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.

Short-term functional outcomes of patients with acute intracerebral hemorrhage in the native and expatriate population.

Objectives: Functional outcomes in patients with intracerebral hemorrhage (ICH) have not been well characterized in the Middle East and North Africa Region. We report the 30 and 90-day clinical outcomes in the native and expatriate of Qatar with ICH. Methods: We evaluated the Glasgow Coma Scale (GCS), NIHSS, and imaging in the Qatar Stroke Registry (2013-22). The outcome measures were a modified Rankin Scale (mRS) at 90 days and mortality at 30 and 90 days. Unfavorable outcome was defined as mRS of 4-6. We performed non-parametric ROC analyses to measure the concordance index (C-index) to assess the goodness-of-fit of ICH score for predicting 30 day and 90-day mortality and functional outcome. Results: 1,660 patients (median age of 49 (41.5-58) years; male 83.1%, expatriates 77.5%) with ICH, including supratentorial deep in 65.2%, cortical in 16.2%, infratentorial 16% and primary intraventricular in 2.5% were studied. The median baseline ICH volume was 7.5 (3.2-15.8) ml. An unfavorable outcome was seen in 673 (40.5%) patients at 90 days. The unfavorable 90-day outcome (mRS 4-6) was 49.2% in the native population vs. 44.4% in Africans, 39.0% in South Asian, 35.3% in Far Eastern, and 7.7% in Caucasians, p < 0.001. Mortality at 30 days and 90 days was 10.4 and 15.1%. Increasing age [OR (95% CI), 1.02 (1.00-1.03)], lower GCS [0.77 (0.73-0.80)], prior use of antiplatelet medications [1.82 (1.19-2.08)], higher ICH volume [1.03 (1.02-1.04)], and presence of any intraventricular hemorrhage [1.57(1.19-2.08)], were associated with unfavorable outcome. Conclusion: In this relatively younger ICH cohort more than 75% were expatriates. The ICH volume, 90-day unfavorable outcome and mortality was lower in the expatriates compared to the local Arab population, likely related to the younger age and smaller size of the hemorrhages. Prognostic scoring systems may have to be modified in this population to avoid early withdrawal of care.

Structural elucidation and development of azelaic acid loaded mesoporous silica nanoparticles infused gel: Revolutionizing nanodrug delivery for cosmetics and pharmaceuticals.

This research aimed to enhance dermal delivery and optimize depigmentation therapy by designing mesoporous silica nanoparticles (MSNs) encapsulating azelaic acid (AZA) within a gel matrix. The MSNs were prepared using the sol-gel method. After subsequent processes, including acid extraction and drug loading, were then elucidated through PDI, size, zeta-potential, entrapment efficiency, nitrogen adsorption assay, FE-SEM, thermogravimetric analysis, differential scanning calorimetry, Fourier transform infrared spectroscopy, X-ray diffraction, and tyrosinase inhibition assay, were employed to assess the formulation. In-vitro stability tests for both AZA-MSN gel (AZCG) and AZA-loaded mesoporous silica gel (AZMG) were conducted at 8 °C, 25 °C, 40 °C, and 40 °C + 75 % RH, encompassing assessments of color, liquefaction, pH, and conductivity. Our findings showed a notable entrapment efficiency of 93.46 % for AZA-MSNs, with FE-SEM illustrating porous spherical MSNs. The particle size of AZA-MSNs was determined to be 211.9 nm, with a pore size of 2.47 nm and XRD analysis confirmed the amorphous state of AZA within the MSN carriers. Rheology examination indicated a non-Newtonian flow, while ex-vivo rat skin permeation studies conducted in a phosphate buffer (pH = 5.5) demonstrated a biphasic release pattern with 85.53 % cumulative drug permeation for AZA-MSNs. Overall, the study endorse the potential of AZA-MSNs as an efficacious and stable formulation for AZA delivery, highlighting their promise in addressing pigmentation concerns compared to conventional approaches.

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.

