A risk prediction model for post-stroke depression in Chinese stroke survivors based on clinical and socio-psychological features

Investigating the reporting of participant characteristics relating to health equity in randomised controlled trials of non-pharmacological interventions for post-stroke anxiety and/or depression: a scoping review

PURPOSE

The review aims to identify what characteristics are reported in randomised controlled trials for the non-pharmacological management of post-stroke anxiety and/or depression and whether research has explored the correlation between participant characteristics and their outcomes.

METHODS

A comprehensive systematic search was completed of five databases: CINAHL, Medline, PsychInfo, Web of Science, and The World Health Organisation. Google Scholar was also accessed. The reporting of participant characteristics was assessed by adapting the PROGRESS-Plus framework, a research framework of protected characteristics known to impact health equity (such as, age).

RESULTS

19 papers (n = 2187) were included. There was generally poor reporting of characteristics associated with an increased likelihood of post-stroke anxiety and/or depression. All studies reported the gender/sex of participants, 18 studies reported the age of participants, and 11 studies reported lesion location. None of the studies reported the sexual orientation or pre-existing disabilities of participants.

CONCLUSION

There was variation in the reporting and analyses of protected characteristics. Future research should follow a health equity framework to ensure reporting of protected characteristics to support clinicians in identifying whether the proposed interventions are relevant to their stroke population and consider undergoing subgroup analyses to compare outcomes across protected characteristics.

Prognosis prediction models for post-stroke depression: a protocol for systematic review, meta-analysis, and critical appraisal

INTRODUCTION

Post-stroke depression (PSD) is a prevalent complication that has been shown to have a negative impact on rehabilitation outcomes and quality of life and poses a significant risk for suicidal intention. However, models for discriminating and predicting PSD in stroke survivors for effective secondary prevention strategies are inadequate as the pathogenesis of PSD remains unknown. Prognostic prediction models that exhibit greater rule-in capacity have the potential to mitigate the issue of underdiagnosis and undertreatment of PSD. Thus, the planned study aims to systematically review and critically evaluate published studies on prognostic prediction models for PSD.

METHODS AND ANALYSIS

A systematic literature search will be conducted in PubMed and Embase through Ovid. Two reviewers will complete study screening, data extraction, and quality assessment utilizing appropriate tools. Qualitative data on the characteristics of the included studies, methodological quality, and the appraisal of the clinical applicability of models will be summarized in the form of narrative comments and tables or figures. The predictive performance of the same model involving multiple studies will be synthesized with a random effects meta-analysis model or meta-regression, taking into account heterogeneity.

ETHICS AND DISSEMINATION

Ethical approval is considered not applicable for this systematic review. Findings will be shared through dissemination at academic conferences and/or publication in peer-reviewed academic journals.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42023388548.

Social Support and Depression among Stroke Patients: A Topical Review

Research has shown a protective association between social support and depression, depression among stroke patients, and health impacts of depression. Despite this, not much is known about the effect of social support on depression among stroke patients. This review aims to summarize the current research examining the association between social support and depression among stroke patients. A literature search was performed in PubMed to find original peer-reviewed journal articles from 2016 to 12 March 2023 that examined the association between social support and depression among stroke patients. The search terms were depression and "social support" and stroke, which lead to 172 articles. After abstract review, seven observational studies that studied the target association among stroke patients were selected. One additional study was found using PsycINFO as a complementary source with the same search strategy and criteria. Overall, a negative association was found between social support and depression among stroke patients in eight studies, with more social support leading to lower rates of depression post-stroke. The other study did not find a statistically significant association. Overall, the results of recent studies suggest that social support is negatively associated with depression among stroke patients. In most studies, this association was statistically significant. The findings suggest the importance of improving social support perceived by stroke patients in the prevention of depression after the occurrence of stroke.

