Multimodal Predictive Modeling of Endovascular Treatment Outcome for Acute Ischemic Stroke Using Machine-Learning

Ischemic stroke outcome prediction with diversity features from whole brain tissue using deep learning network

Objectives

This study proposed an outcome prediction method to improve the accuracy and efficacy of ischemic stroke outcome prediction based on the diversity of whole brain features, without using basic information about patients and image features in lesions.

Design

In this study, we directly extracted dynamic radiomics features (DRFs) from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) and further extracted static radiomics features (SRFs) and static encoding features (SEFs) from the minimum intensity projection (MinIP) map, which was generated from the time dimension of DSC-PWI images. After selecting whole brain features Ffuse from the combinations of DRFs, SRFs, and SEFs by the Lasso algorithm, various machine and deep learning models were used to evaluate the role of Ffuse in predicting stroke outcomes.

Results

The experimental results show that the feature Ffuse generated from DRFs, SRFs, and SEFs (Resnet 18) outperformed other single and combination features and achieved the best mean score of 0.971 both on machine learning models and deep learning models and the 95% CI were (0.703, 0.877) and (0.92, 0.983), respectively. Besides, the deep learning models generally performed better than the machine learning models.

Conclusion

The method used in our study can achieve an accurate assessment of stroke outcomes without segmentation of ischemic lesions, which is of great significance for rapid, efficient, and accurate clinical stroke treatment.

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.

A Clinical and Imaging Fused Deep Learning Model Matches Expert Clinician Prediction of 90-Day Stroke Outcomes

BACKGROUND AND PURPOSE

Predicting long-term clinical outcome in acute ischemic stroke is beneficial for prognosis, clinical trial design, resource management, and patient expectations. This study used a deep learning-based predictive model (DLPD) to predict 90-day mRS outcomes and compared its predictions with those made by physicians.

MATERIALS AND METHODS

A previously developed DLPD that incorporated DWI and clinical data from the acute period was used to predict 90-day mRS outcomes in 80 consecutive patients with acute ischemic stroke from a single-center registry. We assessed the predictions of the model alongside those of 5 physicians (2 stroke neurologists and 3 neuroradiologists provided with the same imaging and clinical information). The primary analysis was the agreement between the ordinal mRS predictions of the model or physician and the ground truth using the Gwet Agreement Coefficient. We also evaluated the ability to identify unfavorable outcomes (mRS >2) using the area under the curve, sensitivity, and specificity. Noninferiority analyses were undertaken using limits of 0.1 for the Gwet Agreement Coefficient and 0.05 for the area under the curve analysis. The accuracy of prediction was also assessed using the mean absolute error for prediction, percentage of predictions ±1 categories away from the ground truth (±1 accuracy [ACC]), and percentage of exact predictions (ACC).

RESULTS

To predict the specific mRS score, the DLPD yielded a Gwet Agreement Coefficient score of 0.79 (95% CI, 0.71-0.86), surpassing the physicians' score of 0.76 (95% CI, 0.67-0.84), and was noninferior to the readers (P < .001). For identifying unfavorable outcome, the model achieved an area under the curve of 0.81 (95% CI, 0.72-0.89), again noninferior to the readers' area under the curve of 0.79 (95% CI, 0.69-0.87) (P < .005). The mean absolute error, ±1ACC, and ACC were 0.89, 81%, and 36% for the DLPD.

CONCLUSIONS

A deep learning method using acute clinical and imaging data for long-term functional outcome prediction in patients with acute ischemic stroke, the DLPD, was noninferior to that of clinical readers.

Artificial Intelligence and Machine Learning Applications in Critically Ill Brain Injured Patients

The utilization of Artificial Intelligence (AI) and Machine Learning (ML) is paving the way for significant strides in patient diagnosis, treatment, and prognostication in neurocritical care. These technologies offer the potential to unravel complex patterns within vast datasets ranging from vast clinical data and EEG (electroencephalogram) readings to advanced cerebral imaging facilitating a more nuanced understanding of patient conditions. Despite their promise, the implementation of AI and ML faces substantial hurdles. Historical biases within training data, the challenge of interpreting multifaceted data streams, and the "black box" nature of ML algorithms present barriers to widespread clinical adoption. Moreover, ethical considerations around data privacy and the need for transparent, explainable models remain paramount to ensure trust and efficacy in clinical decision-making.This article reflects on the emergence of AI and ML as integral tools in neurocritical care, discussing their roles from the perspective of both their scientific promise and the associated challenges. We underscore the importance of extensive validation in diverse clinical settings to ensure the generalizability of ML models, particularly considering their potential to inform critical medical decisions such as withdrawal of life-sustaining therapies. Advancement in computational capabilities is essential for implementing ML in clinical settings, allowing for real-time analysis and decision support at the point of care. As AI and ML are poised to become commonplace in clinical practice, it is incumbent upon health care professionals to understand and oversee these technologies, ensuring they adhere to the highest safety standards and contribute to the realization of personalized medicine. This engagement will be pivotal in integrating AI and ML into patient care, optimizing outcomes in neurocritical care through informed and data-driven decision-making.

