Machine Learning Application: A Bibliometric Analysis From a Half-Century of Research on Stroke.

The quick advancement of digital technology through artificial intelligence has made it possible to deploy machine learning to predict stroke outcomes. Our aim is to examine the trend of machine learning applications in stroke-related research over the past 50 years. We used search terms stroke and machine learning to search for English versions of original and review articles and conference proceedings published over the past 50 years in Scopus and Web of Science databases. The Biblioshiny web application was utilized for the analysis. The trend of publication and prominent authors and journals were analyzed and identified. The collaborative network between countries was mapped, and a thematic map was used to monitor the authors' trending keywords. In total, 10,535 publications authored by 44,990 authors from 2,212 sources were retrieved. Two distinct clusters of collaborative network nodes were observed, with the United States serving as a connecting node. Three terms - deep learning, algorithms, and neural networks - are observed in the early stages of the emerging theme. Overall, international research collaborations, the establishment of global research initiatives, the development of computational science, and the availability of big data have facilitated the pervasive use of machine learning techniques in stroke research.

Neurological manifestations in SARS-CoV-2 infection: A single-center cross-sectional study in Malaysia.

Background: Neurological involvement associated with SARS-CoV-2 infection has been reported from different regions of the world. However, data from South East Asia are scarce. We described the neurological manifestations and their associated factors among the hospitalized COVID-19 patients from an academic tertiary hospital in Malaysia. Methods: A cross-sectional observational study of hospitalized COVID-19 patients was conducted. The neurological manifestations were divided into the self-reported central nervous system (CNS) symptoms, stroke associated symptoms, symptoms of encephalitis or encephalopathy and specific neurological complications. Multiple logistic regression was performed using demographic and clinical variables to determine the factors associated with outcome. Results: Of 156 hospitalized COVID-19 patients with mean age of 55.88 ± 6.11 (SD) years, 23.7% developed neurological complications, which included stroke, encephalitis and encephalopathy. Patients with neurological complications were more likely to have diabetes mellitus (p = 0.033), symptoms of stroke [limb weakness (p < 0.001), slurred speech (p < 0.001)]; and encephalitis or encephalopathy [confusion (p < 0.001), forgetfulness (p = 0.006) and seizure (p = 0.019)]. Unvaccinated patients had a 4.25-fold increased risk of having neurological complications (adjusted OR = 4.25; 95% CI: 1.02, 17.71, p = 0.047). Anosmia and dysgeusia were less associated with neurological complications (adjusted OR = 0.22; 95% CI: 0.05, 0.96, p = 0.044). The odds of neurological complications were increased by 18% in patients with leukocytosis (adjusted OR = 1.18, 95% CI: 1.003, p = 0.0460). Conclusions: Stroke, encephalitis and encephalopathy were the common neurological complications from our study. Diabetes mellitus, presence of symptoms of stroke, symptoms of encephalitis or encephalopathy, leukocytosis, and being unvaccinated against COVID-19 were the associated risk factors of developing neurological complications.

Machine Learning Models for Predicting Stroke Mortality in Malaysia: An Application and Comparative Analysis.

Background Stroke is a significant public health concern characterized by increasing mortality and morbidity. Accurate long-term outcome prediction for acute stroke patients, particularly stroke mortality, is vital for clinical decision-making and prognostic management. This study aimed to develop and compare various prognostic models for stroke mortality prediction. Methods In a retrospective cohort study from January 2016 to December 2021, we collected data from patients diagnosed with acute stroke from five selected hospitals. Data contained variables on demographics, comorbidities, and interventions retrieved from medical records. The cohort comprised 950 patients with 20 features. Outcomes (censored vs. death) were determined by linking data with the Malaysian National Mortality Registry. We employed three common survival modeling approaches, the Cox proportional hazard regression (Cox), support vector machine (SVM), and random survival forest (RSF), while enhancing the Cox model with Elastic Net (Cox-EN) for feature selection. Models were compared using the concordance index (C-index), time-dependent area under the curve (AUC), and discrimination index (D-index), with calibration assessed by the Brier score. Results The support vector machine (SVM) model excelled among the four, with three-month, one-year, and three-year time-dependent AUC values of 0.842, 0.846, and 0.791; a D-index of 5.31 (95% CI: 3.86, 7.30); and a C-index of 0.803 (95% CI: 0.758, 0.847). All models exhibited robust calibration, with three-month, one-year, and three-year Brier scores ranging from 0.103 to 0.220, all below 0.25. Conclusion The support vector machine (SVM) model demonstrated superior discriminative performance, suggesting its efficacy in developing prognostic models for stroke mortality. This study enhances stroke mortality prediction and supports clinical decision-making, emphasizing the utility of the support vector machine method.