A machine learning approach for predicting suicidal ideation in post stroke patients

Currently, the identification of stroke patients with an increased suicide risk is mainly based on self‐report questionnaires, and this method suffers from a lack of objectivity. This study developed and validated a suicide ideation (SI) prediction model using clinical data and identified SI predictors. Significant variables were selected through traditional statistical analysis based on retrospective data of 385 stroke patients; the data were collected from October 2012 to March 2014. The data were then applied to three boosting models (Xgboost, CatBoost, and LGBM) to identify the comparative and best performing models. Demographic variables that showed significant differences between the two groups were age, onset, type, socioeconomic, and education level. Additionally, functional variables also showed a significant difference with regard to ADL and emotion (p < 0.05). The CatBoost model (0.900) showed higher performance than the other two models; and depression, anxiety, self-efficacy, and rehabilitation motivation were found to have high importance. Negative emotions such as depression and anxiety showed a positive relationship with SI and rehabilitation motivation and self-efficacy displayed an inverse relationship with SI. Machine learning-based SI models could augment SI prevention by helping rehabilitation and medical professionals identify high-risk stroke patients in need of SI prevention intervention.

Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods

BACKGROUND

Identifying patients at a high risk of psychosis relapse is crucial for early interventions. A relevant psychiatric clinical context is often recorded in clinical notes; however, the utilization of unstructured data remains limited. This study aimed to develop psychosis-relapse prediction models using various types of clinical notes and structured data.

METHODS

Clinical data were extracted from the electronic health records of the Ajou University Medical Center in South Korea. The study population included patients with psychotic disorders, and outcome was psychosis relapse within 1 year. Using only structured data, we developed an initial prediction model, then three natural language processing (NLP)-enriched models using three types of clinical notes (psychological tests, admission notes, and initial nursing assessment) and one complete model. Latent Dirichlet Allocation was used to cluster the clinical context into similar topics. All models applied the least absolute shrinkage and selection operator logistic regression algorithm. We also performed an external validation using another hospital database.

RESULTS

A total of 330 patients were included, and 62 (18.8%) experienced psychosis relapse. Six predictors were used in the initial model and 10 additional topics from Latent Dirichlet Allocation processing were added in the enriched models. The model derived from all notes showed the highest value of the area under the receiver operating characteristic (AUROC = 0.946) in the internal validation, followed by models based on the psychological test notes, admission notes, initial nursing assessments, and structured data only (0.902, 0.855, 0.798, and 0.784, respectively). The external validation was performed using only the initial nursing assessment note, and the AUROC was 0.616.

CONCLUSIONS

We developed prediction models for psychosis relapse using the NLP-enrichment method. Models using clinical notes were more effective than models using only structured data, suggesting the importance of unstructured data in psychosis prediction.

Pre-Stroke Depression in Ghana and Nigeria: Prevalence, Predictors and Association With Poststroke Depression

OBJECTIVES

Depression is a risk factor for stroke. There is a knowledge gap on the predictors of prestroke depression in stroke survivors living in low- and middle-income countries (LMICs). We estimated prevalence and predictors of prestroke depression, as well as its association with poststroke depression (PSD) in the largest study of stroke in Africa.

METHODS

We evaluated information collected as part of the Stroke Investigative Research and Education Network (SIREN) study, a multicentre, case-control study conducted at 15 sites in Ghana and Nigeria. Prestroke depression status was ascertained in stroke survivors using a validated self-report tool, while PSD was assessed using a stroke specific screening tool for depression ("HRQOLISP-E"). Independent associations were investigated using complementary log-log regression and binary logit models.

RESULTS

Among 1,977 participants, prestroke depression was found in 141 (7.1%). In multivariate analyses, prestroke depression was significantly associated with tachycardia (OR = 2.22, 95% CI = 1.37-3.56) and low consumption of green leafy vegetables (OR = 1.91, 95% CI = 1.12-3.24). Forty-one (29.1%) of the prestroke depression sub-sample developed PSD. However, prestroke depression was not significantly associated with PSD.

CONCLUSION

The findings should energize before-the-stroke identification and prioritization of limited treatment resources in LMICs to persons with depression who have multiple, additional, risks of stroke.

