Pre-thrombectomy prognostic prediction of large-vessel ischemic stroke using machine learning: A systematic review and meta-analysis

Automatic prediction of stroke treatment outcomes: latest advances and perspectives

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. Engaging and developing deep learning techniques can help to analyse large and diverse medical data, including brain scans, medical reports, and other sensor information, such as EEG, ECG, EMG, and so on. Despite the common data standardisation challenge within the medical image analysis domain, the future of deep learning in stroke outcome prediction lies in using multimodal information, including final infarct data, to achieve better prediction of long-term functional outcomes. This article provides a broad review of recent advances and applications of deep learning in the prediction of stroke outcomes, including (i) the data and models used, (ii) the prediction tasks and measures of success, (iii) the current challenges and limitations, and (iv) future directions and potential benefits. This comprehensive review aims to provide researchers, clinicians, and policy makers with an up-to-date understanding of this rapidly evolving and promising field.

Predictive models of clinical outcome of endovascular treatment for anterior circulation stroke using machine learning

BACKGROUND AND PURPOSE

Mechanical Thrombectomy (MT) has recently become the standard of care for anterior circulation stroke with large vessel occlusion, but predictive factors of successful MT are still not clearly defined. To tailor treatment individually for each patient, the aim of this study was to evaluate the performances of Machine Learning to predict clinical outcome (mRS) at 3 months after MT.

MATERIAL AND METHODS

From the ETIS French prospective multicenter registry, data from patients who underwent MT for anterior circulation stroke with large vessel occlusion between January 2018 and December 2020 were extracted. Three machine learning models (Support Vector Machine, Random Forest and XGBoost) have been trained with clinical, biological and brain imaging data available in emergency conditions from the cohort of patients treated from 2018 to 2019. Models' performances to predict good outcome (3-months mRS <3) were evaluated on patients treated in 2020. Performances were evaluated with AUC, accuracy, sensitivity and specificity, then ROC curves AUC were compared with the best performing model.

RESULTS

4297 patients were included, 1737 (40 %) with good outcome and 2560 (60 %) with bad outcome were used to train models and 599 patients treated in 2020 were used to evaluate their performances. The best model was obtained with XGBoost: AUC = 0.77, accuracy = 69.3 % but no statistically significant difference existed between models.

CONCLUSION

Our study shows satisfying performances of machine learning to predict clinical outcome after MT using data easily available at initial diagnosis and before the decision to treat.

Deep learning on pre-procedural computed tomography and clinical data predicts outcome following stroke thrombectomy

BACKGROUND

Deep learning using clinical and imaging data may improve pre-treatment prognostication in ischemic stroke patients undergoing endovascular thrombectomy (EVT).

METHODS

Deep learning models were trained and tested on baseline clinical and imaging (CT head and CT angiography) data to predict 3-month functional outcomes in stroke patients who underwent EVT. Classical machine learning models (logistic regression and random forest classifiers) were constructed to compare their performance with the deep learning models. An external validation dataset was used to validate the models. The MR PREDICTS prognostic tool was tested on the external validation set, and its performance was compared with the deep learning and classical machine learning models.

RESULTS

A total of 975 patients (550 men; mean±SD age 67.5±15.1 years) were studied with 778 patients in the model development cohort and 197 in the external validation cohort. The deep learning model trained on baseline CT and clinical data, and the logistic regression model (clinical data alone) demonstrated the strongest discriminative abilities for 3-month functional outcome and were comparable (AUC 0.811 vs 0.817, Q=0.82). Both models exhibited superior prognostic performance than the other deep learning (CT head alone, CT head, and CT angiography) and MR PREDICTS models (all Q<0.05).

CONCLUSIONS

The discriminative performance of deep learning for predicting functional independence was comparable to logistic regression. Future studies should focus on whether incorporating procedural and post-procedural data significantly improves model performance.

Machine learning for clinical outcome prediction in cerebrovascular and endovascular neurosurgery: systematic review and meta-analysis

BACKGROUND

Machine learning (ML) may be superior to traditional methods for clinical outcome prediction. We sought to systematically review the literature on ML for clinical outcome prediction in cerebrovascular and endovascular neurosurgery.

METHODS

A comprehensive literature search was performed, and original studies of patients undergoing cerebrovascular surgeries or endovascular procedures that developed a supervised ML model to predict a postoperative outcome or complication were included.