Guidelines on the use of disinfectants: comparison between Malaysia and other countries.

Aim: Sanitation and cleanliness are essential factors in reducing the spread of pathogens and preventing healthcare-associated infections. Disinfectants are associated with better hygiene outcomes to reduce pathogen transmission risk and minimize risks to healthcare workers (HCWs) and patients. Methods: A literature search was undertaken using the electronic databases Scopus, Web of Science, Ovid and Google Scholar. The inclusion criteria for this study are observational and original research studies dating from the five-year period 2017-2021. Other inclusion criteria are full text, English language, qualitative or quantitative studies relevant to the research question. The exclusion criteria are animal studies, systematic reviews, conference proceedings, abstracts, projection modelling studies, in-vivo or in-vitro studies, and books. Results: Five study nations included the United States of America (USA), the United Kingdom (UK), China, India and South Korea, together with Malaysia. These nations have existing policies, regulations and guidelines regarding the use of disinfectants. HCWs should be aware of the national laws and guidelines that govern the purchase, distribution and use of disinfectants. They should also understand the different roles of the agencies involved, so the context for the guidance provided is clear. Coordination and collaboration across various stakeholders are required for creating solid policies. Conclusion: Product research and innovation are indispensable, as appropriate personal protective equipment and safety measures for HCWs and patients have top priority in every nation. Hence, clear guidelines for handling disinfectants, in addition to health education about scientific-evidence-based disinfectants, are required.

The effects of intravenous infusion of autologous mesenchymal stromal cells in patients with subacute middle cerebral artery infarct: a phase 2 randomized controlled trial on safety, tolerability and efficacy.

BACKGROUND AIMS: Mesenchymal stromal cells (MSCs) are characterized by paracrine and immunomodulatory functions capable of changing the microenvironment of damaged brain tissue toward a more regenerative and less inflammatory milieu. The authors conducted a phase 2, single-center, assessor-blinded randomized controlled trial to investigate the safety and efficacy of intravenous autologous bone marrow-derived MSCs (BMMSCs) in patients with subacute middle cerebral artery (MCA) infarct. METHODS: Patients aged 30-75 years who had severe ischemic stroke (National Institutes of Health Stroke Scale [NIHSS] score of 10-35) involving the MCA territory were recruited within 2 months of stroke onset. Using permuted block randomization, patients were assigned to receive 2 million BMMSCs per kilogram of body weight (treatment group) or standard medical care (control group). The primary outcomes were the NIHSS, modified Rankin Scale (mRS), Barthel Index (BI) and total infarct volume on brain magnetic resonance imaging (MRI) at 12 months. All outcome assessments were performed by blinded assessors. Per protocol, analyses were performed for between-group comparisons. RESULTS: Seventeen patients were recruited. Nine were assigned to the treatment group, and eight were controls. All patients were severely disabled following their MCA infarct (median mRS = 4.0 [4.0-5.0], BI = 5.0 [5.0-25.0], NIHSS = 16.0 [11.5-21.0]). The baseline infarct volume on the MRI was larger in the treatment group (median, 71.7 [30.5-101.7] mL versus 26.7 [12.9-75.3] mL, P = 0.10). There were no between-group differences in median NIHSS score (7.0 versus 6.0, P = 0.96), mRS (2.0 versus 3.0, P = 0.38) or BI (95.0 versus 67.5, P = 0.33) at 12 months. At 12 months, there was significant improvement in absolute change in median infarct volume, but not in total infarct volume, from baseline in the treatment group (P = 0.027). No treatment-related adverse effects occurred in the BMMSC group. CONCLUSIONS: Intravenous infusion of BMMSCs in patients with subacute MCA infarct was safe and well tolerated. Although there was no neurological recovery or functional outcome improvement at 12 months, there was improvement in absolute change in median infarct volume in the treatment group. Larger, well-designed studies are warranted to confirm this and the efficacy of BMMSCs in ischemic stroke.