Role of social support in poststroke depression: A meta-analysis

Poststroke depression significantly affects health and quality of life of stroke patients. This study evaluates the role of social support in influencing poststroke depression. The literature search was conducted in electronic databases and study selection was based on precise eligibility criteria. The prevalence rates reported by individual studies were pooled. A meta-analysis of standardized mean differences (SMD) in social support between depressed and non-depressed stroke patients was performed. The odds ratios and correlation coefficients showing the relationship between social support and depression were pooled to achieve overall estimates. Twenty-five studies (9431 patients) were included. The prevalence of depression was 36% [95% confidence interval (CI): 28, 45]. Patients with poststroke depression had significantly lower social support in comparison with patients with no or lower levels of depression [SMD in social support scores -0.338 (95% CI: -0.589, -0.087); p = 0.008]. The odds of depression were lower in patients receiving higher levels of social support [OR 0.82 (95% CI: 0.69, 0.95)] but were higher in patients who were receiving weaker social support [OR 5.22 (95% CI: -0.87, 11.31)]. A meta-analysis of correlation coefficients found a significantly inverse correlation between social support and poststroke depression [r -0.336 (95% CI: -0.414, -0.254)]. Poststroke depression has a significant independent inverse association with social support.

Family Functioning Mediates the Relationship Between Activities of Daily Living and Poststroke Depression

BACKGROUND

Poststroke depression is common and includes depressive and somatic symptoms. However, few studies have confirmed the influence of family functioning on poststroke depression or explored the association among daily activities, family functioning, and poststroke depression.

OBJECTIVES

We examined the independent risk factors of daily activities and family functioning for poststroke depression and identified the mediating effect of family functioning on the association between daily activities and poststroke depression.

METHODS

This cross-sectional study design used convenience sampling to recruit 422 stroke survivors from the neurology department of a hospital in Harbin, China, from February to July 2018. We assessed participants' demographic and clinical variables, including depression, daily activities, and family functioning. Pearson's correlations and multiple linear regression analyses were conducted, and a path analysis with bootstrapping was utilized to define direct/indirect effects.

RESULTS

Daily activities and family functioning had a significant and direct negative effect on participants' depression. The indirect effect of 1,000 bootstrap samples after bias correction with a 95% confidence interval was below zero, indicating that family function had a significant mediating effect on the association between depression and daily activities.

DISCUSSION

This study revealed the importance of family functioning in the association between depression and daily activities in stroke survivors. To the best of our knowledge, this study was the first to explore the mediating role of family functioning in poststroke depression, emphasizing the importance of family for the mental health of stroke patients. To reduce the incidence of poststroke depression, interventions that enhance daily activities and family functioning may include nurses, family therapists, rehabilitation physicians, and community workers.

Prediction of Major Depressive Disorder Following Beta-Blocker Therapy in Patients with Cardiovascular Diseases

Incident depression has been reported to be associated with poor prognosis in patients with cardiovascular disease (CVD), which might be associated with beta-blocker therapy. Because early detection and intervention can alleviate the severity of depression, we aimed to develop a machine learning (ML) model predicting the onset of major depressive disorder (MDD). A model based on L1 regularized logistic regression was trained against the South Korean nationwide administrative claims database to identify risk factors for the incident MDD after beta-blocker therapy in patients with CVD. We identified 50,397 patients initiating beta-blockers for CVD, with 774 patients developing MDD within 365 days after initiating beta-blocker therapy. An area under the receiver operating characteristic curve (AUC) of 0.74 was achieved. A history of non-selective beta-blockers and factors related to anxiety disorder, sleeping problems, and other chronic diseases were the most strong predictors. AUCs of 0.62–0.71 were achieved in the external validation conducted on six independent electronic health records and claims databases in the USA and South Korea. In conclusion, an ML model that identifies patients at high-risk for incident MDD was developed. Application of ML to identify susceptible patients for adverse events of treatment may serve as an important approach for personalized medicine.

