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

Abstract

BackgroundPost-stroke depression (PSD) is a frequent complication that worsens rehabilitation outcomes and patient quality of life. This study developed a risk prediction model for PSD based on patient clinical and socio-psychology features for the early detection of high risk PSD patients.ResultsRisk predictors included a history of brain cerebral infarction (odds ratio [OR], 3.84; 95% confidence interval [CI], 2.22-6.70; P < 0.0001) and four socio-psychological factors including Eysenck Personality Questionnaire with Neuroticism/Stability (OR, 1.18; 95% CI, 1.12-1.20; P < 0.0001), life event scale (OR, 0.99; 95% CI, 0.98-0.99; P = 0.0007), 20 items Toronto Alexithymia Scale (OR, 1.06; 95% CI, 1.02-1.10; P = 0.002) and Social Support Rating Scale (OR, 0.91; 95% CI, 0.87-0.90; P < 0.001) in the logistic model. In addition, 11 rules were generated in the tree model. The areas under the curve of the ROC and the accuracy for the tree model were 0.85 and 0.86, respectively.MethodsThis study recruited 562 stroke patients in China who were assessed for demographic data, medical history, vascular risk factors, functional status post-stroke, and socio-psychological factors. Multivariate backward logistic regression was used to extract risk factors for depression in 1-month after stroke. We converted the logistic model to a visible tree model using the decision tree method. Receiver operating characteristic (ROC) was used to evaluate the performance of the model.ConclusionThis study provided an effective risk model for PSD and indicated that the socio-psychological factors were important risk factors of PSD.

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

“…After excluding duplicates, our combined searches identified a total of 11884 studies. A total of 29 studies (Aben et al, 2006;;Bara et al, (2016); Caeiro et al, 2006;Castellanos-Pinedo et al, 2011;De Ryck et al, 2013;Dou et al, 2015;Gillen et al, 2001;Hackett et al, 2006;Jorgensen et al, 2016;Kim et al, 2014;Kocer et al, 2011;Kootker et al, 2016;Liu et al, 2017;McCarthy et al, 2016;Ng et al, 1995;Paolucci et al, 2006;Pohjasvarra et al, 1998;Prisnie et al, 2016;Schottke et al, 2015;Sienkiewicz-Jarosz et al, 2010;Singh et al, 2000;Slater et al, 2012;Tang et al, 2005;Tang et al, 2011;Tse et al, 2017;Verdelho et al, 2004;Vermeer et al, 2017;White et al, 2014;Zhang et al, 2010 ) met our inclusion criteria (164993 patients; see Table 1). We requested additional data from seven authors and received data from one (Acknowledgements).…”

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

“…However, it is hard to identify the consistent risk factors from the literature. Large studies have paid much attention to the vascular factors [ 3 , 4 ] and socioeconomic risk factors [ 5 ], but minimal attention has been paid to the biological factors. Intracerebral neurotransmitters have been directly related to PSD, especially monoamine neurotransmitters including noradrenaline (NE), 5-hydroxytryptamine (5-HT), and dopamine (DA), which are important neurotransmitters closely related to human mental activity, especially emotional activity [ 6 ].…”

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

“…This study adds to the growing body of research that utilizes predictive analytics to improve the forecasting of depression [19,22-25,28]. A strength of this study is that the derived prediction models use a relatively small number of predictors (ie, 5 compared with 10-20 in most prior studies) while still achieving comparable predictive accuracy as measured by the AUROC.…”

“…A few studies have explored the development of depression risk predictive tools [22-25]. King et al [22] used a stepwise logistic regression method to develop a risk prediction model for major depression at 6 and 12 months by using a dataset from general practice attendees.…”

“…In addition, using the logistic regression method, Wang et al [24] developed a risk prediction model of major depression in 2-3 years for the general adult population. Finally, Liu et al [25] developed a decision tree model for predicting poststroke depression in stroke survivors. The predictive accuracy, as measured by the area under the receiver operating curve (AUROC) of those studies, was approximately 0.8.…”