Materiały źródłowe

• #1 Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-Parametric Feature Embedded Siamese Network

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7690444/

  Stroke is the second leading cause of death and disability worldwide, with ischemic stroke as the most common type. […] The preferred diagnostic procedure at the acute stage involves the acquisition of multi-parametric magnetic resonance imaging (MRI). […] The success of the intervention is assessed via the standardized thrombolysis in cerebral infarction (TICI) grading system. […] The problem of predicting the clinical outcome of treated patients is shown in Figure 1. […] Clinical outcome prediction in treated patients is complex because it involves various clinical and imaging biomarkers. […] Recent machine learning techniques, such as deep learning, have been used in the field of cerebrovascular disorders and have the potential to solve the important problem of outcome prediction in acute ischemic stroke.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] Despite the substantial body of literature addressing short-, intermediate, and long-term stroke outcome predictions, there has been notably limited research into forecasting the outcomes and functional prognosis after thrombolytic treatment. […] Machine learning algorithms have recently been employed to forecast stroke outcomes and prognosis, demonstrating comparable or superior effectiveness to conventional methods like logistic regression. […] The primary motive behind this study is to harness the predictive capabilities of machine learning to uncover meaningful and actionable connections between various study variables and their impact on patient outcomes. By doing so, we empower clinicians in Qatar and similar settings with a robust tool for crafting individualized care plans tailored to the unique context of their patients. Specifically, our study aims to construct a machine learning model to predict the prognostic outcomes of thrombolytic (fibrinolytic) treatment. This model will delve into the multitude of factors influencing the prognosis as measured by the 90-day mRS after discharge for patients who undergo thrombolysis for ischemic stroke.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] The pre-stroke modified Rankin Score (mRS) plays a pivotal role in predicting the prognosis of individuals with IS who underwent thrombolysis. […] The occurrence of hospital-acquired UTI emerges as a robust predictor of an adverse stroke prognosis. Stroke patients are recognized to be highly vulnerable to infections during their hospital stay, which can negatively impact their functional recovery. […] It is crucial to emphasize that, except for hospital-acquired UTI, all the discussed predictors function as early indicators (at admission) for forecasting the prognosis of ischemic stroke in patients who have undergone thrombolysis, enhancing this study’s significance. Early prediction of the disease and treatment outcomes holds profound importance as it equips clinicians with the tools to craft individualized care strategies addressing the pivotal factors contributing to adverse outcomes, ultimately elevating the quality of life for stroke patients.

• #4 Overview of ischemic stroke prognosis in adults – UpToDate

  https://www.uptodate.com/contents/overview-of-ischemic-stroke-prognosis-in-adults

  Overview of ischemic stroke prognosis in adults […] Clinicians are often asked to predict outcome after stroke by the patient, family, other healthcare workers, and insurance providers. A wide variety of factors influence stroke prognosis, including age, stroke severity, stroke mechanism, infarct location, comorbid conditions, clinical findings, and related complications. […] In addition, interventions such as thrombolysis, mechanical thrombectomy, stroke unit care, and rehabilitation can play a major role in the outcome of ischemic stroke. Knowledge of the important factors that affect prognosis is necessary for the clinician to make a reasonable prediction for individual patients, to provide a rational approach to patient management, and to help the patient and family understand the course of the disease. […] This topic will review the factors that affect stroke prognosis, with a focus on the acute phase of ischemic stroke. The major medical and neurologic complications of acute stroke are discussed separately. […] The prognosis for individual stroke subtypes is also discussed in the following topics:

• #5 Machine learning for early dynamic prediction of functional outcome after stroke | Communications Medicine

  https://www.nature.com/articles/s43856-024-00666-w

  Prediction of outcome after stroke is critical for treatment planning and resource allocation but is complicated by fluctuations during the first days after onset. […] Our transformer model predicts mortality, with an area under the receiver operating characteristic curve of 0.830 (95% CI 0.7630.885) on admission, reaching 0.893 (95% CI 0.8390.933) 72h later for a 3-month outcome. […] The performance of our transformer model demonstrates the potential of machine learning models integrating clinical, physiological, imaging, and biological variables over time after stroke. […] To determine the best treatment and allocate resources, an early and accurate prediction of outcome is essential. […] Our model was able to provide accurate hourly prediction of outcome based on regularly updated clinical data obtained from the patient.

• #6 Predictions for functional outcome and mortality in acute ischaemic stroke following successful endovascular thrombectomy | BMJ Neurology Open

  https://neurologyopen.bmj.com/content/6/1/e000707

  Accurate outcome predictions for patients who had ischaemic stroke with successful reperfusion after endovascular thrombectomy (EVT) may improve patient treatment and care. Our study developed prediction models for key clinical outcomes in patients with successful reperfusion following EVT in an Australian population. […] Predictors associated with one or more poor outcomes include: older age, higher premorbid functional modified Rankin Scale, higher baseline National Institutes of Health Stroke Scale score, higher blood glucose, larger core volume, pre-EVT thrombolytic therapy, history of heart failure, interhospital transfer, non-rural/regional stroke onset, longer onset-to-groin puncture time and atherosclerosis-caused stroke. […] Our models using real-world predictors assessed at hospital admission showed satisfactory performance in predicting poor functional outcomes and short-term and long-term mortality for patients with successful reperfusion following EVT.

• #7 Predicting 3-month poor functional outcomes of acute ischemic stroke in young patients using machine learning | European Journal of Medical Research | Full Text

  https://eurjmedres.biomedcentral.com/articles/10.1186/s40001-024-02056-3

  Prediction of short-term outcomes in young patients with acute ischemic stroke (AIS) may assist in making therapy decisions. […] This study aims to use a ML-based predictive model for poor 3-month functional outcomes in young AIS patients and to compare the predictive performance of ML models with the logistic regression model. […] The mRS at admission, living alone conditions, and high National Institutes of Health Stroke Scale (NIHSS) at discharge remained independent predictors of poor 3-month outcomes. […] ML outperformed logistic regression, where XGBoost the boost was the best model for predicting poor functional outcomes in young AIS patients. It is important to consider living alone conditions with high severity scores to improve stroke prognosis. […] In 2268 young patients, poor functional outcome was significantly associated with a high mRS score at admission, living alone conditions, and a high NIHSS score at discharge. […] ML is superior to logistic regression, with XGBoost being the best model. […] Our results suggest that employing ML methods particularly XGBoost may improve upon conventional logistic regression models in identifying young stroke patients at risk of poor functional outcomes within 3 months.

