Impact of 25-Hydroxyvitamin D on the Prognosis of Acute Ischemic Stroke: Machine Learning Approach

Diet and Nutraceuticals for treatment and prevention of primary and secondary stroke: Emphasis on nutritional antiplatelet and antithrombotic agents

Ischemic stroke is a devastating disease that causes morbidity and mortality. Malnutrition following ischemic stroke is common in stroke patients. During the rehabilitation, the death rates of stroke patients are significantly increased due to malnutrition. Nutritional supplements such as protein, vitamins, fish, fish oils, moderate wine or alcohol consumption, nuts, minerals, herbal products, food colorants, marine products, fiber, probiotics and Mediterranean diets have improved neurological functions in stroke patients as well as their quality of life. Platelets and their mediators contribute to the development of clots leading to stroke. Ischemic stroke patients are treated with thrombolytics, antiplatelets, and antithrombotic agents. Several systematic reviews, meta-analyses, and clinical trials recommended that consumption of these nutrients and diets mitigated the vascular, peripheral, and central complications associated with ischemic stroke (Fig. 2). Particularly, these nutraceuticals mitigated the platelet adhesion, activation, and aggregation that intended to reduce the risks of primary and secondary stroke. Although these nutraceuticals mitigate platelet dysfunction, there is a greater risk of bleeding if consumed excessively. Moreover, malnutrition must be evaluated and adequate amounts of nutrients must be provided to stroke patients during intensive care units and rehabilitation periods. In this review, we have summarized the importance of diet and nutraceuticals in ameliorating neurological complications and platelet dysfunction with an emphasis on primary and secondary prevention of ischemic stroke.

A systematic review and meta-analysis of the linkage between low vitamin D and the risk as well as the prognosis of stroke

OBJECTIVE

The research intended to probe the connection between the risk of stroke and serum vitamin D levels.

METHODS

Three electronic databases (Cochrane Library, EMBASE, PubMed) were searched according to the subject terms from inception until July 29, 2022, and retrieved researches were screened on the basis of inclusion and exclusion criteria. Two investigators conducted the quality assessment and data extraction. Using Stata 16.0 software, a meta-analysis was conducted on the extracted data.

FINDINGS

In total, 27 studies with 45,302 participants were included. Among these studies, 20 focused on stroke risk, while 7 examined stroke prognosis. According to the meta-analysis findings, it was observed that a higher stroke risk is connected to reduced levels of serum vitamin D. This association was reflected in a combined relative risk (RR) of 1 .28 (95% confidence interval (CI): 1.15-1.42) and a worse prognosis after stroke (RR = 2.95, 95% CI: 1.90-4.60). Additional analysis indicated that no apparent relationship between a decrease in vitamin D and the probability of experiencing a hemorrhagic stroke was found. The RR found was 1.93 (95% CI: 0.95-3.95). On the other hand, it was observed that a reduction in serum vitamin D levels was linked to an elevated likelihood of developing an ischemic stroke. The RR identified was 1.72 (95% CI: 1.78-2.03). Moreover, a lower level of vitamin D in the bloodstream was associated with a more unfavorable prognosis for individuals who suffered from a stroke. The RR for this correlation was 2.95 (95% CI: 1.90-4.60). However, further research is required to confirm the above-mentioned findings.

CONCLUSION

In conclusion, lower concentration vitamin D was found to be related to an increased risk of stroke, which could mainly be reflected in ischemic stroke patients but not in patients with hemorrhagic stroke. A lower serum vitamin D level was correlative with the poor prognosis of stroke.

Vitamin D and ischemic stroke - Association, mechanisms, and therapeutics

Confronting the rising tide of ischemic stroke and its associated mortality and morbidity with ageing, prevention and acute management of ischemic stroke is of paramount importance. Mounting observational studies have established a non-linear association of vitamin D status with cardiovascular diseases, including ischemic stroke. Paradoxically, current clinical trials fail to demonstrate the cardiovascular benefits of vitamin D supplementation. We aim to update recent clinical and experimental findings on the role of vitamin D in the disease course of ischemic stroke, from its onset, progression, recovery, to recurrence, and the established and alternative possible pathophysiological mechanisms. This review justifies the necessities to address stroke etiological subtypes and focus on vitamin D-deficient subjects for investigating the potential of vitamin D supplementation as a preventive and therapeutic approach for ischemic stroke. Well-powered clinical trials are warranted to determine the efficacy, safety, timing, target individuals, optimal dosages, and target 25OHD concentrations of vitamin D supplementation in the prevention and treatment of ischemic stroke.

Machine learning prediction of motor function in chronic stroke patients: a systematic review and meta-analysis

Background

Recent studies have reported that machine learning (ML), with a relatively strong capacity for processing non-linear data and adaptive ability, could improve the accuracy and efficiency of prediction. The article summarizes the published studies on ML models that predict motor function 3-6 months post-stroke.

Methods

A systematic literature search was conducted in PubMed, Embase, Cochorane and Web of Science as of April 3, 2023 for studies on ML prediction of motor function in stroke patients. The quality of the literature was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). A random-effects model was preferred for meta-analysis using R4.2.0 because of the different variables and parameters.

