Predicting short and long-term mortality after acute ischemic stroke using EHR

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSION

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

Machine learning-based prognostication of mortality in stroke patients

Objectives

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

Materials and methods

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

Results

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

Conclusions

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

A comprehensive review for artificial intelligence on neuroimaging in rehabilitation of ischemic stroke

Stroke is the second leading cause of death worldwide, with ischemic stroke accounting for a significant proportion of morbidity and mortality among stroke patients. Ischemic stroke often causes disability and cognitive impairment in patients, which seriously affects the quality of life of patients. Therefore, how to predict the recovery of patients can provide support for clinical intervention in advance and improve the enthusiasm of patients for rehabilitation treatment. With the popularization of imaging technology, the diagnosis and treatment of ischemic stroke patients are often accompanied by a large number of imaging data. Through machine learning and Deep Learning, information from imaging data can be used more effectively. In this review, we discuss recent advances in neuroimaging, machine learning, and Deep Learning in the rehabilitation of ischemic stroke.

Development and internal validation of machine learning-based models and external validation of existing risk scores for outcome prediction in patients with ischaemic stroke

Aims

We developed new machine learning (ML) models and externally validated existing statistical models [ischaemic stroke predictive risk score (iScore) and totalled health risks in vascular events (THRIVE) scores] for predicting the composite of recurrent stroke or all-cause mortality at 90 days and at 3 years after hospitalization for first acute ischaemic stroke (AIS).

Methods and results

In adults hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models [random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBOOST)] and externally validated the iScore and THRIVE scores for predicting the composite outcomes after AIS hospitalization, using data from 721 patients and 90 potential predictor variables. At 90 days and 3 years, 11 and 34% of patients, respectively, reached the composite outcome. For the 90-day prediction, the area under the receiver operating characteristic curve (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year prediction, the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE.

Conclusion

The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for long-term outcome prediction. Our findings warrant comparative analyses of ML and existing statistical method-based risk prediction tools for outcome prediction after AIS in new data sets.

Systematic Review of Machine Learning Applied to the Secondary Prevention of Ischemic Stroke

Ischemic stroke is a serious disease posing significant threats to human health and life, with the highest absolute and relative risks of a poor prognosis following the first occurrence, and more than 90% of strokes are attributable to modifiable risk factors. Currently, machine learning (ML) is widely used for the prediction of ischemic stroke outcomes. By identifying risk factors, predicting the risk of poor prognosis and thus developing personalized treatment plans, it effectively reduces the probability of poor prognosis, leading to more effective secondary prevention. This review includes 41 studies since 2018 that used ML algorithms to build prognostic prediction models for ischemic stroke, transient ischemic attack (TIA), and acute ischemic stroke (AIS). We analyzed in detail the risk factors used in these studies, the sources and processing methods of the required data, the model building and validation, and their application in different prediction time windows. The results indicate that among the included studies, the top five risk factors in terms of frequency were cardiovascular diseases, age, sex, national institutes of health stroke scale (NIHSS) score, and diabetes. Furthermore, 64% of the studies used single-center data, 65% of studies using imbalanced data did not perform data balancing, 88% of the studies did not utilize external validation datasets for model validation, and 72% of the studies did not provide explanations for their models. Addressing these issues is crucial for enhancing the credibility and effectiveness of the research, consequently improving the development and implementation of secondary prevention measures.