• #8 Random forest-based prediction of stroke outcome | Scientific Reports

  https://www.nature.com/articles/s41598-021-89434-7

  Taking into account the prevalence of cerebrovascular diseases, accurately predicting stroke evolution is essential to stratify the rehabilitation care that should be administered, especially to patients with the best chance of recovery. […] We hypothesized that models developed with ML techniques based on the demographic, clinical, biochemical and neuroimaging variables obtained in the first 48 h after stroke are accurate stroke mortality and morbidity predictors at 3 months. […] The model indicates that the most relevant variables are NIHSS (48) and NIHSS (24). […] The rest of the variables provide information marginally, although the importance of T(0) and ED should not be disregarded. […] The findings in this report are subject to at least four limitations. […] In our study, we analyzed a ML model of stroke prediction at 3 months using the Hospitals Stroke Registry (BICHUS) on the basis of demographic, clinical, molecular and neuroimaging variables. […] Machine learning algorithms, particularly Random Forest, can be effectively used in long-term outcome prediction of mortality and morbidity of stroke patients.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] The pre-stroke modified Rankin Score (mRS) plays a pivotal role in predicting the prognosis of individuals with IS who underwent thrombolysis. […] The occurrence of hospital-acquired UTI emerges as a robust predictor of an adverse stroke prognosis. Stroke patients are recognized to be highly vulnerable to infections during their hospital stay, which can negatively impact their functional recovery. […] It is crucial to emphasize that, except for hospital-acquired UTI, all the discussed predictors function as early indicators (at admission) for forecasting the prognosis of ischemic stroke in patients who have undergone thrombolysis, enhancing this study’s significance. Early prediction of the disease and treatment outcomes holds profound importance as it equips clinicians with the tools to craft individualized care strategies addressing the pivotal factors contributing to adverse outcomes, ultimately elevating the quality of life for stroke patients.

• #10 Overview of ischemic stroke prognosis in adults – UpToDate

  https://www.uptodate.com/contents/overview-of-ischemic-stroke-prognosis-in-adults

  Overview of ischemic stroke prognosis in adults […] Clinicians are often asked to predict outcome after stroke by the patient, family, other healthcare workers, and insurance providers. A wide variety of factors influence stroke prognosis, including age, stroke severity, stroke mechanism, infarct location, comorbid conditions, clinical findings, and related complications. […] In addition, interventions such as thrombolysis, mechanical thrombectomy, stroke unit care, and rehabilitation can play a major role in the outcome of ischemic stroke. Knowledge of the important factors that affect prognosis is necessary for the clinician to make a reasonable prediction for individual patients, to provide a rational approach to patient management, and to help the patient and family understand the course of the disease. […] This topic will review the factors that affect stroke prognosis, with a focus on the acute phase of ischemic stroke. The major medical and neurologic complications of acute stroke are discussed separately. […] The prognosis for individual stroke subtypes is also discussed in the following topics:

• #11

  https://link.springer.com/article/10.1007/s13534-025-00462-y

  Stroke is a major global health problem that causes mortality and morbidity. Predicting the outcomes of stroke intervention can facilitate clinical decision-making and improve patient care. […] The outcome for stroke patients is influenced by a number of factors, including the type, location and size of the stroke, the time elapsed before treatment and the rehabilitation interventions received. […] Consequently, developing an automated tool that uses available imaging and patient information to predict treatment outcomes would improve clinical decision-making and the efficacy of ischaemic stroke treatment. […] The early prediction of stroke outcome and delivery of the appropriate treatment is critical since the ischaemic penumbra, the region of brain tissue surrounding the infarct that can still be saved, has a limited window for successful intervention.

• #12 Stroke outcome prediction: new opportunities from Clinical Neurophysiology – European Stroke Organisation

  https://eso-stroke.org/stroke-outcome-prediction-new-opportunities-from-clinical-neurophysiology/

  In daily clinical practice, it is common experience to be asked to formulate a stroke prognosis soon after the index event. The strongest stroke outcome predictor is clinical severity, while other additional predictors of outcome are age, infarct volume and location, aetiology, revascularization treatment and comorbidities. Nevertheless, even if all the mentioned stroke outcome predictors are taken into account, it is easy to make mistakes. […] In a recently published study, Greve and Colleagues described that upper limb MEPs recovery during mechanical thrombectomy can predict three-months clinical outcomes. […] Moreover, MEP recovery was associated to small infarcts sparing the motor pathways descending from primary motor cortex. […] It has been demonstrated that acute ischemic stroke changes the network signature for each band and these modifications can predict functional outcome.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  The SHAP analysis yielded invaluable and pivotal insights for forecasting functional outcomes (mRS90). In this context, the crucial factors, ranked by importance, are stroke severity upon presentation (measured by NIHSS), pre-stroke mRS, RBS, SBP, DBP, HTN, CAD, SUO, and UTI. Higher values of NIHSS at admission and pre-stroke mRS scores were positively correlated with unfavorable outcomes, underscoring the impact of initial neurological impairment. […] Importantly, the identified key predictors, apart from hospital-acquired UTI, can serve as early indicators of an unfavorable prognosis, as they can be assessed upon admission. As a result, this research has the potential to enhance clinicians’ ability to predict the prognosis of IS patients undergoing prompt thrombolysis and tailor care strategies to address prognosis risk.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  The SHAP analysis yielded invaluable and pivotal insights for forecasting functional outcomes (mRS90). In this context, the crucial factors, ranked by importance, are stroke severity upon presentation (measured by NIHSS), pre-stroke mRS, RBS, SBP, DBP, HTN, CAD, SUO, and UTI. Higher values of NIHSS at admission and pre-stroke mRS scores were positively correlated with unfavorable outcomes, underscoring the impact of initial neurological impairment. […] Importantly, the identified key predictors, apart from hospital-acquired UTI, can serve as early indicators of an unfavorable prognosis, as they can be assessed upon admission. As a result, this research has the potential to enhance clinicians’ ability to predict the prognosis of IS patients undergoing prompt thrombolysis and tailor care strategies to address prognosis risk.

• #15 Predictions for functional outcome and mortality in acute ischaemic stroke following successful endovascular thrombectomy | BMJ Neurology Open

