Prediction of depressive symptoms onset and long-term trajectories in home-based older adults using machine learning techniques

Lin, Shaowu; Wu, Yafei; He, Lingxiao; Fang, Ya

doi:10.1080/13607863.2022.2031868

Cited by 14 publications

(9 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding is consistent with previous studies conducted in military samples, where a resilient group (55.9% – 86.5%) was observed comprising most of the participants [12]–[14]. Furthermore, this large resilient group was also identified in recent studies investigating depression trajectories in students, older adults, and adolescents[7]–[9]. The intermediate-stable trajectory (20%) exhibited an increase in depressive symptoms after deployment and slightly elevated levels of depressive symptoms compared to the resilient trajectory.…”

Section: Discussionsupporting

confidence: 91%

“…While the occurrence of depression in the military has been studied extensively, little attention has been paid to the long-term development (trajectories) of depression after deployment. Studies investigating trajectories of depressive symptoms mainly focused on civilian rather than military samples [7]–[10]. Musliner and colleagues [11] conducted a systematic review on the heterogeneity in long-term development of depressive symptoms and found that most of these studies identified three or four different symptom trajectories and sampled the general population.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Long-term Trajectories of Depressive Symptoms in Deployed Military Personnel: A 10-year prospective study

Plas,

Bruinsma,

van Lissa

et al. 2023

Preprint

View full text Add to dashboard Cite

Background. Military missions are associated with an increased risk of depression. Understanding the long-term development of depressive symptoms after deployment is important to improve decision-making regarding deployment and mental health policies in the military. Therefore, this study aims to investigate trajectories of depressive symptoms from pre- to post-deployment and assess the role of specific factors, such as demographics, early life trauma, posttraumatic stress disorder (PTSD) symptoms and deployment stressors, in the Dutch army. Methods. The study includes a cohort of 1032 military men and women deployed to Afghanistan between 2005 and 2008. From pre- to 10 years post-deployment (across 6 distinct time points), depressive and PTSD symptoms were assessed using the Symptom CheckList-90 (SCL-90) and the Self-Rating Inventory for PTSD (SRIP) respectively. Demographics, early trauma, and deployment experiences were collected at baseline and after deployment, respectively. Latent Class Growth Analysis was used to explore heterogeneity in developmental trajectories of depressive symptoms over time. Results. The study identified four trajectories for depressive symptoms: resilient (65%), intermediate-stable (20%), symptomatic-chronic (9%), and late-onset-increasing (6%). The late-onset-increasing group had the highest proportion of individuals younger than 21 years. In addition, the resilient group was less likely to have experienced deployment stressors and the symptomatic-chronic group reported more early life traumas compared to the other groups. For individuals classified in trajectories with higher levels of depressive symptoms, PTSD symptoms were higher at all time points. Conclusions. Multiple trajectories for depressive symptoms were identified in a military sample up to 10 years after deployment. These trajectories were associated with age, early trauma, deployment stressors and PTSD symptoms. The majority of the sample fell within the resilient trajectory, supporting the notion that deployed military personnel possess a high level of resilience. Overall, these findings provide valuable insights and a foundation for further research in this area.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Long-term Trajectories of Depressive Symptoms in Deployed Military Personnel: A 10-year prospective study

Plas,

Bruinsma,

van Lissa

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on the longitudinal data of the seven-year follow-up study, we revealed four trajectories of depressive symptoms in older Chinese populations; including low and stable, increasing, decreasing, and high and stable, accounting for 63.69%, 16.70%, 12.31%, and 7.30%, respectively. These heterogeneous patterns were consistent with the findings of Xiang [ 24 ], Lin et al [ 25 ] and Kuchibhatla et al [ 26 ], in which four similar trajectories were identified in the older population, with a majority of participants in the low and stable group and less than 10% in the high and stable groups. It is worth noting that in the study by Kuchibhatla et al, the trajectories of both increasing and decreasing groups were below the threshold of positive depressive symptoms, while in the present study, participants in the increasing group had relatively higher initial CES-D-10 scores, which were close to the threshold of depressive symptoms.…”

Section: Discussionsupporting

confidence: 91%

Trajectories of depressive symptoms and their predictors in Chinese older population: Growth Mixture model