Contributions of Machine Learning in the Management of Stroke: A Bibliometric Analysis of the 50 Most Cited Articles

BACKGROUND

Though currently considered a 'black box,' machine learning (ML) has a promising future to ameliorate the health-care burden of stroke which is the second leading cause of mortality worldwide. Through this study, we sought to review the most influential articles on the applications of ML in stroke.

METHODS

Web of Sciences database was searched, and a list of the top 50 most cited articles, assessing the application of ML in stroke, was prepared by 2 authors, independently. Subsequently, a detailed analysis was performed to characterize the most impactful studies.

RESULTS

The total number of citations to the top 50 articles were 2959 (range 35-243 citations) with a median of 47 citations. Highest number of articles were published in the journal Stroke and the United States was the major contributing country. The majority of the studies focused on the utilization of ML to improve stroke risk prediction, diagnosis, and outcome prediction. Statistical analysis revealed an insignificant association between the total and mean number of citations and the impact factor of the journal (P = 0.516 and 0.987, respectively).

CONCLUSIONS

Recent years have witnessed a surge in the application of ML in stroke, with an enhancement in interest and funding over the years. ML has revolutionized the management of stroke and continues to aid in the neurosurgical decision-making and care in stroke patients.

Identifying and predicting physical limitation and cognitive decline trajectory group of older adults in China: A data-driven machine learning analysis

OBJECTIVE

This study aimed to utilize data-driven machine learning methods to identify and predict potential physical and cognitive function trajectory groups of older adults and determine their crucial factors for promoting active ageing in China.

METHODS

Longitudinal data on 3026 older adults from the Chinese Longitudinal Healthy Longevity and Happy Family Survey was used to identify potential physical and cognitive function trajectory groups using a group-based multi-trajectory model (GBMTM). Predictors were selected from sociodemographic characteristics, lifestyle factors, and physical and mental conditions. The trajectory groups were predicted using data-driven machine learning models and dynamic nomogram. Model performance was evaluated by area under the receiver operating characteristics curve (AUROC), area under the precision-recall curve (PRAUC), and confusion matrix.

RESULTS

Two physical and cognitive function trajectory groups were determined, including a trajectory group with physical limitation and cognitive decline (14.18 %) and a normal trajectory group (85.82 %). Logistic regression performed well in predicting trajectory groups (AUROC = 0.881, PRAUC = 0.649). Older adults with lower baseline score of activities of daily living, older age, less frequent housework, and fewer actual teeth were more likely to experience physical limitation and cognitive decline trajectory group.

LIMITATION

This study didn't carry out external validation.

CONCLUSIONS

This study shows that GBMTM and machine learning models effectively identify and predict physical limitation and cognitive decline trajectory group. The identified predictors might be essential for developing targeted interventions to promote healthy ageing.

Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis

Background

Artificial intelligence-derived software technologies have been developed that are intended to facilitate the review of computed tomography brain scans in patients with suspected stroke.

Objectives

To evaluate the clinical and cost-effectiveness of using artificial intelligence-derived software to support review of computed tomography brain scans in acute stroke in the National Health Service setting.

Methods

Twenty-five databases were searched to July 2021. The review process included measures to minimise error and bias. Results were summarised by research question, artificial intelligence-derived software technology and study type. The health economic analysis focused on the addition of artificial intelligence-derived software-assisted review of computed tomography angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with an ischaemic stroke. The de novo model (developed in R Shiny, R Foundation for Statistical Computing, Vienna, Austria) consisted of a decision tree (short-term) and a state transition model (long-term) to calculate the mean expected costs and quality-adjusted life-years for people with ischaemic stroke and suspected large-vessel occlusion comparing artificial intelligence-derived software-assisted review to usual care.

