88, respectively). For the other group, support vector machines (SVM) showed the highest PPV (0.74), and relatively high accuracy and specificity (0.72 and 0.87, respectively). Feature importance analysis indicated that "dissatisfaction with life" was the most important variable of identifying the risk of depression in the SVM model, while "attitude towards expected life span" was the most important one in the RF model.

LIMITATIONS

CHARLS-5 was collected during the COVID-19, so our results may be influenced by the pandemic.

CONCLUSIONS

This study indicated that certain ML models can ideally identify the risk of depression in middle-aged and older adults, which holds significant value for their health management.

Longitudinal relationships between depressive symptoms, functional impairment, and physical activity in later late life

The purpose of this study was to investigate relationships between depressive symptoms, functional disability, and physical activity over time in community-dwelling older adults. The Religious Order Study and Rush Memory and Aging Project are longitudinal cohort studies based in the United States which began recruitment in 1994 and 1997, respectively. This analysis included 1611 participants (27.4% male, 92.9% White, 74.7% cognitively normal) who were included at age 80 and followed until age 90. Depressive symptoms were assessed using the modified Center for Epidemiologic Studies Depression scale. Functional disability was assessed using the Instrumental Activities of Daily Living (IADL) scale. Physical activity was self-reported hours of weekly exercise. Reciprocal temporal relationships between these variables were investigated using a random intercept cross-lagged panel model, which decomposes observed variables into stable between-person ('trait') and variable within-person ('state') components to estimate the directional effects between variables over time. Traits for depressive symptoms, IADL disability, and physical activity were correlated. IADL disability showed autoregressive effects; disability starting at age 82 strongly predicted subsequent disability. Consistent autoregressive effects were not observed for depressive symptoms nor physical activity. Several small cross-lagged effects between states were observed for IADL disability and physical activity, as well as for IADL disability and depressive symptoms. There were no direct effects between depressive symptoms and physical activity, but several paths through IADL disability were observed between ages 82 and 88. Functional disability played an important role in octogenarians, highlighting the importance of maintaining functional independence later in life.

Bi-directional relationships between physical activity and mental health among a large sample of Canadian youth: a sex-stratified analysis of students in the COMPASS study

OBJECTIVE

The aim of this research was to examine the bidirectional association between self-reported symptoms of mental disorder and physical activity among a large sample of Canadian secondary school students over time.

METHODS

Linked survey data were obtained from 28,567 grade 9 to 12 students across Canada participating in two waves of the COMPASS Study (2017-18; 2018-19). Autoregressive cross-lagged models were run to examine the reciprocal relationships between self-reported moderate-to-vigorous physical activity (MVPA) and symptoms of depression (CESD-10) and anxiety (GAD-7). Models were stratified by gender, and accounted for grade, ethno-racial identity, and school-level clustering.

RESULTS

Autoregressive associations show that neither symptoms of anxiety nor depression, at baseline, were predictive of mean MVPA at follow-up - consistent for the full sample and among both males and females. Higher MVPA among males at baseline was associated with lower symptoms of both anxiety (β = - 0.03, p = 0.002) and depression (β = - 0.05, p < 0.001) at follow-up. However, among females, higher MVPA at baseline was associated with greater symptoms of anxiety (β = 0.03, p < 0.001), but not symptoms of depression (β = 0.01, p = 0.073), at follow-up.

CONCLUSION

In our large sample of Canadian secondary school students, associations between physical activity and symptoms of mental disorder were not bi-directional, and these relationships differed in males and females. This study illustrates the complex nature of the relationship between physical activity and symptoms of mental disorder among youth. While results support the benefits of promoting physical activity among males to prevent or manage internalizing symptoms, the relationship among females warrants further investigation.

Does baseline leisure-time physical activity level predict future depressive symptoms or physical activity among depressive patients? Findings from a Finnish five-year cohort study

OBJECTIVES

The aims of this study were to investigate whether baseline leisure-time physical activity (LTPA) is associated with future recovery from depression among patients with a depression diagnosis and whether baseline LTPA is associated with total physical activity after five years of follow-up.