An interpretable ensemble learning model facilitates early risk stratification of ischemic stroke in intensive care unit: Development and external validation of ICU-ISPM

Ischemic stroke (IS) is a common and severe condition that requires intensive care unit (ICU) admission, with high mortality and variable prognosis. Accurate and reliable predictive tools that enable early risk stratification can facilitate interventions to improve patient outcomes; however, such tools are currently lacking. In this study, we developed and validated novel ensemble learning models based on soft voting and stacking methods to predict in-hospital mortality from IS in the ICU using two public databases: MIMIC-IV and eICU-CRD. Additionally, we identified the key predictors of mortality and developed a user-friendly online prediction tool for clinical use. The soft voting ensemble model, named ICU-ISPM, achieved an AUROC of 0.861 (95% CI: 0.829-0.892) and 0.844 (95% CI: 0.819-0.869) in the internal and external test cohorts, respectively. It significantly outperformed the APACHE scoring system and was more robust than individual models. ICU-ISPM obtained the highest performance compared to other models in similar studies. Using the SHAP method, the model was interpretable, revealing that GCS score, age, and intubation were the most important predictors of mortality. This model also provided a risk stratification system that can effectively distinguish between low-, medium-, and high-risk patients. Therefore, the ICU-ISPM is an accurate, reliable, interpretable, and clinically applicable tool, which is expected to assist clinicians in stratifying IS patients by the risk of mortality and rationally allocating medical resources. Based on ICU-ISPM, an online risk prediction tool was further developed, which was freely available at: http://ispm.idrblab.cn/.

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.

An integrated pipeline for prediction of Clostridioides difficile infection

With the expansion of electronic health records(EHR)-linked genomic data comes the development of machine learning-enable models. There is a pressing need to develop robust pipelines to evaluate the performance of integrated models and minimize systemic bias. We developed a prediction model of symptomatic Clostridioides difficile infection(CDI) by integrating common EHR-based and genetic risk factors(rs2227306/IL8). Our pipeline includes (1) leveraging phenotyping algorithm to minimize temporal bias, (2) performing simulation studies to determine the predictive power in samples without genetic information, (3) propensity score matching to control for the confoundings, (4) selecting machine learning algorithms to capture complex feature interactions, (5) performing oversampling to address data imbalance, and (6) optimizing models and ensuring proper bias-variance trade-off. We evaluate the performance of prediction models of CDI when including common clinical risk factors and the benefit of incorporating genetic feature(s) into the models. We emphasize the importance of building a robust integrated pipeline to avoid systemic bias and thoroughly evaluating genetic features when integrated into the prediction models in the general population and subgroups.

Artificial Intelligence in Acute Ischemic Stroke Subtypes According to Toast Classification: A Comprehensive Narrative Review

The correct recognition of the etiology of ischemic stroke (IS) allows tempestive interventions in therapy with the aim of treating the cause and preventing a new cerebral ischemic event. Nevertheless, the identification of the cause is often challenging and is based on clinical features and data obtained by imaging techniques and other diagnostic exams. TOAST classification system describes the different etiologies of ischemic stroke and includes five subtypes: LAAS (large-artery atherosclerosis), CEI (cardio embolism), SVD (small vessel disease), ODE (stroke of other determined etiology), and UDE (stroke of undetermined etiology). AI models, providing computational methodologies for quantitative and objective evaluations, seem to increase the sensitivity of main IS causes, such as tomographic diagnosis of carotid stenosis, electrocardiographic recognition of atrial fibrillation, and identification of small vessel disease in magnetic resonance images. The aim of this review is to provide overall knowledge about the most effective AI models used in the differential diagnosis of ischemic stroke etiology according to the TOAST classification. According to our results, AI has proven to be a useful tool for identifying predictive factors capable of subtyping acute stroke patients in large heterogeneous populations and, in particular, clarifying the etiology of UDE IS especially detecting cardioembolic sources.