  https://neurologyopen.bmj.com/content/6/1/e000707

  Accurate outcome predictions for patients who had ischaemic stroke with successful reperfusion after endovascular thrombectomy (EVT) may improve patient treatment and care. Our study developed prediction models for key clinical outcomes in patients with successful reperfusion following EVT in an Australian population. […] Predictors associated with one or more poor outcomes include: older age, higher premorbid functional modified Rankin Scale, higher baseline National Institutes of Health Stroke Scale score, higher blood glucose, larger core volume, pre-EVT thrombolytic therapy, history of heart failure, interhospital transfer, non-rural/regional stroke onset, longer onset-to-groin puncture time and atherosclerosis-caused stroke. […] Our models using real-world predictors assessed at hospital admission showed satisfactory performance in predicting poor functional outcomes and short-term and long-term mortality for patients with successful reperfusion following EVT.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  The SHAP analysis yielded invaluable and pivotal insights for forecasting functional outcomes (mRS90). In this context, the crucial factors, ranked by importance, are stroke severity upon presentation (measured by NIHSS), pre-stroke mRS, RBS, SBP, DBP, HTN, CAD, SUO, and UTI. Higher values of NIHSS at admission and pre-stroke mRS scores were positively correlated with unfavorable outcomes, underscoring the impact of initial neurological impairment. […] Importantly, the identified key predictors, apart from hospital-acquired UTI, can serve as early indicators of an unfavorable prognosis, as they can be assessed upon admission. As a result, this research has the potential to enhance clinicians’ ability to predict the prognosis of IS patients undergoing prompt thrombolysis and tailor care strategies to address prognosis risk.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  The SHAP analysis yielded invaluable and pivotal insights for forecasting functional outcomes (mRS90). In this context, the crucial factors, ranked by importance, are stroke severity upon presentation (measured by NIHSS), pre-stroke mRS, RBS, SBP, DBP, HTN, CAD, SUO, and UTI. Higher values of NIHSS at admission and pre-stroke mRS scores were positively correlated with unfavorable outcomes, underscoring the impact of initial neurological impairment. […] Importantly, the identified key predictors, apart from hospital-acquired UTI, can serve as early indicators of an unfavorable prognosis, as they can be assessed upon admission. As a result, this research has the potential to enhance clinicians’ ability to predict the prognosis of IS patients undergoing prompt thrombolysis and tailor care strategies to address prognosis risk.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  (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. […] (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.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  (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. […] (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.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  (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. […] (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.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] The pre-stroke modified Rankin Score (mRS) plays a pivotal role in predicting the prognosis of individuals with IS who underwent thrombolysis. […] The occurrence of hospital-acquired UTI emerges as a robust predictor of an adverse stroke prognosis. Stroke patients are recognized to be highly vulnerable to infections during their hospital stay, which can negatively impact their functional recovery. […] It is crucial to emphasize that, except for hospital-acquired UTI, all the discussed predictors function as early indicators (at admission) for forecasting the prognosis of ischemic stroke in patients who have undergone thrombolysis, enhancing this study’s significance. Early prediction of the disease and treatment outcomes holds profound importance as it equips clinicians with the tools to craft individualized care strategies addressing the pivotal factors contributing to adverse outcomes, ultimately elevating the quality of life for stroke patients.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  The SHAP analysis yielded invaluable and pivotal insights for forecasting functional outcomes (mRS90). In this context, the crucial factors, ranked by importance, are stroke severity upon presentation (measured by NIHSS), pre-stroke mRS, RBS, SBP, DBP, HTN, CAD, SUO, and UTI. Higher values of NIHSS at admission and pre-stroke mRS scores were positively correlated with unfavorable outcomes, underscoring the impact of initial neurological impairment. […] Importantly, the identified key predictors, apart from hospital-acquired UTI, can serve as early indicators of an unfavorable prognosis, as they can be assessed upon admission. As a result, this research has the potential to enhance clinicians’ ability to predict the prognosis of IS patients undergoing prompt thrombolysis and tailor care strategies to address prognosis risk.

• #23 Role of some inflammatory biomarkers in prediction of short-term outcome in acute ischemic stroke | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery | Full Text

  https://ejnpn.springeropen.com/articles/10.1186/s41983-021-00294-4

  Accurate identification of stroke outcome predictors might help ideal beginning time for immediate intervention and management. […] Identification of the relationship between short-term outcomes of ischemic stroke and inflammatory biomarkers such as WBC, NLR, and CRP might aid in supporting that anti-inflammatory therapy might be a potential treatment for AIS. […] Higher NIHSS showed a high significant association with the patient unfavorable outcomes. […] Concerning NLR as a good predictor of short-term outcomes in the AIS patients, our study showed that 74.4% of the AIS patients with high (3) NLR was found to have unfavorable outcomes. […] There was a significant association between patient unfavorable outcomes and elevation of admission CRP. […] The most independent factors of unfavorable outcomes of ischemic stroke in our study were higher NIHSS, higher WBC count, higher NLR, and higher CRP.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] The pre-stroke modified Rankin Score (mRS) plays a pivotal role in predicting the prognosis of individuals with IS who underwent thrombolysis. […] The occurrence of hospital-acquired UTI emerges as a robust predictor of an adverse stroke prognosis. Stroke patients are recognized to be highly vulnerable to infections during their hospital stay, which can negatively impact their functional recovery. […] It is crucial to emphasize that, except for hospital-acquired UTI, all the discussed predictors function as early indicators (at admission) for forecasting the prognosis of ischemic stroke in patients who have undergone thrombolysis, enhancing this study’s significance. Early prediction of the disease and treatment outcomes holds profound importance as it equips clinicians with the tools to craft individualized care strategies addressing the pivotal factors contributing to adverse outcomes, ultimately elevating the quality of life for stroke patients.

• #25 Role of some inflammatory biomarkers in prediction of short-term outcome in acute ischemic stroke | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery | Full Text

  https://ejnpn.springeropen.com/articles/10.1186/s41983-021-00294-4

  The higher the biomarkers (total WBCs, NLR, and the level of CRP) at the onset of AIS, the poorer the short-term outcomes are expected. […] We recommend using inflammatory blood biomarkers such as total WBC count, NLR values, and CRP values in predicting the short-term outcomes of acute ischemic stroke patients.

• #26 Role of some inflammatory biomarkers in prediction of short-term outcome in acute ischemic stroke | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery | Full Text

  https://ejnpn.springeropen.com/articles/10.1186/s41983-021-00294-4

  Accurate identification of stroke outcome predictors might help ideal beginning time for immediate intervention and management. […] Identification of the relationship between short-term outcomes of ischemic stroke and inflammatory biomarkers such as WBC, NLR, and CRP might aid in supporting that anti-inflammatory therapy might be a potential treatment for AIS. […] Higher NIHSS showed a high significant association with the patient unfavorable outcomes. […] Concerning NLR as a good predictor of short-term outcomes in the AIS patients, our study showed that 74.4% of the AIS patients with high (3) NLR was found to have unfavorable outcomes. […] There was a significant association between patient unfavorable outcomes and elevation of admission CRP. […] The most independent factors of unfavorable outcomes of ischemic stroke in our study were higher NIHSS, higher WBC count, higher NLR, and higher CRP.

• #27 Role of some inflammatory biomarkers in prediction of short-term outcome in acute ischemic stroke | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery | Full Text

  https://ejnpn.springeropen.com/articles/10.1186/s41983-021-00294-4

  Accurate identification of stroke outcome predictors might help ideal beginning time for immediate intervention and management. […] Identification of the relationship between short-term outcomes of ischemic stroke and inflammatory biomarkers such as WBC, NLR, and CRP might aid in supporting that anti-inflammatory therapy might be a potential treatment for AIS. […] Higher NIHSS showed a high significant association with the patient unfavorable outcomes. […] Concerning NLR as a good predictor of short-term outcomes in the AIS patients, our study showed that 74.4% of the AIS patients with high (3) NLR was found to have unfavorable outcomes. […] There was a significant association between patient unfavorable outcomes and elevation of admission CRP. […] The most independent factors of unfavorable outcomes of ischemic stroke in our study were higher NIHSS, higher WBC count, higher NLR, and higher CRP.