METHODS

A total of 258 patients aged ≥35 years with clinically confirmed depression at baseline participated. The study was conducted between 2008 and 2016 in municipalities within the Central Finland Hospital District. Depressive symptoms (DS) were determined with the Beck Depression Inventory (BDI) with a cutoff score ≥10, and depression diagnoses were confirmed by the Mini-International Neuropsychiatric Interview (MINI). Blood pressure and anthropometric parameters were measured and blood samples for glucose and lipid determinations were drawn at baseline. LTPA, physical activity, and other social and clinical factors were captured by standard self-administered questionnaires at baseline and the five-year follow-up point.

RESULTS

Of the 258 patients, 76 (29%) had DS at follow-up. Adjusted odds ratio (OR) for future DS was 1.43 (confidence interval [CI] 0.69-2.95) for participants with moderate LTPA and 0.92 (CI 0.42-2.00) for participants with high LTPA, compared with low LTPA at baseline. Higher baseline LTPA levels were associated with higher total physical activity in the future (β=0.14 [95% CI: 0.02-0.26] for linearity = 0.024).

CONCLUSION

Baseline LTPA did not affect the five-year prognosis of depression among depressed patients in a Finnish adult population. Because the baseline LTPA level predicted the future total physical activity, it could be included as a part of the overall health management and treatment of depression in clinical practices.

A prospective study into change of vitamin D levels, depression and frailty among depressed older persons

OBJECTIVES

While vitamin D is involved in frailty as well as depression, hardly any study has examined the course of vitamin D levels prospectively. The objective of this study is to examine whether a change of vitamin D in depressed older adults is associated with either depression course, course of frailty, or both.

METHODS

The study population consisted of 232 of 378 older adults (60-93 years) with a DSM-IV defined depressive disorder participating in the Netherlands Study of Depression in Older persons, a prospective clinical cohort study. Baseline and 2-year follow-up data on depressive disorder (DSM-IV diagnosis), symptom severity (inventory of depressive symptoms), frailty phenotype (and its individual components) and vitamin D levels were obtained. Linear mixed models were used to study the association of change in vitamin D levels with depression course, course of frailty, and the combination.

RESULTS

Vitamin D levels decreased from baseline to follow-up, independent from depression course. An increase in frailty was associated with a significantly sharper decrease of vitamin D levels over time. Post hoc analyses showed that this association with frailty might be driven by an increase of exhaustion over time and counteracted by an increase in walking speed.

CONCLUSIONS

Our findings generate the hypothesis that vitamin D supplementation in late-life depression may improve frailty, which may partly explain inconsistent findings of randomised controlled trials evaluating the effect of vitamin D for depression. We advocate to consider frailty (components) as an outcome in future supplementation trials in late-life depression.

Use of machine learning approach to predict depression in the elderly in China: A longitudinal study

BACKGROUND

Early detection of potential depression among elderly people is conducive for timely preventive intervention and clinical care to improve quality of life. Therefore, depression prediction considering sequential progression patterns in elderly needs to be further explored.

METHODS

We selected 1,538 elderly people from Chinese Longitudinal Healthy Longevity Study (CLHLS) wave 3-7 survey. Long short-term memory (LSTM) and six machine learning (ML) models were used to predict different depression risk factors and the depression risks in the elderly population in the next two years. Receiver operating curve (ROC) and decision curve analysis (DCA) were used to evaluate the prediction accuracy of the reference model and ML models.

RESULTS

The area under the ROC curve (AUC) values of logistic regression with lasso regularisation (AUC=0.629, p-value=0.020) was the highest among ML models. DCA results showed that the net benefit of six ML models was similar (threshold: 0.00-0.10), the net benefit of lasso regression was the largest (threshold: 0.10-0.17 and 0.22-0.25), and the net benefit of DNN was the largest (threshold: 0.17-0.22 and 0.25-0.40). In two ML models, activities of daily living (ADL)/ instrumental ADL (IADL), self-rated health, marital status, arthritis, and number of cohabiting were the most important predictors for elderly with depression.

LIMITATIONS

The retrospective waves used in the LSTM model need to be further increased.

CONCLUSION

The decision support system based on the proposed LSTM+ML model may be very valuable for doctors, nurses and community medical providers for early diagnosis and intervention.