Stroke mortality prediction based on ensemble learning and the combination of structured and textual data

For severe cerebrovascular diseases such as stroke, the prediction of short-term mortality of patients has tremendous medical significance. In this study, we combined machine learning models Random Forest classifier (RF), Adaptive Boosting (AdaBoost), Extremely Randomised Trees (ExtraTree) classifier, XGBoost classifier, TabNet, and DistilBERT to construct a multi-level prediction model that used bioassay data and radiology text reports from haemorrhagic and ischaemic stroke patients to predict six-month mortality. The performances of the prediction models were measured using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), precision, recall, and F1-score. The prediction models were built with the use of data from 19,616 haemorrhagic stroke patients and 50,178 ischaemic stroke patients. Novel six-month mortality prediction models for these patients were developed, which enhanced the performance of the prediction models by combining laboratory test data, structured data, and textual radiology report data. The achieved performances were as follows: AUROC = 0.89, AUPRC = 0.70, precision = 0.52, recall = 0.78, and F1 score = 0.63 for haemorrhagic patients, and AUROC = 0.88, AUPRC = 0.54, precision = 0.34, recall = 0.80, and F1 score = 0.48 for ischaemic patients. Such models could be used for mortality risk assessment and early identification of high-risk stroke patients. This could contribute to more efficient utilisation of healthcare resources for stroke survivors.

Deep learning-based personalised outcome prediction after acute ischaemic stroke

BACKGROUND

Whether deep learning models using clinical data and brain imaging can predict the long-term risk of major adverse cerebro/cardiovascular events (MACE) after acute ischaemic stroke (AIS) at the individual level has not yet been studied.

METHODS

A total of 8590 patients with AIS admitted within 5 days of symptom onset were enrolled. The primary outcome was the occurrence of MACEs (a composite of stroke, acute myocardial infarction or death) over 12 months. The performance of deep learning models (DeepSurv and Deep-Survival-Machines (DeepSM)) and traditional survival models (Cox proportional hazards (CoxPH) and random survival forest (RSF)) were compared using the time-dependent concordance index ([Formula: see text] index).

RESULTS

Given the top 1 to all 60 clinical factors according to feature importance, CoxPH and RSF yielded [Formula: see text] index of 0.7236-0.8222 and 0.7279-0.8335, respectively. Adding image features improved the performance of deep learning models and traditional models assisted by deep learning models. DeepSurv and DeepSM yielded the best [Formula: see text] index of 0.8496 and 0.8531 when images were added to all 39 relevant clinical factors, respectively. In feature importance, brain image was consistently ranked highly. Deep learning models automatically extracted the image features directly from personalised brain images and predicted the risk and date of future MACEs at the individual level.

CONCLUSIONS

Deep learning models using clinical data and brain images could improve the prediction of MACEs and provide personalised outcome prediction for patients with AIS. Deep learning models will allow us to develop more accurate and tailored prognostic prediction systems that outperform traditional models.

One-year mortality after acute stroke: a prospective cohort study from a comprehensive stroke care centre, Kerala, India

OBJECTIVES

The primary objective was to report the 1-year all-cause mortality among patients with stroke. The secondary objectives were (1) to report the mortality stratified by type of stroke and sex and (2) to report predictors of 1-year mortality among patients with stroke.

DESIGN

A prospective cohort study.

SETTING

Institutional-stroke care unit of a tertiary care hospital PARTICIPANTS: Patients who were treated in the study institution during 2016-2020 for acute stroke and were followed up for a period of 1 year after stroke in the same institution.

MAIN OUTCOME MEASURES

The main outcome measures were the mortality proportion of any stroke and first ever stroke cohorts at select time points, including in-hospital stay, along with 2 weeks, 2 months, 6 months and 1 year after index stroke. The secondary outcomes were (1) mortality proportions stratified by sex and type of stroke and (2) predictors of 1-year mortality for any stroke and first ever stroke.

RESULTS

We recruited a total of 1336 patients. The mean age of participants was 61.6 years (13.5 years). The mortality figures for 2 weeks, 2 months, 6 months and 12 months after discharge were 79 (5.9%), 88 (6.7%), 101 (7.6%) and 114 (8.5%), respectively, in the full cohort. The in-hospital mortality was 45 (3.4%). The adjusted analysis revealed 3 predictors for 1-year mortality after first ever stroke-age, pre-treatment National Institutes of Health Stroke Scale (NIHSS) score and Modified Rankin Scale (mRS) score at baseline. The same for the full cohort had only two predictors-age and pre-treatment NIHSS score.

