Health-related quality of life, medical resource use and physical function in patients with diabetes mellitus and depression: A cross-sectional analysis from the National Health and Nutrition Examination Survey

Trajectories of depressive symptoms in Korean adults with diabetes: Individual differences and associations with life satisfaction and mortality

OBJECTIVE

We examined trajectories of depressive symptoms and their predictors in adults with diabetes. We assessed whether these trajectories were related to life satisfaction and mortality.

DESIGN

Longitudinal, prospective observational study.

METHODS

We analysed data from 1217 adults with diabetes (aged ≥45 years) in the Korean Longitudinal Study of Aging (2006-2018).

RESULTS

Three trajectories of depressive symptomology were identified in growth mixture models: low/stable (i.e., low and stable levels of symptoms; 85.56%), high/decreasing (i.e., high levels of symptoms with a decreasing trajectory; 7.47%), and moderate/increasing (i.e., moderate levels of symptoms with an increasing trajectory; 6.98%). Participants with poor perceived health status at baseline were more likely to be in the moderate/increasing or high/decreasing classes than in the low/stable class. The moderate/increasing class had the lowest satisfaction with quality of life, followed by the high/decreasing and low/stable classes. The moderate/increasing and the high/decreasing classes had lower satisfaction with relationships with spouse and children than the low/stable class. The high/decreasing class had a higher mortality risk than the low/stable class.

CONCLUSIONS

Long-term monitoring of depressive symptoms in adults with diabetes is warranted given their potential adverse impact on life satisfaction and mortality.

Depression, anxiety, and health-related quality of life in normal weight, overweight and obese individuals with diabetes: a representative study in Germany

OBJECTIVE

Diabetes in the course of lifetime is related to a higher risk for mental disorders. The present study addresses the comparison of individuals with diabetes and non-diabetic individuals in depressive symptoms, generalized anxiety symptoms, and health-related quality of life. Furthermore, mediator effect of BMI and health-related quality of life (HRQOL) on the association between diabetes, depression, and generalized anxiety was analyzed.

METHODS

In this cross-sectional study, the three questionnaires PHQ-9, GAD-7, EQ-5D-5L were measured in a representative sample of the German population (N = 2386). In addition, the presence of diabetes and BMI were assessed via self-report.

RESULTS

There were higher values in depressive and anxiety symptoms as well as lower score in HRQOL in individuals with diabetes compared to non-diabetic individuals. Obese individuals with diabetes showed the highest rates in depressive symptoms and generalized anxiety as well as lowest score in HRQOL. With regard to the mediator analyses, association between diabetes, depressive symptoms, and anxiety symptoms is partially mediated by the BMI and fully mediated by the HRQOL.

CONCLUSIONS

In conclusion, individuals with diabetes have an increased risk in the development of depressive and anxiety symptoms as well as lower health-related quality of life. Future research and strategies in the public health policies among individuals with diabetes should take into account that the association between diabetes, depression, and anxiety is mediated by BMI and HRQOL.

Applying contrastive pre-training for depression and anxiety risk prediction in type 2 diabetes patients based on heterogeneous electronic health records: a primary healthcare case study

OBJECTIVE

Due to heterogeneity and limited medical data in primary healthcare services (PHS), assessing the psychological risk of type 2 diabetes mellitus (T2DM) patients in PHS is difficult. Using unsupervised contrastive pre-training, we proposed a deep learning framework named depression and anxiety prediction (DAP) to predict depression and anxiety in T2DM patients.

MATERIALS AND METHODS

The DAP model consists of two sub-models. Firstly, the pre-trained model of DAP used unlabeled discharge records of 85 085 T2DM patients from the First Affiliated Hospital of Nanjing Medical University for unsupervised contrastive learning on heterogeneous electronic health records (EHRs). Secondly, the fine-tuned model of DAP used case-control cohorts (17 491 patients) selected from 149 596 T2DM patients' EHRs in the Nanjing Health Information Platform (NHIP). The DAP model was validated in 1028 patients from PHS in NHIP. Evaluation included receiver operating characteristic area under the curve (ROC-AUC) and precision-recall area under the curve (PR-AUC), and decision curve analysis (DCA).

RESULTS

The pre-training step allowed the DAP model to converge at a faster rate. The fine-tuned DAP model significantly outperformed the baseline models (logistic regression, extreme gradient boosting, and random forest) with ROC-AUC of 0.91±0.028 and PR-AUC of 0.80±0.067 in 10-fold internal validation, and with ROC-AUC of 0.75 ± 0.045 and PR-AUC of 0.47 ± 0.081 in external validation. The DCA indicate the clinical potential of the DAP model.

CONCLUSION

The DAP model effectively predicted post-discharge depression and anxiety in T2DM patients from PHS, reducing data fragmentation and limitations. This study highlights the DAP model's potential for early detection and intervention in depression and anxiety, improving outcomes for diabetes patients.

Depression prediction based on LassoNet-RNN model: A longitudinal study

Depression has become a widespread health concern today. Understanding the influencing factors can promote human mental health as well as provide a basis for exploring preventive measures. Combining LassoNet with recurrent neural network (RNN), this study constructed a screening model ,LassoNet-RNN, for identifying influencing factors of individual depression. Based on multi-wave surveys of China Health and Retirement Longitudinal Study (CHARLS) dataset (11,661 observations), we analyzed the multivariate time series data and recognized 27 characteristic variables selected from four perspectives: demographics, health-related risk factors, household economic status, and living environment. Additionally, the importance rankings of the characteristic variables were obtained. These results offered insightful recommendations for theoretical developments and practical decision making in public health.