Xie¹,

Wang

2023

BMC Geriatr

View full text Add to dashboard Cite

Background Given the rapidly rising proportion of the older population in China and the relatively high prevalence of depressive symptoms among this population, this study aimed to identify the trajectories of depressive symptoms and the factors associated with the trajectory class to gain a better understanding of the long-term course of depressive symptoms in this population. Methods Data were obtained from four wave’s survey of the China Health and Retirement Longitudinal Study (CHARLS). A total of 3646 participants who aged 60 years or older during baseline survey, and completed all follow-ups were retained in this study. Depressive symptoms were measured using the 10-item version of the Center for Epidemiologic Studies Depression Scale (CES-D-10). Growth mixture modelling (GMM) was adopted to identify the trajectory classes of depressive symptoms, and both linear and quadratic functions were considered. A multivariate logistic regression model was used to calculate the adjusted odds ratios (ORs) of the associated factors to predict the trajectory class of participants. Results A four-class quadratic function model was the best-fitting model for the trajectories of depressive symptoms in the older Chinese population. The four trajectories were labelled as increasing (16.70%), decreasing (12.31%), high and stable (7.30%), and low and stable (63.69%), according to their trends. Except for the low and stable trajectory, the other trajectories were almost above the threshold for depressive symptoms. The multivariate logistic regression model suggested that the trajectories of chronic depressive symptoms could be predicted by being female, living in a village (rural area), having a lower educational level, and having chronic diseases. Conclusions This study identified four depressive symptom trajectories in the older Chinese population and analysed the factors associated with the trajectory class. These findings can provide references for prevention and intervention to reduce the chronic course of depressive symptoms in the older Chinese population.

show abstract

“…Another large-scale ML-based study found that sleep duration is one of the top five predictors of DSS among home-based older adults. 54 Our findings support this hypothesis, although they do not claim to show any causality between sleep and DSS. The cross-sectional nature of our study precludes the assessment of the long-term causal pathways in the general population.…”

Section: Discussionsupporting

confidence: 64%

Prediction of depressive symptoms severity based on sleep quality, anxiety, and brain: a machine learning approach across three cohorts

Olfati

Samea²,

Faghihroohi

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Depressive symptoms are rising in the general population and can lead to depression years later, but the contributing factors are less known. Although the link between sleep disturbances and depressive symptoms has been reported, the predictive role of sleep on depressive symptoms severity (DSS) and the impact of anxiety and brain structure on their interrelationship at the individual subject level remain poorly understood. Methods: Here, we used 1813 participants from three population-based datasets. We applied ensemble machine learning models to assess the predictive role of sleep, anxiety, and brain structure on DSS in the primary dataset (n = 1101), then we tested the generalizability of our findings in two independent datasets. In addition, we performed a mediation analysis to identify the effect of anxiety and brain structure on the link between sleep and DSS. Results: We observed that sleep quality could predict DSS (r = 0.43, rMSE = 2.73, R2 = 0.18), and adding anxiety strengthened its prediction (r = 0.67, rMSE = 2.25, R2 = 0.45). However, brain structure (alone or along with sleep/anxiety) did not predict DSS. Importantly, out-of-cohort validations of our findings in other samples provided similar findings. Further, anxiety scores (not brain structure) could mediate the link between sleep quality and DSS. Conclusion: Taken together, poor sleep quality and anxiety symptoms could predict DSS across three cohorts. We hope that our findings incentivize clinicians to consider the importance of screening and treating subjects with sleep and anxiety problems to reduce the burden of depressive symptoms.

show abstract

Prediction of depressive symptoms onset and long-term trajectories in home-based older adults using machine learning techniques

Cited by 14 publications

References 63 publications

Long-term Trajectories of Depressive Symptoms in Deployed Military Personnel: A 10-year prospective study

Long-term Trajectories of Depressive Symptoms in Deployed Military Personnel: A 10-year prospective study

Trajectories of depressive symptoms and their predictors in Chinese older population: Growth Mixture model

Prediction of depressive symptoms severity based on sleep quality, anxiety, and brain: a machine learning approach across three cohorts

Contact Info

Product

Resources

About