CONCLUSION

Mortality of stroke at 1-year follow-up in the study population is low in comparison to several studies published earlier. The predictors of 1-year mortality after stroke included age, NIHSS score at baseline and mRS score at baseline.

Stacking ensemble learning model to predict 6-month mortality in ischemic stroke patients

Patients with acute ischemic stroke can benefit from reperfusion therapy. Nevertheless, there are gray areas where initiation of reperfusion therapy is neither supported nor contraindicated by the current practice guidelines. In these situations, a prediction model for mortality can be beneficial in decision-making. This study aimed to develop a mortality prediction model for acute ischemic stroke patients not receiving reperfusion therapies using a stacking ensemble learning model. The model used an artificial neural network as an ensemble classifier. Seven base classifiers were K-nearest neighbors, support vector machine, extreme gradient boosting, random forest, naive Bayes, artificial neural network, and logistic regression algorithms. From the clinical data in the International Stroke Trial database, we selected a concise set of variables assessable at the presentation. The primary study outcome was all-cause mortality at 6 months. Our stacking ensemble model predicted 6-month mortality with acceptable performance in ischemic stroke patients not receiving reperfusion therapy. The area under the curve of receiver-operating characteristics, accuracy, sensitivity, and specificity of the stacking ensemble classifier on a put-aside validation set were 0.783 (95% confidence interval 0.758-0.808), 71.6% (69.3-74.2), 72.3% (69.2-76.4%), and 70.9% (68.9-74.3%), respectively.

Dissecting Polygenic Etiology of Ischemic Stroke in the Era of Precision Medicine

Ischemic stroke (IS), the leading cause of death and disability worldwide, is caused by many modifiable and non-modifiable risk factors. This complex disease is also known for its multiple etiologies with moderate heritability. Polygenic risk scores (PRSs), which have been used to establish a common genetic basis for IS, may contribute to IS risk stratification for disease/outcome prediction and personalized management. Statistical modeling and machine learning algorithms have contributed significantly to this field. For instance, multiple algorithms have been successfully applied to PRS construction and integration of genetic and non-genetic features for outcome prediction to aid in risk stratification for personalized management and prevention measures. PRS derived from variants with effect size estimated based on the summary statistics of a specific subtype shows a stronger association with the matched subtype. The disruption of the extracellular matrix and amyloidosis account for the pathogenesis of cerebral small vessel disease (CSVD). Pathway-specific PRS analyses confirm known and identify novel etiologies related to IS. Some of these specific PRSs (e.g., derived from endothelial cell apoptosis pathway) individually contribute to post-IS mortality and, together with clinical risk factors, better predict post-IS mortality. In this review, we summarize the genetic basis of IS, emphasizing the application of methodologies and algorithms used to construct PRSs and integrate genetics into risk models.

Predicting mortality among ischemic stroke patients using pathways-derived polygenic risk scores

We aim to determine whether ischemic stroke(IS)-related PRSs are also associated with and further predict 3-year all-cause mortality. 1756 IS patients with European ancestry were randomly split into training (n = 1226) and testing (n = 530) groups with 3-year post-event observations. Univariate Cox proportional hazards regression model (CoxPH) was used for primary screening of individual prognostic PRSs. Only the significantly associated PRSs and clinical risk factors with the same direction for a causal relationship with IS were used to construct a multivariate CoxPH. Feature selection was conducted by the LASSO method. After feature selection, a prediction model with 11 disease-associated pathway-specific PRSs outperformed the base model, as demonstrated by a higher concordance index (0.751, 95%CI [0.693–0.809] versus 0.729, 95%CI [0.676–0.782]) in the testing sample. A PRS derived from endothelial cell apoptosis showed independent predictability in the multivariate CoxPH (Hazard Ratio = 1.193 [1.027–1.385], p = 0.021). These PRSs fine-tuned the model by better stratifying high, intermediate, and low-risk groups. Several pathway-specific PRSs were associated with clinical risk factors in an age-dependent manner and further confirmed some known etiologies of IS and all-cause mortality. In conclusion, Pathway-specific PRSs for IS are associated with all-cause mortality, and the integrated multivariate risk model provides prognostic value in this context.