RESULTS

A total of 60 studies predicting 71 outcomes were included. Most cohorts were derived from single institutions (66.7%). The studies included stroke (32), subarachnoid hemorrhage ((SAH) 16), unruptured aneurysm (7), arteriovenous malformation (4), and cavernous malformation (1). Random forest was the best performing model in 12 studies (20%) followed by XGBoost (13.3%). Among 42 studies in which the ML model was compared with a standard statistical model, ML was superior in 33 (78.6%). Of 10 studies in which the ML model was compared with a non-ML clinical prediction model, ML was superior in nine (90%). External validation was performed in 10 studies (16.7%). In studies predicting functional outcome after mechanical thrombectomy the pooled area under the receiver operator characteristics curve (AUROC) of the test set performances was 0.84 (95% CI 0.79 to 0.88). For studies predicting outcomes after SAH, the pooled AUROCs for functional outcomes and delayed cerebral ischemia were 0.89 (95% CI 0.76 to 0.95) and 0.90 (95% CI 0.66 to 0.98), respectively.

CONCLUSION

ML performs favorably for clinical outcome prediction in cerebrovascular and endovascular neurosurgery. However, multicenter studies with external validation are needed to ensure the generalizability of these findings.

Development of a PMGDNI model to predict the probability of three-month unfavorable outcome acute ischemic stroke after endovascular treatment: a cohort study

BACKGROUND

Patients with acute large vessel occlusion stroke (ALVOS) may exhibit considerable variability in clinical outcomes following mechanical thrombectomy (MT). This study aimed to develop a novel statistical model predicting functional independence three months post-endovascular treatment for acute stroke and validate its performance within the cohort.

METHOD

Consecutive patients undergoing endovascular treatment for acute stroke with large vessel occlusion were randomly divided into a modeling group and a validation group in a 7:3 ratio. Independent risk factors were identified through LASSO regression and multivariate logistic regression analyses, leading to the development of a prognostic model whose performance was rigorously validated.

RESULTS

A total of 913 patients were screened, with 893 cases included. The modeling group comprised 625 cases, and the validation group included 268 cases. Identified independent factors for adverse outcomes after endovascular treatment of acute ischemic stroke (AIS) were pneumonia (OR = 4.517, 95% CI = 2.916-7.101, P < 0.001), mechanical ventilation (OR = 2.449, 95% CI = 1.475-5.148, P = 0.001), admission GCS ≥ 8 (OR = 0.365, 95% CI = 0.167-0.745, P = 0.008), dysphagia (OR = 2.074, 95% CI = 1.375-3.126, P < 0.001), and 72-hour highest Na ≥ 145 (OR = 2.794, 95% CI = 1.508-5.439, P = 0.002), along with intracranial hemorrhage (OR = 2.453, 95% CI = 1.408-4.396, P = 0.002). These factors were illustrated in a PMGDNI column chart. The area under the ROC curve for the modeling group was 82.5% (95% CI = 0.793-0.857), and for the validation group, it was 83.7% (95% CI = 0.789-0.885). The Hosmer-Lemeshow test indicates that there is no statistically significant difference (P > 0.05) between the predicted and actual probabilities of adverse outcomes. The clinical decision curve demonstrated optimal net benefits at thresholds of 0.30-1.00 and 0.25-1.00 for both training and validation sets, indicating effective clinical efficacy within these probability ranges.

CONCLUSION

We have successfully developed a new predictive model enhancing the accuracy of prognostic assessments for acute ischemic stroke following EVT. It provides an individual, visual, and precise prediction of the risk probability of a 90-day unfavorable outcome.

Performance Metrics, Algorithms, and Applications of Artificial Intelligence in Vascular and Interventional Neurology: A Review of Basic Elements

Artificial intelligence (AI) is currently being used as a routine tool for day-to-day activity. Medicine is not an exception to the growing usage of AI in various scientific fields. Vascular and interventional neurology deal with diseases that require early diagnosis and appropriate intervention, which are crucial to saving patients' lives. In these settings, AI can be an extra pair of hands for physicians or in conditions where there is a shortage of clinical experts. In this article, the authors have reviewed the common metrics used in interpreting the performance of models and common algorithms used in this field.

Predictions for functional outcome and mortality in acute ischaemic stroke following successful endovascular thrombectomy

Background

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.

Methods

The study included all patients who had ischaemic stroke with occlusion in the proximal anterior cerebral circulation and successful reperfusion post-EVT over a 7-year period. Multivariable logistic regression and Cox regression models, incorporating bootstrap and multiple imputation techniques, were used to identify predictors and develop models for key clinical outcomes: 3-month poor functional status; 30-day, 1-year and 3-year mortality; survival time.