Mild to Severe Depressive Symptoms in Elderly Stroke Survivors and Its Associated Factors: Evidence From a Cross-Sectional Study in Zhejiang Province, China

Objective: The objective of the study is to explore the prevalence of mild to severe depressive symptoms in elderly stroke survivors and its associated factors. Methods: We did data analyses of 335 elders with stroke history. Data were collected in a survey conducted between 2014 and 2015, among permanent residents aged 60 and older in Zhejiang Province, China. Prevalence of mild to severe depressive symptoms among stroke survivors were calculated, and univariate analyses and multilevel logistic regression were used to explore its associated factors. Results: Prevalence of mild to severe depressive symptoms was 22.09% (95% CI: 17.65-26.53%) in elders with stroke history, more than twice compared to their counterparts not suffering stroke (9.77%, P < 0.001). In multilevel logistic regression, we found that elderly stroke survivors who were illiterate (OR = 2.33, p = 0.008), or had limitation in activities of daily living (OR = 3.04, p = 0.001) were more likely to be present with mild to severe depressive symptoms, respectively, while those with more fresh vegetable consumption were at lower odds (OR = 0.82, p = 0.047). Conclusions: Prevalence of mild to severe depressive symptoms was high in elderly stroke survivors. Targeted screening might be needed for those being illiterate, disabled in activities of daily living, and having little consumption of fresh vegetable. The association between fresh vegetable consumption and depressive symptom in stroke patients calls for further research.

Use of Patient-Reported Data to Match Depression Screening Intervals With Depression Risk Profiles in Primary Care Patients With Diabetes: Development and Validation of Prediction Models for Major Depression

Background

Clinical guidelines recommend screening for depression in the general adult population but recognizes that the optimum interval for screening is unknown. Ideal screening intervals should match the patient risk profiles.

Objective

This study describes a predictive analytics approach for mining clinical and patient-reported data from a large clinical study for the identification of primary care patients at high risk for depression to match depression screening intervals with patient risk profiles.

Methods

This paper analyzed data from a large safety-net primary care study for diabetes and depression. A regression-based data mining technique was used to examine 53 demographics, clinical variables, and patient-reported variables to develop three prediction models for major depression at 6, 12, and 18 months from baseline. Predictors with the strongest predictive power that require low information collection efforts were selected to develop the prediction models. Predictive accuracy was measured by the area under the receiver operating curve (AUROC) and was evaluated by 10-fold cross-validation. The effectiveness of the prediction algorithms in supporting clinical decision making for six “typical” types of patients was demonstrated.

Results

The analysis included 923 patients who were nondepressed at the study baseline. Five patient-reported variables were selected in the prediction models to predict major depression at 6, 12, and 18 months: (1) Patient Health Questionnaire 2-item score; (2) the Sheehan Disability Scale; (3) previous problems with depression; (4) the diabetes symptoms scale; and (5) emotional burden of diabetes. All three depression prediction models had an AUROC>0.80, comparable with published depression prediction studies. Among the 6 “typical” types of patients, the algorithms suggest that patients who reported impaired daily functioning by health status are at an elevated risk for depression in all three periods.

Conclusions

This study demonstrated that leveraging patient-reported data and prediction models can help improve identification of high-risk patients and clinical decisions about the depression screening interval for diabetes patients. Implementation of this approach can be coupled with application of modern technologies such as telehealth and mobile health assessment for collecting patient-reported data to improve privacy, reducing stigma and costs, and promoting a personalized depression screening that matches screening intervals with patient risk profiles.

Prevalence of pre-stroke depression and its association with post-stroke depression: a systematic review and meta-analysis

BACKGROUND

Depression is a common post-stroke complication. Pre-stroke depression may be an important contributor, however the epidemiology of pre-stroke depression is poorly understood. Using systematic review and meta-analysis, we described the prevalence of pre-stroke depression and its association with post-stroke depression.

METHODS

We searched multiple cross-disciplinary databases from inception to July 2017 and extracted data on the prevalence of pre-stroke depression and its association with post-stroke depression. We assessed the risk of bias (RoB) using validated tools. We described summary estimates of prevalence and summary odds ratio (OR) for association with post-stroke depression, using random-effects models. We performed subgroup analysis describing the effect of depression assessment method. We used a funnel plot to describe potential publication bias. The strength of evidence presented in this review was summarised via 'GRADE'.