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

  https://www.mdpi.com/2075-4426/13/11/1555

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] Despite the substantial body of literature addressing short-, intermediate, and long-term stroke outcome predictions, there has been notably limited research into forecasting the outcomes and functional prognosis after thrombolytic treatment. […] Machine learning algorithms have recently been employed to forecast stroke outcomes and prognosis, demonstrating comparable or superior effectiveness to conventional methods like logistic regression. […] The primary motive behind this study is to harness the predictive capabilities of machine learning to uncover meaningful and actionable connections between various study variables and their impact on patient outcomes. By doing so, we empower clinicians in Qatar and similar settings with a robust tool for crafting individualized care plans tailored to the unique context of their patients. Specifically, our study aims to construct a machine learning model to predict the prognostic outcomes of thrombolytic (fibrinolytic) treatment. This model will delve into the multitude of factors influencing the prognosis as measured by the 90-day mRS after discharge for patients who undergo thrombolysis for ischemic stroke.

• #29 Random forest-based prediction of stroke outcome | Scientific Reports

  https://www.nature.com/articles/s41598-021-89434-7

  We research into the clinical, biochemical and neuroimaging factors associated with the outcome of stroke patients to generate a predictive model using machine learning techniques for prediction of mortality and morbidity 3-months after admission. […] In conclusion, machine learning algorithms RF can be effectively used in stroke patients for long-term outcome prediction of mortality and morbidity. […] Predicting functional outcome after stroke would help clinicians make patient-specific decisions. […] Machine learning (ML) provides a promising tool for disease evolution prediction and it is being increasingly used in biomedical studies. […] It has only been recently, however, that a study evaluated stroke outcome prediction at 3 months also in a group of non-traumatic intracerebral hemorrhage (ICH) patients using a nationwide disease registry.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  (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. […] (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.

• #31

  https://link.springer.com/article/10.1007/s11517-024-03073-4

  Accurately predicting the prognosis of ischemic stroke patients after discharge is crucial for physicians to plan for long-term health care. […] This study aimed to overcome these gaps by utilizing a large national stroke registry database to assess various prediction models that estimate how patients prognosis changes over time with associated clinical factors. […] The study revealed that the XGBoost model outperformed other two traditional models, achieving an AUROC of 0.929 in predicting the prognosis changes of stroke patients followed for 3 months. […] These selected features closely correlated with significant changes in clinical outcomes for stroke patients and showed to be effective for predicting prognosis changes after discharge, allowing physicians to make optimal decisions regarding their patients recovery.

• #32

  https://link.springer.com/article/10.1007/s11517-024-03073-4

  The objective of this study was to identify the best prediction model for the outcome change prognosis at 1-month and 3-month follow-ups with associated clinical features that may promote good outcome changes for stroke patients after discharge. […] The findings of this study will help physicians better understand and plan for their patient recovery and health care management after stroke. […] The ML-based XGboost model significantly outperformed both statistical and clinical score-based models. […] Compared to the clinical score model, statistical (logistic regression) and XGboost models outperformed with AUROCs by approximately 20 to 35%, some with AUROCs over 0.9, which implies its high predictably in outcome prognosis. […] This study clearly demonstrated that the presented ML-based XGboost model can be utilized to predict the long-term outcome changes after ischemic stroke. […] In summary, this study allows physicians to use the predicted results in their clinical practices for planning an optimal personalized care plan aiming for improved recovery.

• #33 Machine learning for early dynamic prediction of functional outcome after stroke | Communications Medicine

  https://www.nature.com/articles/s43856-024-00666-w

  Prediction of outcome after stroke is critical for treatment planning and resource allocation but is complicated by fluctuations during the first days after onset. […] Our transformer model predicts mortality, with an area under the receiver operating characteristic curve of 0.830 (95% CI 0.7630.885) on admission, reaching 0.893 (95% CI 0.8390.933) 72h later for a 3-month outcome. […] The performance of our transformer model demonstrates the potential of machine learning models integrating clinical, physiological, imaging, and biological variables over time after stroke. […] To determine the best treatment and allocate resources, an early and accurate prediction of outcome is essential. […] Our model was able to provide accurate hourly prediction of outcome based on regularly updated clinical data obtained from the patient.

• #34 Machine learning for early dynamic prediction of functional outcome after stroke | Communications Medicine

  https://www.nature.com/articles/s43856-024-00666-w

  We developed a transformer model and compared its performance with other traditional and machine learning algorithms (LSTM and XGB). […] The transformer model achieves a good discriminative performance of high clinical relevance for both in-hospital and 3-month clinical outcomes and outperforms existing static models. […] The model produced an hourly prediction for all outcomes (in-hospital mortality, survival, and functional status at 3 months), continuously updated based on incoming data. […] The highest daily gain in performance was observed within the first 24h of admission. […] The ROC AUC of the model to predict good functional outcome at three months increased from 0.835 (95% CI 0.7950.869) on admission to 0.878 (95% CI 0.8460.908) at 24h and 0.894 (95% CI 0.8630.922) at 72h. […] We have demonstrated that a machine learning model can provide accurate and dynamic prediction of outcome in the acute phase of ischemic stroke.

• #35 Random forest-based prediction of stroke outcome | Scientific Reports

  https://www.nature.com/articles/s41598-021-89434-7

  We research into the clinical, biochemical and neuroimaging factors associated with the outcome of stroke patients to generate a predictive model using machine learning techniques for prediction of mortality and morbidity 3-months after admission. […] In conclusion, machine learning algorithms RF can be effectively used in stroke patients for long-term outcome prediction of mortality and morbidity. […] Predicting functional outcome after stroke would help clinicians make patient-specific decisions. […] Machine learning (ML) provides a promising tool for disease evolution prediction and it is being increasingly used in biomedical studies. […] It has only been recently, however, that a study evaluated stroke outcome prediction at 3 months also in a group of non-traumatic intracerebral hemorrhage (ICH) patients using a nationwide disease registry.