Epidemiological profile of stroke in Qatar: Insights from a seven-year observational study.

OBJECTIVES: Stroke prevalence is progressively increasing in developing countries due to increased vascular risk factors. This study aims to describe the epidemiology, prevalent risk factors, and outcomes of stroke in a multi-ethnic society of Qatar. MATERIALS AND METHODS: We conducted a retrospective analysis of all patients with suspected stroke admitted to stroke services between January 2014 and September 2020. RESULTS: A total of 11,892 patients were admitted during this period with suspected stroke. Of these, the diagnosis was ischemic stroke (48.8 %), transient ischemic attack (10.3 %), intracerebral hemorrhage (10.9 %), cerebral venous sinus thrombosis (1.3 %), and stroke mimics (28.6 %). The median age was 52 (43-62), with a male-female ratio of 3:1. The study population was predominantly Asian (56.8 %) and Arab (36 %). The majority of the patients were hypertensive (66.8 %), diabetic (47.9 %), and dyslipidemic (45.9 %). A history of prior stroke was observed in 11.7 %, while 0.9 % had prior transient ischemic attack. Among ischemic strokes, 31.7 % arrived within 4.5 h, 12.5 % received thrombolysis, and 4.6 % underwent thrombectomy. Median Door-to-Needle time was 51 (33-72) minutes. The average length of stay was 5.2 ± 9.0 days, with 71.5 % discharged home, 13.8 % transferred to rehabilitation, 9.3 % to other specialties, 3 % to long-term care, and 2.4 % suffered in-hospital mortality. CONCLUSION: Stroke in Qatar is characterized by a younger, expatriate-dominant cohort, with notable prevalence of ischemic and hemorrhagic stroke and a distinct risk factor profile. Further analysis of epidemiological differences among different population groups can inform targeted policies for prevention and management to reduce the burden of disease.

Association between serum triglycerides and stroke type, severity, and prognosis. Analysis in 6558 patients.

BACKGROUND AND OBJECTIVES: Hypertriglyceridemia (HT) may increase the risk of stroke. Limited studies have shown that stroke severity and infarction size are smaller in patients with HT. We explored the relationship between triglyceride levels and stroke risk factors, severity and outcome in a large prospective database. DESIGN: Prospective Cross-sectional study. SETTING: We retrospectively interrogated the Qatar Stroke Database in all patients admitted between 2014-2022 with acute ischemic stroke and evaluated the relationship between triglyceride, diabetes, stroke severity (measured on NIHSS), stroke type (TOAST classification) and the short- (mRS at 90 days) and long-term outcomes (MACE at 1 year) in patients with HT. PARTICIPANTS: Six thousand five hundred fifty-eight patients ≥20 years were included in this study RESULTS: Six thousand five hundred fifty-eight patients with ischemic stroke [mean age 54.6 ± 12. 9; male 82.1%) were included. Triglyceride levels upon admission were low-normal (≤1.1 mmol/L) in 2019 patients, high-normal (1.2-1.7 mmol/L) in 2142 patients, borderline-high (1.8-2.2 mmol/L) in 1072 patients and high (≥2.3 mmol/L) in 1325 patients. Higher triglyceride levels were associated with stroke and increased likelihood of having diabetes, obesity, active smoking, and small vessel/lacunar stroke type. An inverse relationship was noted whereby higher triglyceride levels were associated with lower stroke severity and reduced likelihood of poorer outcome (mRS 3-6) at discharge and 90 days. Long-term MACE events were less frequent in patients with higher triglyceride levels. After adjusting age, gender, diabetes, prior stroke, CAD, and obesity, multivariate analysis showed that hypertension and triglyceride levels were higher in mild ischemic strokes patients. CONCLUSIONS: Increasing triglycerides are associated with higher risk of small vessel disease and requires further prospective cohort studies for confirmation.

Larger wind turbines as a solution to reduce environmental impacts.