RESULTS

Of 11 884 studies identified, 29 were included (total participants n = 164 993). Pre-stroke depression pooled prevalence was 11.6% [95% confidence interval (CI) 9.2-14.7]; range: 0.4-24% (I2 95.8). Prevalence of pre-stroke depression varied by assessment method (p = 0.02) with clinical interview suggesting greater pre-stroke depression prevalence (~17%) than case-note review (9%) or self-report (11%). Pre-stroke depression was associated with increased odds of post-stroke depression; summary OR 3.0 (95% CI 2.3-4.0). All studies were judged to be at RoB: 59% of included studies had an uncertain RoB in stroke assessment; 83% had high or uncertain RoB for pre-stroke depression assessment. Funnel plot indicated no risk of publication bias. The strength of evidence based on GRADE was 'very low'.

CONCLUSIONS

One in six stroke patients have had pre-stroke depression. Reported rates may be routinely underestimated due to limitations around assessment. Pre-stroke depression significantly increases odds of post-stroke depression.Protocol identifierPROSPERO identifier: CRD42017065544.

Efficacy of escitalopram oxalate for patients with post-stroke depression

This retrospective study investigated the efficacy and safety of escitalopram oxalate (ESO) for the treatment of post-stroke depression (PSD).A total of 115 patients with PSD were included in this study. A total of 65 patients underwent ESO (Intervention group). A total of 50 patients received acupressure (Control group). The outcome measurements included Montgomery-Åsberg Depression Rating Scale (MADRS), Hamilton Anxiety Rating Scale (HAM-A), and Sheehan Disability Scale (SDS). In addition, we also recorded the adverse events in this study.At the end of 8-week treatment, ESO showed greater efficacy in depression, measured by MADRS (P < .01); anxiety, measured by HAM-A scale (P < .01); and disability, measured by SDS (P < .01), compared to acupressure. Additionally, there were not significant differences regarding adverse events between two groups (P > .05).The present results indicate that ESO can decrease symptoms of patients with PSD.

Predictors of early-onset post-ischemic stroke depression: a cross-sectional study

BACKGROUND

Post-stroke depression (PSD) seriously affects the rehabilitation of nerve function and quality of life. However, the pathogenesis of PSD is still not clear. This study aimed to investigate the demographic, clinical, and biochemical factors in patients with PSD.

METHODS

Patients with an acute ischemic stroke, who met the inclusion criteria at Shanghai Tenth People's Hospital from April 2016 to September 2016, were recruited for this study. The stroke severity was assessed using the National Institutes of Health Stroke Scale (NIHSS), and the mental state was assessed using Mini-Mental State Examination (MMSE), Hamilton Depression Scale (HAMD), and Hamilton Anxiety Scale (HAMA) at 1 week of admission. The patients were divided into PSD and non-PSD groups. The demographic and clinical characteristics, as well as the biochemical factors, were compared between the two groups. A logistic regression analysis was performed to identify the risk factors for depression following stroke.

RESULTS

A total of 83 patients with acute ischemic stroke were recruited. Of these, 36 (43.4%) developed depression. The multivariate logistic regression analysis indicated that high NIHSS [odds ratio (OR): 1.84, 95% confidence interval (CI): 1.09-3.12, P = 0.023] and high HAMD scores (OR: 2.38, 95% CI: 1.61-3.50, P < 0.001) were independent risk predictors for PSD and so were lower dopamine level (OR: 0.64, 95% CI: 0.45-0.91, P = 0.014), lower 5-hydroxytryptamine level (OR: 0.99, 95% CI: 0.98-1.00, P = 0.046), higher tumor necrosis factor-α level (OR: 1.05, 95% CI: 1.00-1.09, P = 0.044), and lower nerve growth factor level (OR: 0.06, 95% CI: 0.01-0.67, P = 0.022).

CONCLUSIONS

The identification of higher NIHSS scores, higher HAMD scores, lower dopamine level, lower 5-hydroxytryptamine level, higher tumor necrosis factor-α level, and lower nerve growth factor level might be useful for clinicians in recognizing and treating depression in patients after a stroke.