• #36 Random forest-based prediction of stroke outcome | Scientific Reports

  https://www.nature.com/articles/s41598-021-89434-7

  Taking into account the prevalence of cerebrovascular diseases, accurately predicting stroke evolution is essential to stratify the rehabilitation care that should be administered, especially to patients with the best chance of recovery. […] We hypothesized that models developed with ML techniques based on the demographic, clinical, biochemical and neuroimaging variables obtained in the first 48 h after stroke are accurate stroke mortality and morbidity predictors at 3 months. […] The model indicates that the most relevant variables are NIHSS (48) and NIHSS (24). […] The rest of the variables provide information marginally, although the importance of T(0) and ED should not be disregarded. […] The findings in this report are subject to at least four limitations. […] In our study, we analyzed a ML model of stroke prediction at 3 months using the Hospitals Stroke Registry (BICHUS) on the basis of demographic, clinical, molecular and neuroimaging variables. […] Machine learning algorithms, particularly Random Forest, can be effectively used in long-term outcome prediction of mortality and morbidity of stroke patients.

• #37 Predicting 3-month poor functional outcomes of acute ischemic stroke in young patients using machine learning | European Journal of Medical Research | Full Text

  https://eurjmedres.biomedcentral.com/articles/10.1186/s40001-024-02056-3

  Prediction of short-term outcomes in young patients with acute ischemic stroke (AIS) may assist in making therapy decisions. […] This study aims to use a ML-based predictive model for poor 3-month functional outcomes in young AIS patients and to compare the predictive performance of ML models with the logistic regression model. […] The mRS at admission, living alone conditions, and high National Institutes of Health Stroke Scale (NIHSS) at discharge remained independent predictors of poor 3-month outcomes. […] ML outperformed logistic regression, where XGBoost the boost was the best model for predicting poor functional outcomes in young AIS patients. It is important to consider living alone conditions with high severity scores to improve stroke prognosis. […] In 2268 young patients, poor functional outcome was significantly associated with a high mRS score at admission, living alone conditions, and a high NIHSS score at discharge. […] ML is superior to logistic regression, with XGBoost being the best model. […] Our results suggest that employing ML methods particularly XGBoost may improve upon conventional logistic regression models in identifying young stroke patients at risk of poor functional outcomes within 3 months.

• #38 Frontiers | Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission

  https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2024.1330497/full

  Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission. […] In acute ischemic stroke, prediction of the tissue outcome after reperfusion can be used to identify patients that might benefit from mechanical thrombectomy (MT). […] The aim of this work was to develop a deep learning model that can predict the follow-up infarct location and extent exclusively based on acute single-phase computed tomography angiography (CTA) datasets. […] 24-h follow-up infarct prediction using acute CTA imaging exclusively is feasible with DSC measures comparable to results of CTP-based algorithms reported in other studies. […] The proposed method might pave the way to a wider acceptance, feasibility, and applicability of follow-up infarct prediction based on artificial intelligence.

• #39 Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-Parametric Feature Embedded Siamese Network

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7690444/

  Stroke is the second leading cause of death and disability worldwide, with ischemic stroke as the most common type. […] The preferred diagnostic procedure at the acute stage involves the acquisition of multi-parametric magnetic resonance imaging (MRI). […] The success of the intervention is assessed via the standardized thrombolysis in cerebral infarction (TICI) grading system. […] The problem of predicting the clinical outcome of treated patients is shown in Figure 1. […] Clinical outcome prediction in treated patients is complex because it involves various clinical and imaging biomarkers. […] Recent machine learning techniques, such as deep learning, have been used in the field of cerebrovascular disorders and have the potential to solve the important problem of outcome prediction in acute ischemic stroke.

• #40 Frontiers | Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission

  https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2024.1330497/full

  The most important finding of this work is that a prediction of tissue outcome using exclusively CTA datasets is generally feasible using deep convolutional neural networks. […] Test set performance of our models reached an average DSC of 0.35 with mean volume error of 11.5 mL. […] Overall, the predictive performance achieved in this work is within the range of previously described tissue outcome prediction models using more complex 4D CT perfusion datasets. […] Multivariable regression analysis suggest that follow-up infarct volume is associated with functional outcome. […] This work has multiple limitations that should be discussed. […] 24-h follow-up infarct prediction exclusively using acute single-phase CTA datasets is feasible and can be successfully achieved with good accuracy.

• #41 Stroke diagnosis, prediction and treatment monitoring with multiparametric MRI – UMC Utrecht

  https://www.umcutrecht.nl/en/stroke-diagnosis-prediction-and-treatment-monitoring-with-multiparametric-mri

  Multiparametric MRI data of brain tissue status (from maps of cerebral blood flow (CBF), apparent diffusion coefficient (ADC) and mean transit time (MTT)) in different rats with a unilateral ischemic stroke. For model training for outcome prediction, acute MRI data were voxel-wise related to tissue outcome (i.e. infarcted (red) or non-infarcted tissue (blue)) based on follow-up T2 scans or histology. Subsequently a generalized linear model (GLM)-based statistical algorithm estimated a separating plane to differentiate between infarcted and non-infarcted voxels. For tissue outcome prediction in another stroke subject, the distribution pattern of the newly introduced voxel-wise combinations relative to the separating plane can be used to estimate infarction risk (0% Pinfarct 100%). […] Furthermore, we are developing machine learning strategies for tissue classification and outcome prediction based on multiparametric MRI data. These tools, which are also being tested in clinical settings, may help to improve diagnosis and treatment decision making.

• #42 Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-Parametric Feature Embedded Siamese Network

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7690444/

  Machine learning models have been created to predict the outcome after reperfusion therapy using neuroimaging; however, most of these studies focused on the prediction of lesion outcome as compared to clinical outcome. […] This research presents PMFE-SN, an automated end-to-end method for predicting treatment outcome even with less and highly skewed MRI data. […] The developed model helps in reducing bias towards majority class, as well as learning from very few samples, i.e., only two samples for training. […] The major contributions of this research include combining multi-parametric 3D MRI images in an end-to-end deep learning architecture model, development of multi-parametric feature embedding in siamese network for handling scarcity of multi-parametric MRI data, introducing two-stage balancing strategy for solving class imbalance problems and defining evaluation metrics insensitive to imbalance.

• #43 Predicting clinical outcome in posterior circulation large-vessel occlusion patients with endovascular recanalisation: the GNC score | Stroke and Vascular Neurology

  https://svn.bmj.com/content/early/2025/04/30/svn-2025-004131

  Acute ischaemic strokes caused by posterior circulation large-vessel occlusions (pc-LVOs) are associated with particularly poor prognoses, including significant disability and mortality rates. […] Poor outcome was defined as a modified Rankin Scale score of 46 at 90 days. […] The GNC score demonstrated excellent predictive performance for clinical outcome, good discrimination and calibration in this cohort, as well as the bootstrap validation. […] This is the first report that CCT based on DSA is an independent prognostic marker in pc-LVO patients with successful recanalisation post-endovascular treatment. […] The GNC score, incorporating readily available clinical and angiographic parameters, offers a reliable tool for outcome prediction in this high-risk population. […] In this study, we found that cerebral circulation time (CCT) based on quantitative digital subtraction angiography was an independent predictor of clinical outcomes in patients with successful recanalisation.