Cyclosporine A loaded brain targeting nanoparticle to treat cerebral ischemia/reperfusion injury in mice

BACKGROUND

Ischemic stroke is one of the main causes of death and disability in the world. The treatment for ischemic stroke is to restore blood perfusion as soon as possible. However, when ischemic brain tissue is re-perfused by blood, the mitochondrial permeability transition pore (mPTP) in neuron and microglia is excessively opened, resulting in the apoptosis of neuron and nerve inflammation. This aggravates nerve injury. Cyclosporine A (CsA) inhibits the over-opening of mPTP, subsequently reducing the release of ROS and the apoptosis of cerebral ischemia/reperfusion injured neuron and microglia. However, CsA is insoluble in water and present in high concentrations in lymphatic tissue. Herein, cerebral infarction tissue targeted nanoparticle (CsA@HFn) was developed to treat cerebral ischemia/reperfusion injury.

RESULTS

CsA@HFn efficiently penetrated the blood-brain barrier (BBB) and selectively accumulated in ischemic area, inhibiting the opening of mPTP and ROS production in neuron. This subsequently reduced the apoptosis of neuron and the damage of BBB. Consequently, CsA@HFn significantly reduced the infarct area. Moreover, CsA@HFn inhibited the recruitment of astrocytes and microglia in ischemic region and polarized microglia into M2 type microglia, which subsequently alleviated the nerve inflammation.

CONCLUSIONS

CsA@HFn showed a significant therapeutic effect on cerebral ischemia/reperfusion injury by alleviating the apoptosis of neuron, nerve inflammation and the damage of BBB in ischemic area. CsA@HFn has great potential in the treatment of ischemic stroke.

Artificial Intelligence: A Shifting Paradigm in Cardio-Cerebrovascular Medicine

The future of healthcare is an organic blend of technology, innovation, and human connection. As artificial intelligence (AI) is gradually becoming a go-to technology in healthcare to improve efficiency and outcomes, we must understand our limitations. We should realize that our goal is not only to provide faster and more efficient care, but also to deliver an integrated solution to ensure that the care is fair and not biased to a group of sub-population. In this context, the field of cardio-cerebrovascular diseases, which encompasses a wide range of conditions-from heart failure to stroke-has made some advances to provide assistive tools to care providers. This article aimed to provide an overall thematic review of recent development focusing on various AI applications in cardio-cerebrovascular diseases to identify gaps and potential areas of improvement. If well designed, technological engines have the potential to improve healthcare access and equitability while reducing overall costs, diagnostic errors, and disparity in a system that affects patients and providers and strives for efficiency.

Imputation of missing values for electronic health record laboratory data

Laboratory data from Electronic Health Records (EHR) are often used in prediction models where estimation bias and model performance from missingness can be mitigated using imputation methods. We demonstrate the utility of imputation in two real-world EHR-derived cohorts of ischemic stroke from Geisinger and of heart failure from Sutter Health to: (1) characterize the patterns of missingness in laboratory variables; (2) simulate two missing mechanisms, arbitrary and monotone; (3) compare cross-sectional and multi-level multivariate missing imputation algorithms applied to laboratory data; (4) assess whether incorporation of latent information, derived from comorbidity data, can improve the performance of the algorithms. The latter was based on a case study of hemoglobin A1c under a univariate missing imputation framework. Overall, the pattern of missingness in EHR laboratory variables was not at random and was highly associated with patients' comorbidity data; and the multi-level imputation algorithm showed smaller imputation error than the cross-sectional method.