The EU aims for carbon neutrality by 2050, focusing on offshore wind energy. Investments in North Sea wind farms, with optimal wind resources, play a crucial role. We employed a high-resolution regional climate model, which incorporates a wind farm parametrization, to investigate and address potential mitigating impacts of large wind farms on power generation and air-sea fluxes. Specifically, we examined the effects of replacing 5 MW turbines with larger 15 MW turbines while maintaining total capacity. Our study found that substituting 15 MW turbines increases the capacity factor by 2-3%, enhancing efficiency. However, these turbines exhibit a slightly smaller impact on 10 m wind speed (1.2-1.5%) and near-surface kinetic energy (0.1-0.2%), leading to reduced effects on sea surface heat fluxes compared to 5 MW turbines. This was confirmed by a stronger reduction in net heat flux of about 0.6-1.3% in simulations with 5 MW compared to 15 MW wind turbines. Air-sea fluxes influence ocean dynamics and marine ecosystems; therefore, minimizing these impacts is crucial. Overall, deploying 15 MW turbines in offshore wind farms may offer advantages for ocean dynamics and marine ecosystems, supporting the EU's carbon-neutral objectives.

Association between HDL levels and stroke outcomes in the Arab population.

Low HDL levels are associated with an increased stroke incidence and worsened long-term outcomes. The aim of this study was to assess the relationship between HDL levels and long-term stroke outcomes in the Arab population. Patients admitted to the Qatar Stroke Database between 2014 and 2022 were included in the study and stratified into sex-specific HDL quartiles. Long-term outcomes included 90-Day modified Rankin Score (mRS), stroke recurrence, and post-stroke cardiovascular complications within 1 year of discharge. Multivariate binary logistic regression analyses were performed to identify the independent effect of HDL levels on short- and long-term outcomes. On multivariate binary logistic regression analyses, 1-year stroke recurrence was 2.24 times higher (p = 0.034) and MACE was 1.99 times higher (p = 0.009) in the low-HDL compared to the high-HDL group. Mortality at 1 year was 2.27-fold in the low-normal HDL group compared to the reference group (p = 0.049). Lower sex-specific HDL levels were independently associated with higher adjusted odds of 1-year post-stroke mortality, stroke recurrence, and MACE (p < 0.05). In patients who suffer a stroke, low HDL levels are associated with a higher risk of subsequent vascular complication.

Spontaneous triple vessel cervicocephalic artery dissection in a young gentleman: A case report.

INTRODUCTION: Cervicocephalic arterial dissections (CADs) occur in 3 cases per 100,000 individuals across all ages. Multiple simultaneous CADs are found in 13 to 22% of cases, and three or more dissections occur in approximately 2%. CADs might result from multifactorial intrinsic deficiencies of vessel wall integrity and extrinsic factors, e.g., minor trauma. CASE PRESENTATION: A young gentleman presented to the emergency department with a sudden onset of a spinning sensation of surrounding, left side arm weakness, blurring of vision, and an NIHSS score of 4. An urgent CT scan of the head and intracranial angiogram showed bilateral severe stenosis of the distal cervical segment of internal carotid arteries (ICAs) and right vertebral artery moderate stenosis at the V2 segment. He had been given IV TPA (Alteplase) within the 4.5-hour window. After 4 hours, the patient's GCS dropped from 15 to 10, and the NIHSS score increased from 4 to 24, followed by witnessed a generalized tonic-clonic seizure. Repeat urgent CT head showed no evidence of intracerebral hemorrhage (ICH). The patient was arranged for cerebral angiographic catheterization that showed bilateral flame-shaped occlusion of cervical ICA dissection. There is a mild focal narrowing of the right cervical vertebral artery, likely dissection. Routine laboratory blood workup for vasculitis was negative. During MICU admission, he had witnessed the right arm hemichorea-ballism spectrum abnormal movement. After the 6th-month follow-up, intracranial CT angiogram showed reduced caliber of the bilateral distal cervical course of the internal carotid arteries seen with residual dissection and focal outpouching of the right ICA representing pseudoaneurysm. DISCUSSION: The occurrence of multiple CADs suggests the presence of an underlying intrinsic arteriopathy, such as FMD, the presence of pseudoaneurysm, environmental triggers, cervical manipulation, and remote history of head or neck surgery. A study of the most extensive case series of patients with cervical artery dissection showed 15.2% of patients with multiple CAD. In most patients with multiple cervical artery dissections, antithrombotic treatment is effective, complete recanalization, and the outcome is favorable. Outside the window period of acute ischemic stroke, either anticoagulation or antiplatelet therapy is a recognized treatment for secondary ischemic stroke prevention due to extracranial artery dissection. For acute stroke or TIA patients caused by intracranial artery dissection, experts recommend antiplatelet therapy rather than anticoagulation. CONCLUSION: Simultaneous triple-vessel cervicocephalic arterial dissections are rarely reported condition. Multiple CADs are associated with underlying vasculopathy and environmental triggers, and a majority are recanalized with antithrombotic treatment with favorable outcomes. Antithrombotic treatment is effective in most patients with multiple CADs, and most expect complete recanalization. This case report guides physicians in the treatment and outcome of acute stroke due to multiple CAD.