• #44 Stroke outcome prediction: new opportunities from Clinical Neurophysiology – European Stroke Organisation

  https://eso-stroke.org/stroke-outcome-prediction-new-opportunities-from-clinical-neurophysiology/

  In daily clinical practice, it is common experience to be asked to formulate a stroke prognosis soon after the index event. The strongest stroke outcome predictor is clinical severity, while other additional predictors of outcome are age, infarct volume and location, aetiology, revascularization treatment and comorbidities. Nevertheless, even if all the mentioned stroke outcome predictors are taken into account, it is easy to make mistakes. […] In a recently published study, Greve and Colleagues described that upper limb MEPs recovery during mechanical thrombectomy can predict three-months clinical outcomes. […] Moreover, MEP recovery was associated to small infarcts sparing the motor pathways descending from primary motor cortex. […] It has been demonstrated that acute ischemic stroke changes the network signature for each band and these modifications can predict functional outcome.

• #45 Stroke outcome prediction: new opportunities from Clinical Neurophysiology – European Stroke Organisation

  https://eso-stroke.org/stroke-outcome-prediction-new-opportunities-from-clinical-neurophysiology/

  In daily clinical practice, it is common experience to be asked to formulate a stroke prognosis soon after the index event. The strongest stroke outcome predictor is clinical severity, while other additional predictors of outcome are age, infarct volume and location, aetiology, revascularization treatment and comorbidities. Nevertheless, even if all the mentioned stroke outcome predictors are taken into account, it is easy to make mistakes. […] In a recently published study, Greve and Colleagues described that upper limb MEPs recovery during mechanical thrombectomy can predict three-months clinical outcomes. […] Moreover, MEP recovery was associated to small infarcts sparing the motor pathways descending from primary motor cortex. […] It has been demonstrated that acute ischemic stroke changes the network signature for each band and these modifications can predict functional outcome.

• #46 Stroke outcome prediction: new opportunities from Clinical Neurophysiology – European Stroke Organisation

  https://eso-stroke.org/stroke-outcome-prediction-new-opportunities-from-clinical-neurophysiology/

  In daily clinical practice, it is common experience to be asked to formulate a stroke prognosis soon after the index event. The strongest stroke outcome predictor is clinical severity, while other additional predictors of outcome are age, infarct volume and location, aetiology, revascularization treatment and comorbidities. Nevertheless, even if all the mentioned stroke outcome predictors are taken into account, it is easy to make mistakes. […] In a recently published study, Greve and Colleagues described that upper limb MEPs recovery during mechanical thrombectomy can predict three-months clinical outcomes. […] Moreover, MEP recovery was associated to small infarcts sparing the motor pathways descending from primary motor cortex. […] It has been demonstrated that acute ischemic stroke changes the network signature for each band and these modifications can predict functional outcome.

• #47 Stroke outcome prediction: new opportunities from Clinical Neurophysiology – European Stroke Organisation

  https://eso-stroke.org/stroke-outcome-prediction-new-opportunities-from-clinical-neurophysiology/

  However, several studies have provided evidence that spontaneous movements monitoring of paretic limb using actigraphy can be used to assess and monitor stroke clinical severity in both the acute and the chronic phase. […] This is just an overview on how an old-fashioned but ever extremely creative branch of the Neurosciences can provide a new insight on the difficult task of formulating a reliable stroke prognosis.

• #48 Comparison of outcome prediction models post-stroke for a population-based registry with clinical variables collected at admission vs. discharge

  https://www.oaepublish.com/articles/2574-1209.2020.45

  Aim: The ability to predict outcomes can help clinicians to better triage and treat stroke patients. We aimed to build prediction models using clinical data at admission and discharge to assess predictors highly relevant to stroke outcomes. […] Prediction of clinical outcome after stroke has been proposed and studied as one potential approach to improve stroke care management. […] This study aimed to identify prediction models for functional outcomes following stroke, to appraise these models using current guidelines, and to determine the pooled accuracy of identified models using a well-established national registry. […] The performances (i.e., the area under the curves (AUCs)) of these independent predictors identified by logistic regression (LR) based on clinical variables were compared.

• #49

  https://link.springer.com/article/10.1007/s13534-025-00462-y

  Stroke is a major global health problem that causes mortality and morbidity. Predicting the outcomes of stroke intervention can facilitate clinical decision-making and improve patient care. […] The outcome for stroke patients is influenced by a number of factors, including the type, location and size of the stroke, the time elapsed before treatment and the rehabilitation interventions received. […] Consequently, developing an automated tool that uses available imaging and patient information to predict treatment outcomes would improve clinical decision-making and the efficacy of ischaemic stroke treatment. […] The early prediction of stroke outcome and delivery of the appropriate treatment is critical since the ischaemic penumbra, the region of brain tissue surrounding the infarct that can still be saved, has a limited window for successful intervention.

• #50 PREDICT-juvenile-stroke: PRospective evaluation of a prediction score determining individual clinical outcome three months after ischemic stroke in young adults – a study protocol | BMC Neurology | Full Text

  https://bmcneurol.biomedcentral.com/articles/10.1186/s12883-022-03003-7

  Although of high individual and socioeconomic relevance, a reliable prediction model for the prognosis of juvenile stroke (1855years) is missing. […] The primary endpoint is to validate the clinical potential of the new prediction score for a favourable outcome 3 months after juvenile stroke or TIA. […] The juvenile stroke prediction score has the potential to enable personalisation of counselling, provision of appropriate information regarding the prognosis and identification of patients who benefit from specific treatments. […] The current study is the first that aims to prospectively validate the clinical potential of a prediction score for the 3 months functional outcome after juvenile stroke. This score has the potential to enable personalized patient care, provision of appropriate information regarding the prognosis and the identification of patients who benefit from a specific treatment.

• #51

  https://link.springer.com/article/10.1007/s11517-024-03073-4

  The objective of this study was to identify the best prediction model for the outcome change prognosis at 1-month and 3-month follow-ups with associated clinical features that may promote good outcome changes for stroke patients after discharge. […] The findings of this study will help physicians better understand and plan for their patient recovery and health care management after stroke. […] The ML-based XGboost model significantly outperformed both statistical and clinical score-based models. […] Compared to the clinical score model, statistical (logistic regression) and XGboost models outperformed with AUROCs by approximately 20 to 35%, some with AUROCs over 0.9, which implies its high predictably in outcome prognosis. […] This study clearly demonstrated that the presented ML-based XGboost model can be utilized to predict the long-term outcome changes after ischemic stroke. […] In summary, this study allows physicians to use the predicted results in their clinical practices for planning an optimal personalized care plan aiming for improved recovery.

