Incidence, clinical features and outcomes of atrial fibrillation and stroke in Qatar

Utilizing machine learning to facilitate the early diagnosis of posterior circulation stroke

BACKGROUND

Posterior Circulation Syndrome (PCS) presents a diagnostic challenge characterized by its variable and nonspecific symptoms. Timely and accurate diagnosis is crucial for improving patient outcomes. This study aims to enhance the early diagnosis of PCS by employing clinical and demographic data and machine learning. This approach targets a significant research gap in the field of stroke diagnosis and management.

METHODS

We collected and analyzed data from a large national Stroke Registry spanning from January 2014 to July 2022. The dataset included 15,859 adult patients admitted with a primary diagnosis of stroke. Five machine learning models were trained: XGBoost, Random Forest, Support Vector Machine, Classification and Regression Trees, and Logistic Regression. Multiple performance metrics, such as accuracy, precision, recall, F1-score, AUC, Matthew's correlation coefficient, log loss, and Brier score, were utilized to evaluate model performance.

RESULTS

The XGBoost model emerged as the top performer with an AUC of 0.81, accuracy of 0.79, precision of 0.5, recall of 0.62, and F1-score of 0.55. SHAP (SHapley Additive exPlanations) analysis identified key variables associated with PCS, including Body Mass Index, Random Blood Sugar, ataxia, dysarthria, and diastolic blood pressure and body temperature. These variables played a significant role in facilitating the early diagnosis of PCS, emphasizing their diagnostic value.

CONCLUSION

This study pioneers the use of clinical data and machine learning models to facilitate the early diagnosis of PCS, filling a crucial gap in stroke research. Using simple clinical metrics such as BMI, RBS, ataxia, dysarthria, DBP, and body temperature will help clinicians diagnose PCS early. Despite limitations, such as data biases and regional specificity, our research contributes to advancing PCS understanding, potentially enhancing clinical decision-making and patient outcomes early in the patient's clinical journey. Further investigations are warranted to elucidate the underlying physiological mechanisms and validate these findings in broader populations and healthcare settings.

Machine learning-based prognostication of mortality in stroke patients

Objectives

Predicting stroke mortality is crucial for personalized care. This study aims to design and evaluate a machine learning model to predict one-year mortality after a stroke.

Materials and methods

Data from the National Multiethnic Stroke Registry was utilized. Eight machine learning (ML) models were trained and evaluated using various metrics. SHapley Additive exPlanations (SHAP) analysis was used to identify the influential predictors.

Results

The final analysis included 9840 patients diagnosed with stroke were included in the study. The XGBoost algorithm exhibited optimal performance with high accuracy (94.5%) and AUC (87.3%). Core predictors encompassed National Institutes of Health Stroke Scale (NIHSS) at admission, age, hospital length of stay, mode of arrival, heart rate, and blood pressure. Increased NIHSS, age, and longer stay correlated with higher mortality. Ambulance arrival and lower diastolic blood pressure and lower body mass index predicted poorer outcomes.

Conclusions

This model's predictive capacity emphasizes the significance of NIHSS, age, hospital stay, arrival mode, heart rate, blood pressure, and BMI in stroke mortality prediction. Specific findings suggest avenues for data quality enhancement, registry expansion, and real-world validation. The study underscores machine learning's potential for early mortality prediction, improving risk assessment, and personalized care. The potential transformation of care delivery through robust ML predictive tools for Stroke outcomes could revolutionize patient care, allowing for personalized plans and improved preventive strategies for stroke patients. However, it is imperative to conduct prospective validation to evaluate its practical clinical effectiveness and ensure its successful adoption across various healthcare environments.

Incidence, clinical features, and outcomes of posterior circulation ischemic stroke: insights from a large multiethnic stroke database

Background

Posterior cerebral circulation ischemic stroke (PCS) comprises up to 25% of all strokes. It is characterized by variable presentation, leading to misdiagnosis and morbidity and mortality. We aim to describe PCS in large multiethnic cohorts.

Methods

A retrospective review of a large national stroke database from its inception on the 1st of January 2014 till 31 December 2020. Incidence per 100,000 adult population/year, demographics, clinical features, stroke location, and outcomes were retrieved. We divided the cohort into patients from MENA (Middle East and North Africa) and others.