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.

Stroke and high-risk TIA outcomes with reduction of treatment duration when treatment initiated in emergency rooms (SHORTER-study).

BACKGROUND: Following transient ischemic attack (TIA) and minor stroke, the risk of recurrent stroke can be significantly reduced with short-duration dual antiplatelet therapy (DAPT). We wish to investigate whether 10 days of DAPT is as effective as 21 days' treatment. STUDY DESIGN: This is an open-label, randomized, parallel-group study comparing whether 10 days of DAPT treatment (ASA + clopidogrel) is non-inferior to 21 days of DAPT in patients with acute ischemic stroke (AIS) or high-risk TIA. In both groups, DAPT is started within 24 hours of symptom onset. This study is being conducted in approximately 15 study sites in the Kingdom of Saudi Arabia. The planned sample size is 1932. OUTCOMES: Non-inferiority of 10 days compared to 21 days of DAPT in the prevention of the composite endpoint of stroke and death at 90 days in AIS/TIA patients. The primary safety outcome is major intra-cranial and systemic hemorrhage. STUDY PERIOD: Enrolment started in the second quarter of 2023, and the completion of the study is expected in the fourth quarter of 2025. DISCUSSION: The trial is expected to show that 10 days of DAPT is non-inferior for the prevention of early recurrence of vascular events in patients with high-risk TIAs and minor strokes.

Tocopherol succinate-loaded ethosomal gel synthesized by cold method technique: Deeper biophysical characterizations for translational application on human skin.

BACKGROUND: Tocopherols are well-known antioxidant and moisturizing agent. Tocopherol succinate (TS) are widely used in many skin products especially used in anti-aging and skin whitening product formulation. AIM: We previously reported the successful synthesis and preliminary characterizations of stable TS ethosomal gels (TSEG) (DOI: 10.1111/jocd.14907). Herein, we develop and further characterize TSEG to enhance the stability of the developed formulation with increased permeation through skin. METHODS: Cold method technique was used to prepare TS ethosomes. The developed ethosomal vesicle size was 250 nm, which allowed TS to penetrate through the stratum corneum layer and act on melanocytes. For stability study was assessed by thermogravimetric analysis (TGA) by placing TSEG and unloaded/control ethosomal gel (CEG) at various temperature conditions, that is, 8°C, 25°C, 40°C, and 40°C ± 75% RH for 3 months. Organoleptic evaluation was done in terms of color, odor, and phase separation. Transmission electron microscopy (TEM), Fourier Transform infrared spectroscopy (FTIR), x-ray diffraction spectroscopy (XRD), zeta potential (ZP) and particle size (PS) was used for TSEG physical characterizations. In vitro dissolution and ex-vivo permeation studies (using Franz diffusion cell) were performed for both TSEG and CEG formulations. Human women (N = 34) were used to evaluate in vivo biophysical parameters including erythema, melanin, moisture content, sebum level, and skin elasticity. RESULTS: Developed formulation was highly thermostable during the 3 months. Erythema, melanin, and sebum level decreased while marked improvement (p < 0.05) in moisture content and elasticity have been observed for the developed TSEG. CONCLUSION: The developed TSEG formulation was found to be efficient, safe (no adverse effects observed), stable (at least for 3 months), and easy to use for topical application with improved skin complexation and skin integrity.