• #52 Role of some inflammatory biomarkers in prediction of short-term outcome in acute ischemic stroke | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery | Full Text

  https://ejnpn.springeropen.com/articles/10.1186/s41983-021-00294-4

  Accurate identification of stroke outcome predictors might help ideal beginning time for immediate intervention and management. […] Identification of the relationship between short-term outcomes of ischemic stroke and inflammatory biomarkers such as WBC, NLR, and CRP might aid in supporting that anti-inflammatory therapy might be a potential treatment for AIS. […] Higher NIHSS showed a high significant association with the patient unfavorable outcomes. […] Concerning NLR as a good predictor of short-term outcomes in the AIS patients, our study showed that 74.4% of the AIS patients with high (3) NLR was found to have unfavorable outcomes. […] There was a significant association between patient unfavorable outcomes and elevation of admission CRP. […] The most independent factors of unfavorable outcomes of ischemic stroke in our study were higher NIHSS, higher WBC count, higher NLR, and higher CRP.

• #53 Role of some inflammatory biomarkers in prediction of short-term outcome in acute ischemic stroke | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery | Full Text

  https://ejnpn.springeropen.com/articles/10.1186/s41983-021-00294-4

  Accurate identification of stroke outcome predictors might help ideal beginning time for immediate intervention and management. […] Identification of the relationship between short-term outcomes of ischemic stroke and inflammatory biomarkers such as WBC, NLR, and CRP might aid in supporting that anti-inflammatory therapy might be a potential treatment for AIS. […] Higher NIHSS showed a high significant association with the patient unfavorable outcomes. […] Concerning NLR as a good predictor of short-term outcomes in the AIS patients, our study showed that 74.4% of the AIS patients with high (3) NLR was found to have unfavorable outcomes. […] There was a significant association between patient unfavorable outcomes and elevation of admission CRP. […] The most independent factors of unfavorable outcomes of ischemic stroke in our study were higher NIHSS, higher WBC count, higher NLR, and higher CRP.

• #54

  https://journals.lww.com/annals-of-medicine-and-surgery/fulltext/2025/05000/surgical_outcomes_of_isolated_coronary_artery.6.aspx

  Survival is significantly impacted by CABG. If at all possible, it is preferable to improve a patients condition before surgery in order to reduce mortality. The patients chance of survival is impacted by complications including stroke and extended intubation. […] We sought to compare the outcomes of surgery with observed mortality in hospitals, and our data suggested complications such as stroke, arrhythmia, and delayed extubation for any reason had a major impact on mortality in hospitals, as the results indicate. Stroke had a significant P value of 0.000, meaning that out of 7 patients who experienced a CVA attack, 2 of them died in hospital. […] Multiple papers worldwide suggest that stroke alone is a risk factor for mortality, predicting a 2-fold increase in mortality risk compared to those without a stroke this evident especially in first year after surgery.

• #55

  https://journals.lww.com/annals-of-medicine-and-surgery/fulltext/2025/05000/surgical_outcomes_of_isolated_coronary_artery.6.aspx

  Survival is significantly impacted by CABG. If at all possible, it is preferable to improve a patients condition before surgery in order to reduce mortality. The patients chance of survival is impacted by complications including stroke and extended intubation. […] We sought to compare the outcomes of surgery with observed mortality in hospitals, and our data suggested complications such as stroke, arrhythmia, and delayed extubation for any reason had a major impact on mortality in hospitals, as the results indicate. Stroke had a significant P value of 0.000, meaning that out of 7 patients who experienced a CVA attack, 2 of them died in hospital. […] Multiple papers worldwide suggest that stroke alone is a risk factor for mortality, predicting a 2-fold increase in mortality risk compared to those without a stroke this evident especially in first year after surgery.

• #56 Comparison of outcome prediction models post-stroke for a population-based registry with clinical variables collected at admission vs. discharge

  https://www.oaepublish.com/articles/2574-1209.2020.45

  Several outcome prediction models based on different patient subgroups were evaluated, and their AUCs based on all clinical variables at admission and discharge were 0.85-0.88 and 0.92-0.96, respectively. […] This study proposed high performance prognostics outcome prediction models derived from a population-based nationwide stroke registry even with reduced LR-selected clinical features. […] These key clinical features can help physicians to better focus on stroke patients to triage for best outcome in acute settings. […] The performances of stroke outcome prediction models using clinical data in different subgroups of patients at admission and discharge are listed in Table 2. […] The best accuracy increased from 0.82 to 0.90, and the best AUC increased from 0.88 to 0.96. […] Our proposed models achieved significantly better prediction performance than previously reported models.

• #57 Comparison of outcome prediction models post-stroke for a population-based registry with clinical variables collected at admission vs. discharge

  https://www.oaepublish.com/articles/2574-1209.2020.45

  Several outcome prediction models based on different patient subgroups were evaluated, and their AUCs based on all clinical variables at admission and discharge were 0.85-0.88 and 0.92-0.96, respectively. […] This study proposed high performance prognostics outcome prediction models derived from a population-based nationwide stroke registry even with reduced LR-selected clinical features. […] These key clinical features can help physicians to better focus on stroke patients to triage for best outcome in acute settings. […] The performances of stroke outcome prediction models using clinical data in different subgroups of patients at admission and discharge are listed in Table 2. […] The best accuracy increased from 0.82 to 0.90, and the best AUC increased from 0.88 to 0.96. […] Our proposed models achieved significantly better prediction performance than previously reported models.

• #58 Comparison of outcome prediction models post-stroke for a population-based registry with clinical variables collected at admission vs. discharge

  https://www.oaepublish.com/articles/2574-1209.2020.45

  Several outcome prediction models based on different patient subgroups were evaluated, and their AUCs based on all clinical variables at admission and discharge were 0.85-0.88 and 0.92-0.96, respectively. […] This study proposed high performance prognostics outcome prediction models derived from a population-based nationwide stroke registry even with reduced LR-selected clinical features. […] These key clinical features can help physicians to better focus on stroke patients to triage for best outcome in acute settings. […] The performances of stroke outcome prediction models using clinical data in different subgroups of patients at admission and discharge are listed in Table 2. […] The best accuracy increased from 0.82 to 0.90, and the best AUC increased from 0.88 to 0.96. […] Our proposed models achieved significantly better prediction performance than previously reported models.

• #59

  https://link.springer.com/article/10.1007/s13534-025-00462-y

  Recent research shows that DL models can directly analyse raw 4D CTP data to predict stroke lesion outcomes, removing post-processing steps to generate 3D perfusion parameter maps and potentially capturing spatio-temporal information more effectively. […] The studies in this category aim to assess the functional abilities of stroke patients, following intervention, by analysing unimodal and multimodal data to estimate their mRS scores. […] These multimodal (fusion) models capture complementary information from various data sources, that can potentially leading to better performance. […] Early prediction (at one week) of stroke evolution has been found to be critical for predicting the functional outcome after stroke treatment. […] Despite these challenges, several promising avenues for future research are: the development of adaptive multimodal fusion methods that effectively leverage the complementary nature of diverse data sources, the incorporation of longitudinal lesion features, the adoption of federated learning techniques for improved data utilisation, and the exploration of annotation-free lesion labelling methods.