Results

In total, 1,571 patients were identified. The incidence of PCS was observed to be rising and ranged from 6.3 to 13.2/100,000 adult population over the study period. Men were 82.4% of the total. The mean age was 54.9 ± 12.7 years (median 54 years, IQR 46, 63). MENA patients comprised 616 (39.2%) while others were 954 (60.7%); of these, the majority (80.5%) were from South Asia. Vascular risk factors were prevalent with 1,230 (78.3%) having hypertension, 970 (61.7%) with diabetes, and 872 (55.5%) having dyslipidemia. Weakness (944, 58.8%), dizziness (801, 50.5%), and slurred speech (584, 36.2%) were the most commonly presenting symptoms. The mean National Institute of Health Stroke Score (NIHSS) score was 3.8 ± 4.6 (median 3, IQR 1, 5). The overall most frequent stroke location was the distal location (568, 36.2%). The non-MENA cohort was younger, less vascularly burdened, and had more frequent proximal stroke location (p < 0.05). Dependency or death at discharge was seen in 39.5% and was associated with increasing age, and proximal and multilocation involvement; while at 90 days it was 27.4% and was associated with age, male sex, and having a MENA nationality (p < 0.05).

Conclusion

In a multiethnic cohort of posterior circulation stroke patients from the MENA region and South Asia, we noted a rising incidence over time, high prevalence of vascular risk factors, and poor outcomes in older men from the MENA region. We also uncovered considerable disparities between the MENA and non-MENA groups in stroke location and outcome. These disparities are crucial factors to consider when tailoring individualized patient care plans. Further research is needed to thoroughly investigate the underlying reasons for these variations.

Predicting 90-day prognosis for patients with stroke: a machine learning approach

Background

Stroke is a significant global health burden and ranks as the second leading cause of death worldwide.

Objective

This study aims to develop and evaluate a machine learning-based predictive tool for forecasting the 90-day prognosis of stroke patients after discharge as measured by the modified Rankin Score.

Methods

The study utilized data from a large national multiethnic stroke registry comprising 15,859 adult patients diagnosed with ischemic or hemorrhagic stroke. Of these, 7,452 patients satisfied the study's inclusion criteria. Feature selection was performed using the correlation and permutation importance methods. Six classifiers, including Random Forest (RF), Classification and Regression Tree, Linear Discriminant Analysis, Support Vector Machine, and k-Nearest Neighbors, were employed for prediction.

Results

The RF model demonstrated superior performance, achieving the highest accuracy (0.823) and excellent discrimination power (AUC 0.893). Notably, stroke type, hospital acquired infections, admission location, and hospital length of stay emerged as the top-ranked predictors.

Conclusion

The RF model shows promise in predicting stroke prognosis, enabling personalized care plans and enhanced preventive measures for stroke patients. Prospective validation is essential to assess its real-world clinical performance and ensure successful implementation across diverse healthcare settings.

Predicting 90-Day Prognosis in Ischemic Stroke Patients Post Thrombolysis Using Machine Learning

(1) Objective: This study aimed to construct a machine learning model for predicting the prognosis of ischemic stroke patients who underwent thrombolysis, assessed through the modified Rankin Scale (mRS) score 90 days after discharge. (2) Methods: Data were sourced from Qatar's stroke registry covering January 2014 to June 2022. A total of 723 patients with ischemic stroke who had received thrombolysis were included. Clinical variables were examined, encompassing demographics, stroke severity indices, comorbidities, laboratory results, admission vital signs, and hospital-acquired complications. The predictive capabilities of five distinct machine learning models were rigorously evaluated using a comprehensive set of metrics. The SHAP analysis was deployed to uncover the most influential predictors. (3) Results: The Support Vector Machine (SVM) model emerged as the standout performer, achieving an area under the curve (AUC) of 0.72. Key determinants of patient outcomes included stroke severity at admission; admission systolic and diastolic blood pressure; baseline comorbidities, notably hypertension (HTN) and coronary artery disease (CAD); stroke subtype, particularly strokes of undetermined origin (SUO); and hospital-acquired urinary tract infections (UTIs). (4) Conclusions: Machine learning can improve early prognosis prediction in ischemic stroke, especially after thrombolysis. The SVM model is a promising tool for empowering clinicians to create individualized treatment plans. Despite limitations, this study contributes to our knowledge and encourages future research to integrate more comprehensive data. Ultimately, it offers a pathway to improve personalized stroke care and enhance the quality of life for stroke survivors.