Results

A total of 978 patients were included in the analyses. Predictors associated with one or more poor outcomes include: older age (ORs for every 5-year increase: 1.22-1.40), higher premorbid functional modified Rankin Scale (ORs: 1.31-1.75), higher baseline National Institutes of Health Stroke Scale (ORs: 1.05-1.07) score, higher blood glucose (ORs: 1.08-1.19), larger core volume (ORs for every 10 mL increase: 1.10-1.22), pre-EVT thrombolytic therapy (ORs: 0.44-0.56), history of heart failure (outcome: 30-day mortality, OR=1.87), interhospital transfer (ORs: 1.42 to 1.53), non-rural/regional stroke onset (outcome: functional dependency, OR=0.64), longer onset-to-groin puncture time (outcome: 3-year mortality, OR=1.08) and atherosclerosis-caused stroke (outcome: functional dependency, OR=1.68). The models using these predictors demonstrated moderate predictive abilities (area under the receiver operating characteristic curve range: 0.752-0.796).

Conclusion

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. These can be used to inform EVT treatment provision and consent.

Utilizing imaging parameters for functional outcome prediction in acute ischemic stroke: A machine learning study

BACKGROUND AND PURPOSE

We aimed to predict the functional outcome of acute ischemic stroke patients with anterior circulation large vessel occlusions (LVOs), irrespective of how they were treated or the severity of the stroke at admission, by only using imaging parameters in machine learning models.

METHODS

Consecutive adult patients with anterior circulation LVOs who were scanned with CT angiography (CTA) and CT perfusion were queried in this single-center, retrospective study. The favorable outcome was defined as a modified Rankin score (mRS) of 0-2 at 90 days. Predictor variables included only imaging parameters. CatBoost, XGBoost, and Random Forest were employed. Algorithms were evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), accuracy, Brier score, recall, and precision. SHapley Additive exPlanations were implemented.

RESULTS

A total of 180 patients (102 female) were included, with a median age of 69.5. Ninety-two patients had an mRS between 0 and 2. The best algorithm in terms of AUROC was XGBoost (0.91). Furthermore, the XGBoost model exhibited a precision of 0.72, a recall of 0.81, an AUPRC of 0.83, an accuracy of 0.78, and a Brier score of 0.17. Multiphase CTA collateral score was the most significant feature in predicting the outcome.

CONCLUSIONS

Using only imaging parameters, our model had an AUROC of 0.91 which was superior to most previous studies, indicating that imaging parameters may be as accurate as conventional predictors. The multiphase CTA collateral score was the most predictive variable, highlighting the importance of collaterals.

Machine Learning-Based Asthma Attack Prediction Models From Routinely Collected Electronic Health Records: Systematic Scoping Review

BACKGROUND

An early warning tool to predict attacks could enhance asthma management and reduce the likelihood of serious consequences. Electronic health records (EHRs) providing access to historical data about patients with asthma coupled with machine learning (ML) provide an opportunity to develop such a tool. Several studies have developed ML-based tools to predict asthma attacks.

OBJECTIVE

This study aims to critically evaluate ML-based models derived using EHRs for the prediction of asthma attacks.

METHODS

We systematically searched PubMed and Scopus (the search period was between January 1, 2012, and January 31, 2023) for papers meeting the following inclusion criteria: (1) used EHR data as the main data source, (2) used asthma attack as the outcome, and (3) compared ML-based prediction models' performance. We excluded non-English papers and nonresearch papers, such as commentary and systematic review papers. In addition, we also excluded papers that did not provide any details about the respective ML approach and its result, including protocol papers. The selected studies were then summarized across multiple dimensions including data preprocessing methods, ML algorithms, model validation, model explainability, and model implementation.

RESULTS

Overall, 17 papers were included at the end of the selection process. There was considerable heterogeneity in how asthma attacks were defined. Of the 17 studies, 8 (47%) studies used routinely collected data both from primary care and secondary care practices together. Extreme imbalanced data was a notable issue in most studies (13/17, 76%), but only 38% (5/13) of them explicitly dealt with it in their data preprocessing pipeline. The gradient boosting-based method was the best ML method in 59% (10/17) of the studies. Of the 17 studies, 14 (82%) studies used a model explanation method to identify the most important predictors. None of the studies followed the standard reporting guidelines, and none were prospectively validated.

CONCLUSIONS

Our review indicates that this research field is still underdeveloped, given the limited body of evidence, heterogeneity of methods, lack of external validation, and suboptimally reported models. We highlighted several technical challenges (class imbalance, external validation, model explanation, and adherence to reporting guidelines to aid reproducibility) that need to be addressed to make progress toward clinical adoption.