Screening of hepatitis B and C viral infection, recognition of risk factors, and immunization of patients against hepatitis B virus: a module developed for effective hepatitis control.

Introduction: The continually increasing incidence of hepatitis, a worldwide health issue, in Pakistan, has highlighted the need to investigate the epidemiology factors and implement preventive measures accordingly. The purpose of this study was to scrutinize the prevalent and significantly associated risk factors of hepatitis in students and employees, screening them for hepatitis B and C virus and vaccinating them against HBV to make IUB hepatitis free. Methodology: A total of 12,912 participants including students (n = 10,948) and employees (n = 1964) were screened for HBV and HCV via immunochromatographic test. Hepatitis- positive participants' blood samples were further tested and viral load was estimated by quantitative PCR. All the hepatitis-negative participants were vaccinated against HBV. The demographic and risk factors-related data were collected using the questionnaire. Statistical analysis (Chi-square test and bivariate regression analysis) was performed using SPSS software to explore any association between risk factors and hepatitis. Results: Results indicated that 662/12912 participants (students = 478/10,948, employees = 184/1,964) tested positive for hepatitis. Among them, HCV was observed to be more prevalent than HBV among the study participants, employees, and students, and viral count was low in both HBV and HCV-infected participants. However, men were more affected than women. The studied risk factors represented higher frequency among hepatitis-positive participants relative to the hepatitis-negative participants. The Chi-square test revealed that students' gender, history of hepatitis in the family and relatives, dental treatment, sharing cosmetics and shaving blades were significant (p > 0.005) risk factors of hepatitis while in the employees group surgery and age were significant. Moreover, the reused of syringes was found to be associated with hepatitis in both groups. The bivariate analysis helped to identify various new risk factors which were independently, either positively or negatively, associated with hepatitis. Discussion: Our study enabled us to recognize different risk factors of hepatitis among the target population. The information thus generated can be usefully applied in planning hepatitis awareness, targeted screening, and effective control programs for other target populations. In general, this module can be further utilized for any other disease.

Gauging Quince Phytonutrients and Its 4% Emulgel Effect on Amplifying Facial Skin Moisturizing Potential.

BACKGROUND: The aim of this study was to evaluate the moisturizing efficacy of quince fruit, used in folk medicine. For this purpose, the phytoconstituents of Cydonia oblonga fruit extract, like phenolics and flavonoids, were determined. A stable cosmetic emulgel containing 4% Cydonia oblonga fresh fruit extract was formulated and subjected to in vivo evaluation compared with a control. MATERIALS AND METHODS: Cydonia oblonga fresh fruit extract was evaluated for tyrosinase activity and phenolic and flavonoid content. A stable emulgel containing 4% Cydonia oblonga fresh fruit extract was formulated and tested in a skin irritation test. After this, in vivo tests of erythema, moisture, sebum, and skin elasticity were conducted. The in vivo evaluation was a randomized and single-blind study. Thirteen healthy female volunteers were selected for a three-month study period. RESULTS: Cydonia oblonga fruit extract showed good phenolic and flavonoid content, which was associated with its good antioxidant and tyrosinase-inhibiting activity. Cydonia oblonga containing the emulgel showed a reduction in sebum and erythema, while the elasticity and moisture content showed increments in their levels after the three-month application of the formulation. The fruit contains chlorogenic acid and many sugars, which might account for its anti-inflammatory and sebum reduction effects; it is also capable of enhancing the skin's hydration level and decreasing skin sagging by enhancing its elasticity. CONCLUSION: The emulgel loaded with Cydonia oblonga fresh fruit extract is verified regarding its folklore status as a moisturizing agent that enhances the facial skin cells' resilience potential.

