Association of clinical and laboratory variables with in-hospital incidence of deep vein thrombosis in patients after acute ischemic stroke: A retrospective study

Machine learning-based prediction model of lower extremity deep vein thrombosis after stroke

This study aimed to apply machine learning (ML) techniques to develop and validate a risk prediction model for post-stroke lower extremity deep vein thrombosis (DVT) based on patients' limb function, activities of daily living (ADL), clinical laboratory indicators, and DVT preventive measures. We retrospectively analyzed 620 stroke patients. Eight ML models-logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), neural network (NN), extreme gradient boosting (XGBoost), Bayesian (NB), and K-nearest neighbor (KNN)-were used to build the model. These models were extensively evaluated using ROC curves, AUC, PR curves, PRAUC, accuracy, sensitivity, specificity, and clinical decision curves (DCA). Shapley's additive explanation (SHAP) was used to determine feature importance. Finally, based on the optimal ML algorithm, different functional feature set models were compared with the Padua scale to select the best feature set model. Our results indicated that the RF algorithm demonstrated superior performance in various evaluation metrics, including AUC (0.74/0.73), PRAUC (0.58/0.58), accuracy (0.75/0.77), and sensitivity (0.78/0.80) in both the training set and test set. DCA analysis revealed that the RF model had the highest clinical net benefit. SHAP analysis showed that D-dimer had the most significant influence on DVT, followed by age, Brunnstrom stage (lower limb), prothrombin time (PT), and mobility ability. The RF algorithm can predict post-stroke DVT to guide clinical practice.

Research progress in extracorporeal shock wave therapy for upper limb spasticity after stroke

Spasticity is one of the most common complications after stroke. With the gradual intensification of spasticity, stroke patients will have a series of problems such as joint ankylosis and movement restriction, which affect the daily activities and increase the burden on patients' families, medical staff and society. There are many ways to treat post-stroke spasticity before, including physical therapy and exercise therapy, drug therapy, surgery and so on, but not satisfied because of a few shortcomings. In recent years, many researchers have applied extracorporeal shock wave therapy (ESWT) for the treatment of post-stroke spasm and achieved good clinical effect, because it is non-invasive, safe, easy to operate, low cost and other advantages compared with other treatment methods. This article reviews the research progress and existing problems of ESWT in the treatment of post-stroke spasticity.

Functional status and its related factors among stroke survivors in rehabilitation departments of hospitals in Shenzhen, China: a cross-sectional study

Background

Many stroke survivors have multiple chronic diseases and complications coupled with various other factors which may affect their functional status. We aimed to investigate the factors associated with poor functional status in hospitalized patients with stroke in Shenzhen, China.

Methods

In this cross-sectional study, four urban hospitals were selected using convenient sampling, and all stroke patients in these four hospitals were included using cluster sampling. The functional status of stroke survivors was evaluated using Longshi Scale. Explanatory variables (factors affecting functional status comprising age, sex, body mass index, smoking, alcohol consumption, complications, and chronic conditions) were collected. Ordinal logistic regression was used to examine which factors were associated with poor functional status.

Results

Stroke survivors with poor functional status accounted for 72.14% and were categorised as the bedridden group based on Longshi scale, 21.67% of patients with moderate functional limitation were categorised as the domestic group, and 6.19% of the patients with mild functional restriction were categorised as the community group. The highest dependence scores were noted for feeding (73.39%), bowel and bladder management (69.74%) and entertainment (69.53%) among the bedridden group, and housework (74.29%) among the domestic group. In the adjusted model, the odds of poor functional status were higher among stroke patients with older age (odds ratio [OR] = 2.39, 95% CI: 1.55–3.80), female sex (OR = 1.73, 95% CI: 1.08–2.77), duration of stroke more than 12 months (OR = 1.94, 95% CI: 1.28–2.95), with pulmonary infection (OR = 10.91, 95% CI: 5.81–20.50), and with deep venous thrombosis (OR = 3.00, 95% CI: 1.28–7.04).

Conclusions

Older adults (age ≥ 60 years) and women were more likely to exhibit poor functional status post-stroke. Pulmonary infection and deep venous thrombosis were related to an increased risk of being dependent on activities of daily living. Therefore, clinical and rehabilitation interventions aimed at preventing or treating these common complications should be addressed to deal with subsequent dysfunction post-stroke. Since all data were obtained in metropolitan areas where the economy is well developed, future studies should be conducted in rural areas and economically less developed cities.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12883-022-02696-0.