Rescue Stent Placement for Acute Ischemic Stroke with Large Vessel Occlusion Refractory to Mechanical Thrombectomy: A Multiethnic Middle Eastern/African/Asian Cohort

PURPOSE

To investigate the safety and effectiveness of rescue stent placement in patients who experienced acute stroke in whom mechanical thrombectomy failed.

METHODS

This was a retrospective review of a multiethnic stroke database. After stent placement, an aggressive antiplatelet protocol was followed with glycoprotein IIb/IIIa infusion. The primary outcomes were incidence of intracerebral hemorrhage (ICH), recanalization score, and favorable prognosis (modified Rankin score ≤ 2) at 90 days. A comparison was made between patients from the Middle East and North Africa (MENA) region and those from other regions.

RESULTS

Fifty-five patients were included, with 87% being men. The mean age was 51.3 years (SD ±11.8); 32 patients (58%) were from South Asia, 12 (22%) from MENA, 9 (16%) from Southeast Asia, and 2 (4%) from elsewhere. Successful recanalization (modified Thrombolysis in Cerebral Infarction score = 2b/3) was achieved in 43 patients (78%), and symptomatic ICH occurred in 2 patients (4%). A favorable outcome at 90 days was seen in 26 of the 55 patients (47%). Apart from significantly older age-mean, 62.8 years (SD ±13; median, 69 years) versus 48.1 years (SD ±9.3; median, 49 years)-and coronary artery disease burden-4 (33%) versus 1 (2%) (P < .05), patients from MENA had risk factors, stroke severity, recanalization rates, ICH rates, and 90-day outcomes similar to those from South and Southeast Asia.

CONCLUSION

Rescue stent placement showed good outcomes and a low risk of clinically significant bleeding in a multiethnic cohort of patients from MENA and South and Southeast Asia, similar to that in published literature.

Trends in stroke admissions before, during and post-peak of the COVID-19 pandemic: A one-year experience from the Qatar stroke database

Background

Several reports document a decrease in the rates of stroke hospital admissions during the covid-19 pandemic. There is very little information whether the admission rates will change as the infection is controlled. We report on our rates of admissions before, during and following the peak of covid-19 infections in a prospective database from Qatar.

Methods and results

The stroke admissions in the six months prior to COVID-19 pandemic averaged 229/month. There was a decrease to 157/month in March-June during the peak of the pandemic. In the 6 months following the peak, as covid-19 numbers began to decrease, the average numbers increased back to 192/month. There was an increase in severe ischemic strokes and decreased in functional recovery. The decreased admissions were mainly driven by fewer stroke mimics. Patients presenting with ischemic stroke or cerebral hemorrhage remained unchanged.

Conclusions

Fewer stroke mimics presenting to the hospital can explain the fewer admissions and poor outcome at the height of the covid-19 pandemic. The continued decrease in the number of ischemic stroke and stroke mimic admissions following the pandemic peak requires more study.

Impact of thyroid disease in patients with atrial fibrillation: Analysis from the JoFib registry

Background

Thyroid disease is a well-established risk factor for atrial fibrillation (AF). However, only a handful of studies examined its impact on treatment. This study aims to report the prevalence rate of thyroid disease in patients with AF and to demonstrate the effect of thyroid disease on AF treatment.

Materials and methods

We retrospectively analyzed the Jordanian Atrial Fibrillation Study (JoFib). Among Jordan and Palestine, patients with AF were evaluated for their sociodemographic, clinical, and pharmacological characteristics.