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.

Appropriate use of antiplatelet medications following transient ischemic attacks and stroke: a 9-year study from the Middle East.

Background and purpose: Guidelines recommend that patients with high-risk TIAs and minor strokes presenting within 1-3 days from onset should be offered dual antiplatelet therapy (DAPT). There are little data on real-world adherence to these recommendations. We evaluated the appropriateness of DAPT use in TIA and stroke patients in a prospective database. Methods: The Qatar Stroke Database began the enrollment of patients with TIAs and acute stroke in 2014 and currently has ~16,000 patients. For this study, we evaluated the rates of guideline-adherent use of antiplatelet treatment at the time of discharge in patients with TIAs and stroke. TIAs were considered high-risk with an ABCD2 score of 4, and a minor stroke was defined as an NIHSS of 3. Patient demographics, clinical features, risk factors, previous medications, imaging and laboratory investigations, final diagnosis, discharge medications, and discharge and 90-day modified Rankin Scale (mRS) were analyzed. Results: After excluding patients with ICH, mimics, and rare secondary causes, 8,082 patients were available for final analysis (TIAs: 1,357 and stroke: 6,725). In high-risk TIAs, 282 of 666 (42.3%) patients were discharged on DAPT. In patients with minor strokes, 1,207 of 3,572 (33.8%) patients were discharged on DAPT. DAPT was inappropriately offered to 238 of 691 (34.4%) low-risk TIAs and 809 of 3,153 (25.7%) non-minor stroke patients. Conclusion: This large database of prospectively collected patients with TIAs and stroke shows that, unfortunately, despite several guidelines, a large majority of patients with TIAs and stroke are receiving inappropriate antiplatelet treatment at discharge from the hospital. This requires urgent attention and further investigation.

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.

Corneal immune cells as a biomarker of inflammation in multiple sclerosis: a longitudinal study.

Background: Corneal immune cells (ICs) are antigen-presenting cells that are known to increase ocular and systemic inflammatory conditions. Objective: We aimed to assess longitudinal changes in corneal IC in patients with multiple sclerosis (MS) and relation to disability and ongoing treatment. Design: Prospective observational study conducted between September 2016 and February 2020. Methods: Patients with relapsing-remitting MS (RRMS) (n = 45) or secondary progressive MS (SPMS) (n = 15) underwent corneal confocal microscopy (CCM) at baseline and 2-year follow-up for estimation of corneal IC density [dendritic cells with (DCF) (cells/mm2) or without nerve fiber contact (DCP); and non-dendritic cells with (NCF) or without nerve fiber contact (NCP)]. Optical coherence tomography, neuroimaging, and disability assessments were additionally performed. Healthy controls (n = 20) were assessed at baseline. Results: In both RRMS and SPMS compared to controls, DCP (p < 0.001 and p < 0.001, respectively) and DCF (p < 0.001 and p = 0.005) were higher and NCF (p = 0.007 and p = 0.02) was lower at baseline. DCP showed excellent performance in identifying patients with MS (sensitivity/specificity = 0.88/0.90) followed by DCF (0.80/0.75) and NCF (0.80/0.85). At follow-up compared to baseline, DCP (p = 0.01) was significantly reduced, and NCP (p = 0.004) and NCF (p = 0.04) were increased. Subgroup analysis showed that baseline NCP and NCF were significantly higher (p = 0.04-0.05) in patients who switched disease-modifying treatment, and baseline NCP (p = 0.05) was higher in patients on interferon. Conclusion: Baseline and change in corneal IC were related to axonal degeneration and treatment status. Evaluation of corneal IC using CCM may allow an assessment of ongoing inflammation, disease progression, and the effect of treatment in MS.