Knowledge of Acute Stroke Management Among Healthcare Professionals: Development and Validation of Acute Stroke Management Questionnaire (ASMaQ).

BACKGROUND: Around 15.0% of all strokes occurred in hospitalised patients and studies showed significant delay in the stroke recognition and lack of awareness on thrombolytic therapy for acute ischaemic stroke (AIS) which lead to higher mortality for in-hospital stroke. We aimed to develop and validate a new instrument known as acute stroke management questionnaire (ASMaQ) to evaluate the awareness of healthcare professionals in managing acute ischaemic stroke cases. METHODS: This study consisted of 3 steps; the formulation of ASMaQ draft, content validation and construct validity. A total of 110 questions were drafted with 5-point Likert scale answers. From the list, 31 were selected and subsequently tested on 158 participants. The results were analysed and validated using exploratory factor analysis on SPSS. Components were extracted and questions with low factor loading were removed. The internal consistency was then measured with Cronbach's alpha. RESULTS: Following analysis, 3 components were extracted and named as general stroke knowledge, hyperacute stroke care and advanced stroke management. Two items were deleted leaving 29 out of 31 questions for the final validated ASMaQ. Internal consistency showed high reliability with Cronbach's alpha of 0.82. Our respondents scored a total cumulative mean of 113.62 marks or 66.6%. A sub analysis by occupation showed that medical assistants scored the lowest in the group with a score of 57% whilst specialists including neurologists scored the highest at 79.4%. CONCLUSION: The ASMaQ is a newly developed and validated questionnaire consisting of 29 questions testing the respondents' acute stroke management knowledge.

Cerebral Lupus and Cryptococcal Meningitis in a Pregnant Woman.

Systemic lupus erythematosus (SLE) is a chronic autoimmune and multisystem disorder, which frequently affects young women. During pregnancy, SLE flares could occur up to 65%, with renal and hematological manifestations being the most common. However, reports on neuropsychiatric lupus in pregnant women are scarce. We herein report a 26-year-old lupus pregnant woman, who had cerebral lupus with concurrent cryptococcal meningitis. This case highlights the complexity in diagnosing and managing our patient to achieve the best outcome for both the mother and infant.

Relative adrenal insufficiency amongst hospitalized mild to moderate acute ischemic stroke patients.

INTRODUCTION: Acute ischemic stroke is a stressful condition where there is marked increase in the production of cortisol. In the past, adrenal insufficiency in critically ill patients had been shown to be associated with significant morbidity and mortality. To date, there have been no studies performed to determine its prevalence among patients with acute ischemic stroke.  OBJECTIVES: The aim of this study was to determine the prevalence of relative adrenal insufficiency in acute ischemic stroke by utilizing low dose (LD) and standard dose (SD) synacthen tests and to correlate it with inpatient hospital morbidity and mortality. METHOD: Fifty-eight patients who fulfilled the diagnosis of acute ischemic stroke within 72 hours from the onset of a stroke were subjected to LD (1µg) synacthen test (LDST) and two hours later to SD (250 µg) synacthen test (SDST). RESULT: Based on an increment of less than 250 nmol/L after LDST, 38 (65.5%) patients had relative adrenal insufficiency. However, using similar criteria with the SDST, only 18 (31.0%) patients had relative adrenal insufficiency. Three patients died during the study period and they had a tendency to have high baseline cortisol levels. The diagnosis of relative adrenal insufficiency in general was not associated with any other significant clinical outcomes. CONCLUSION: This is the first study demonstrating the prevalence of relative adrenal insufficiency amongst acute ischemic stroke patients. Utilizing the LDST, relative adrenal insufficiency was found more sensitive in detecting relative adrenal insufficiency in patients with acute ischemic stroke as compared to SDST.