Results

A total of 44 studies were included in this meta-analysis, involving 72,368 patients and 136 models. Models were categorized into subgroups according to the predicted outcome Modified Rankin Scale cut-off value and whether they were constructed based on radiomics. C-statistics, sensitivity, and specificity were calculated. The random-effects model showed that the C-statistics of all models were 0.81 (95% CI: 0.79; 0.83) in the training set and 0.82 (95% CI: 0.80; 0.85) in the validation set. According to different Modified Rankin Scale cut-off values, C-statistics of ML models predicting Modified Rankin Scale>2(used most widely) in stroke patients were 0.81 (95% CI: 0.78; 0.84) in the training set, and 0.84 (95% CI: 0.81; 0.87) in the validation set. C-statistics of radiomics-based ML models in the training set and validation set were 0.81 (95% CI: 0.78; 0.84) and 0.87 (95% CI: 0.83; 0.90), respectively.

Conclusion

ML can be used as an assessment tool for predicting the motor function in patients with 3-6 months of post-stroke. Additionally, the study found that ML models with radiomics as a predictive variable were also demonstrated to have good predictive capabilities. This systematic review provides valuable guidance for the future optimization of ML prediction systems that predict poor motor outcomes in stroke patients.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022335260, identifier: CRD42022335260.

Predicting futile recanalization, malignant cerebral edema, and cerebral herniation using intelligible ensemble machine learning following mechanical thrombectomy for acute ischemic stroke

Purpose

To establish an ensemble machine learning (ML) model for predicting the risk of futile recanalization, malignant cerebral edema (MCE), and cerebral herniation (CH) in patients with acute ischemic stroke (AIS) who underwent mechanical thrombectomy (MT) and recanalization.

Methods

This prospective study included 110 patients with premorbid mRS ≤ 2 who met the inclusion criteria. Futile recanalization was defined as a 90-day modified Rankin Scale score >2. Clinical and imaging data were used to construct five ML models that were fused into a logistic regression algorithm using the stacking method (LR-Stacking). We added the Shapley Additive Explanation method to display crucial factors and explain the decision process of models for each patient. Prediction performances were compared using area under the receiver operating characteristic curve (AUC), F1-score, and decision curve analysis (DCA).

Results

A total of 61 patients (55.5%) experienced futile recanalization, and 34 (30.9%) and 22 (20.0%) patients developed MCE and CH, respectively. In test set, the AUCs for the LR-Stacking model were 0.949, 0.885, and 0.904 for the three outcomes mentioned above. The F1-scores were 0.882, 0.895, and 0.909, respectively. The DCA showed that the LR-Stacking model provided more net benefits for predicting MCE and CH. The most important factors were the hypodensity volume and proportion in the corresponding vascular supply area.

Conclusion

Using the ensemble ML model to analyze the clinical and imaging data of AIS patients with successful recanalization at admission and within 24 h after MT allowed for accurately predicting the risks of futile recanalization, MCE, and CH.

Effect of Vitamin D Supplementation on the Prognosis of Post-stroke Fatigue: A Retrospective Cohort Study

Objective: We aimed to evaluate the effect of vitamin D supplementation in post-stroke fatigue (PSF) patients with vitamin D deficiency on fatigue symptoms and outcomes. Methods: Patients with primary acute ischemic stroke (AIS) were recruited consecutively from July 2016 to June 2018. Post-stroke fatigue patients were screened out with the Fatigue Severity Scale (FSS) questionnaire, serum concentrations of 25-hydroxyvitamin D [25-(OH)-D] were assessed with enzyme-linked immunosorbent assay (ELISA), and neurological function was evaluated with FSS and modified Rankin Scale (mRS) scoring criteria. Post-stroke fatigue patients with vitamin D deficiency were divided into two groups: a study group in which patients received vitamin D supplementation (cholecalciferol, 600 IU/day) along with usual care, and a control group in which patients received usual care alone. At the end of 1 and 3 months after treatment, all PSE patients accepted re-measurement of serum vitamin D and re-evaluation of fatigue and neurological function. Results: A total of 532 AIS patients were consecutively recruited to participate in this study. Patients without PSF, non-vitamin D deficiency, pre-stroke fatigue, or vitamin D supplementation were excluded from the study. In addition, patients who were lost to follow-up were also excluded. Finally, 139 out of 532 (26.1%) patients with PSF and vitamin D deficiency received vitamin D supplementation treatment. Fatigue Severity Scale score was significantly lower in the study group than in the control group at 1 month (t = -4.731, p < 0.01) and 3 months (t = -7.937, p < 0.01) after treatment. One month after treatment, mRS score in the study group was lower than that in the control group without statistical difference (t = -0.660, p > 0.05), whereas mRS was significantly higher in the study group than in the control group at 3 months after treatment (t = -4.715, p < 0.01). Conclusions: Our results indicated that vitamin D supplementation could improve fatigue symptoms and neurological outcomes in PSF patients with vitamin D deficiency. Subject to replication in other settings, a randomized controlled trial (RCT) might be undertaken to validate the potential beneficial impact of vitamin D supplementation in post-stroke patients found to be vitamin D deficient.