• #60

  https://link.springer.com/article/10.1007/s13534-025-00462-y

  Recent research shows that DL models can directly analyse raw 4D CTP data to predict stroke lesion outcomes, removing post-processing steps to generate 3D perfusion parameter maps and potentially capturing spatio-temporal information more effectively. […] The studies in this category aim to assess the functional abilities of stroke patients, following intervention, by analysing unimodal and multimodal data to estimate their mRS scores. […] These multimodal (fusion) models capture complementary information from various data sources, that can potentially leading to better performance. […] Early prediction (at one week) of stroke evolution has been found to be critical for predicting the functional outcome after stroke treatment. […] Despite these challenges, several promising avenues for future research are: the development of adaptive multimodal fusion methods that effectively leverage the complementary nature of diverse data sources, the incorporation of longitudinal lesion features, the adoption of federated learning techniques for improved data utilisation, and the exploration of annotation-free lesion labelling methods.

• #61

  https://link.springer.com/article/10.1007/s13534-025-00462-y

  Recent research shows that DL models can directly analyse raw 4D CTP data to predict stroke lesion outcomes, removing post-processing steps to generate 3D perfusion parameter maps and potentially capturing spatio-temporal information more effectively. […] The studies in this category aim to assess the functional abilities of stroke patients, following intervention, by analysing unimodal and multimodal data to estimate their mRS scores. […] These multimodal (fusion) models capture complementary information from various data sources, that can potentially leading to better performance. […] Early prediction (at one week) of stroke evolution has been found to be critical for predicting the functional outcome after stroke treatment. […] Despite these challenges, several promising avenues for future research are: the development of adaptive multimodal fusion methods that effectively leverage the complementary nature of diverse data sources, the incorporation of longitudinal lesion features, the adoption of federated learning techniques for improved data utilisation, and the exploration of annotation-free lesion labelling methods.

• #62

  https://link.springer.com/article/10.1007/s13534-025-00462-y

  Recent research shows that DL models can directly analyse raw 4D CTP data to predict stroke lesion outcomes, removing post-processing steps to generate 3D perfusion parameter maps and potentially capturing spatio-temporal information more effectively. […] The studies in this category aim to assess the functional abilities of stroke patients, following intervention, by analysing unimodal and multimodal data to estimate their mRS scores. […] These multimodal (fusion) models capture complementary information from various data sources, that can potentially leading to better performance. […] Early prediction (at one week) of stroke evolution has been found to be critical for predicting the functional outcome after stroke treatment. […] Despite these challenges, several promising avenues for future research are: the development of adaptive multimodal fusion methods that effectively leverage the complementary nature of diverse data sources, the incorporation of longitudinal lesion features, the adoption of federated learning techniques for improved data utilisation, and the exploration of annotation-free lesion labelling methods.

• #63 Improving Stroke Outcome Prediction Using Molecular and Machine Learning Approaches in Large Vessel Occlusion

  https://www.mdpi.com/2077-0383/13/19/5917

  Improving Stroke Outcome Prediction Using Molecular and Machine Learning Approaches in Large Vessel Occlusion […] Predicting stroke outcomes in acute ischemic stroke (AIS) can be challenging, especially for patients with large vessel occlusion (LVO). […] The present study aimed to confirm whether sudden metabolic changes due to blood-brain barrier (BBB) disruption during LVO reflect differences in circulating metabolites and RNA between small and large core strokes. […] The second objective was to evaluate whether integrating molecular markers with existing neurological and imaging tools can enhance outcome predictions in LVO strokes. […] Our study provides a future framework for advancing stroke therapeutics by incorporating molecular markers into the existing neurological and imaging tools to improve predictive efficacy and enhance patient outcomes.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  (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. […] (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.

• #65

  https://link.springer.com/article/10.1007/s11517-024-03073-4

  The objective of this study was to identify the best prediction model for the outcome change prognosis at 1-month and 3-month follow-ups with associated clinical features that may promote good outcome changes for stroke patients after discharge. […] The findings of this study will help physicians better understand and plan for their patient recovery and health care management after stroke. […] The ML-based XGboost model significantly outperformed both statistical and clinical score-based models. […] Compared to the clinical score model, statistical (logistic regression) and XGboost models outperformed with AUROCs by approximately 20 to 35%, some with AUROCs over 0.9, which implies its high predictably in outcome prognosis. […] This study clearly demonstrated that the presented ML-based XGboost model can be utilized to predict the long-term outcome changes after ischemic stroke. […] In summary, this study allows physicians to use the predicted results in their clinical practices for planning an optimal personalized care plan aiming for improved recovery.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  (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. […] (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.

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

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10672468/

  Predicting stroke outcomes is vital in clinical care, and one widely used metric for assessing post-stroke disability and independence is the 90-day modified Rankin Scale (mRS) score after hospital discharge. This scale serves as a crucial tool for evaluating the expected post-stroke outcomes. […] The pre-stroke modified Rankin Score (mRS) plays a pivotal role in predicting the prognosis of individuals with IS who underwent thrombolysis. […] The occurrence of hospital-acquired UTI emerges as a robust predictor of an adverse stroke prognosis. Stroke patients are recognized to be highly vulnerable to infections during their hospital stay, which can negatively impact their functional recovery. […] It is crucial to emphasize that, except for hospital-acquired UTI, all the discussed predictors function as early indicators (at admission) for forecasting the prognosis of ischemic stroke in patients who have undergone thrombolysis, enhancing this study’s significance. Early prediction of the disease and treatment outcomes holds profound importance as it equips clinicians with the tools to craft individualized care strategies addressing the pivotal factors contributing to adverse outcomes, ultimately elevating the quality of life for stroke patients.

• #68

  https://link.springer.com/article/10.1007/s11517-024-03073-4

  The objective of this study was to identify the best prediction model for the outcome change prognosis at 1-month and 3-month follow-ups with associated clinical features that may promote good outcome changes for stroke patients after discharge. […] The findings of this study will help physicians better understand and plan for their patient recovery and health care management after stroke. […] The ML-based XGboost model significantly outperformed both statistical and clinical score-based models. […] Compared to the clinical score model, statistical (logistic regression) and XGboost models outperformed with AUROCs by approximately 20 to 35%, some with AUROCs over 0.9, which implies its high predictably in outcome prognosis. […] This study clearly demonstrated that the presented ML-based XGboost model can be utilized to predict the long-term outcome changes after ischemic stroke. […] In summary, this study allows physicians to use the predicted results in their clinical practices for planning an optimal personalized care plan aiming for improved recovery.

Zobacz więcej