Results

A total of 2000 patients with AF (53.3% males, mean age 67.6 ± 13.1 years) were enrolled in the JoFib registry from May 2019 to November 2020. Thyroid disease was present in 210 (10.5%) patients. Hypertension, diabetes mellitus, and dyslipidemia were the most common comorbidities among patients with thyroid history (75.2%, 51.0%, and 45.7%, respectively). Diabetes mellitus (p = .04), pulmonary hypertension (p = .01), and chronic kidney disease (p = .01) were significantly higher in this particular subgroup. Patients with thyroid disease demonstrated significantly higher usage of anticoagulants (p = .02).

Conclusion

Despite having similar stroke and bleeding risks, patients with thyroid disease demonstrated meaningful differences in their baseline characteristics. Prospective studies are required to assess the influence of thyroid hormone fluctuations on the progression of AF.

•

Thyroid disease doesn't appear to impact bleeding risk in atrial fibrillation.

•

Patients with thyroid disease are more likely to consume more anticoagulants.

•

Thyroid disease in atrial fibrillation maybe linked with pulmonary hypertension.

•

Assessment tools of stork or bleeding may be underestimated in Arab Jordanians.

Stroke in the adult Qatari population (Q-stroke) a hospital-based retrospective cohort study

BACKGROUND

Studies assessing the burden of stroke in Qataris are limited. We aim to study stroke in the Qatari population.

METHODS

A retrospective review was undertaken of all Qatari adults presenting with stroke to Hamad Medical Corporation over a 5-year period. Descriptive statistics were used to summarize demographic and all other clinical characteristics of the patients. The primary outcome was the incidence of stroke in the Qatari patients. Comparison was made between the sexes.

RESULTS

862 patients were included, with 58.9% being male. The average incidence of stroke over the 5-year period was 92.04 per 100,000 adult Qatari population. The mean age of the cohort was 64.3±14.4 years, (range 19-105 years). The mean age of first ever cerebrovascular event was 63.2±14.5 years. The diagnosis was ischemic stroke in (73.7%), transient ischemic attack in (13.8%), intracerebral hemorrhage (ICH) in (11.6%), subarachnoid hemorrhage in (0.7%) and (0.2%) cerebral venous sinus thrombosis. Small vessel disease was the most common cause of ischemic stroke accounting for (46.5%), followed by large artery atherosclerosis (24.5%). Hypertension (82.7%) and diabetes (71.6%) were particularly prevalent in this cohort. Females were older (65.8±14.1 vs 63.4±14.5 years), had more hypertension and diabetes and more disability or death at 90 days (p<0.05) compared to Qatari males.

CONCLUSION

Stroke occurs at a significantly lower age in Qataris compared to the western population. This study has uncovered sex differences that need to be studied further.

Current status of stroke in Qatar: Including data from the BRAINS study

BACKGROUND

Qatar is located on the north-eastern coast of the Arabian Peninsula. Qatari natives account for less than 15% of the population while the largest migrant group comprising 60% derives from South Asia. Despite projections that stroke burden in Qatar will increase with population ageing, epidemiological studies focusing on stroke in Qatar are relatively scarce.

METHOD

We reviewed the available epidemiological publications relating to Qatar. In addition, we have added to this knowledge by incorporating Qatari data from the on-going Bio-Repository of DNA in Stroke, an independent multinational database of stroke patients.

RESULTS

Qatar has low reported incidence and mortality rates of 58 and 9.17 per 100,000 per year, respectively, which may be explained by its middle-aged migrant worker majority population. Correspondingly, South Asian migrants in Qatar suffered younger strokes than Qatari natives (48.7 vs 63.4 years, P < 0.001). Among the most common risk factors identified in stroke patients were hypertension (77.9%), diabetes (43.8%) and hypercholesterolemia (28.5%). Ischaemic stroke was the most frequent subtype amongst migrant South Asians (71.1%). The majority of stroke cases had computed tomography and/or magnetic resonance imaging scans, but only 11.1% of ischaemic strokes were thrombolysed. Qataris on one-year follow up were more often found to have died (6.5% vs 0.3%) and had further stroke/transient ischaemic attack events (17.4% vs 6.4%, P = 0.009) compared to South Asians.

CONCLUSION

The burden of stroke is increasing in Qatar, and considerable disparities are observed between the native and migrant populations which likely will require different approaches to management by its healthcare system.