Results

A total of 22 studies (30 publications) were included in the review; 18/22 studies concerned artificial intelligence-derived software for the interpretation of computed tomography angiography to detect large-vessel occlusion. No study evaluated an artificial intelligence-derived software technology used as specified in the inclusion criteria for this assessment. For artificial intelligence-derived software technology alone, sensitivity and specificity estimates for proximal anterior circulation large-vessel occlusion were 95.4% (95% confidence interval 92.7% to 97.1%) and 79.4% (95% confidence interval 75.8% to 82.6%) for Rapid (iSchemaView, Menlo Park, CA, USA) computed tomography angiography, 91.2% (95% confidence interval 77.0% to 97.0%) and 85.0 (95% confidence interval 64.0% to 94.8%) for Viz LVO (Viz.ai, Inc., San Fransisco, VA, USA) large-vessel occlusion, 83.8% (95% confidence interval 77.3% to 88.7%) and 95.7% (95% confidence interval 91.0% to 98.0%) for Brainomix (Brainomix Ltd, Oxford, UK) e-computed tomography angiography and 98.1% (95% confidence interval 94.5% to 99.3%) and 98.2% (95% confidence interval 95.5% to 99.3%) for Avicenna CINA (Avicenna AI, La Ciotat, France) large-vessel occlusion, based on one study each. These studies were not considered appropriate to inform cost-effectiveness modelling but formed the basis by which the accuracy of artificial intelligence plus human reader could be elicited by expert opinion. Probabilistic analyses based on the expert elicitation to inform the sensitivity of the diagnostic pathway indicated that the addition of artificial intelligence to detect large-vessel occlusion is potentially more effective (quality-adjusted life-year gain of 0.003), more costly (increased costs of £8.61) and cost-effective for willingness-to-pay thresholds of £3380 per quality-adjusted life-year and higher.

Limitations and conclusions

The available evidence is not suitable to determine the clinical effectiveness of using artificial intelligence-derived software to support the review of computed tomography brain scans in acute stroke. The economic analyses did not provide evidence to prefer the artificial intelligence-derived software strategy over current clinical practice. However, results indicated that if the addition of artificial intelligence-derived software-assisted review for guiding mechanical thrombectomy treatment decisions increased the sensitivity of the diagnostic pathway (i.e. reduced the proportion of undetected large-vessel occlusions), this may be considered cost-effective.

Future work

Large, preferably multicentre, studies are needed (for all artificial intelligence-derived software technologies) that evaluate these technologies as they would be implemented in clinical practice.

Study registration

This study is registered as PROSPERO CRD42021269609.

Funding

This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133836) and is published in full in Health Technology Assessment; Vol. 28, No. 11. See the NIHR Funding and Awards website for further award information.

Incremental value of serum neurofilament light chain and glial fibrillary acidic protein as blood-based biomarkers for predicting functional outcome in severe acute ischemic stroke

INTRODUCTION

Blood-based biomarkers may improve prediction of functional outcome in patients with acute ischemic stroke. The role of neurofilament light chain (NfL) and glial fibrillary acidic (GFAP) as potential biomarkers especially in severe stroke patients is unknown.

PATIENTS AND METHODS

Prospective, monocenter, cohort study including consecutive patients with severe ischemic stroke in the anterior circulation on admission (NIHSS score ⩾ 6 points or indication for mechanical thrombectomy). Outcome was assessed 3 months after the index stroke by the modified Rankin Scale (mRS). Serum biomarkers levels of NfL and GFAP were determined by ultrasensitive ELISA. Univariate and multivariate logistic regression models were performed to determine the association of biomarker levels and functional disability. Discrimination, calibration, and overall performance were analyzed in different models via AUROC, calibration plots (with Emax and Eavg), Brier-score and R2 using variables, identified as important covariates for functional outcome in previous studies.

RESULTS

Between 06/2020 and 08/2021, 213 patients were included [47% female, mean age 76 (SD ± 12) years, median NIHSS score 13 (interquartile range, IQR 9; 17)]. Biomarker serum levels were measured at a median of 1 [IQR, 1; 2] day after admission. Compared to patients with mRS 0-2 at 3 months, patients with mRS 3-6 had higher serum levels of NfL (median: 136 pg/ml vs 41 pg/ml; p < 0.0001) and GFAP (700 ng/ml vs 9.6 ng/ml; p < 0.0001). Both biomarkers were significantly associated with functional outcome [adjusted logistic regression, odds ratio (95% CI) for NfL: 2.63 (1.62; 4.56), GFAP: 2.16 (1.58; 3.09)]. In all models the addition of serum NfL led to a significant improvement in the AUROC, as did the addition of serum GFAP. Calibration plots showed high agreement between the predicted and observed outcomes and after addition of the two blood-based biomarkers there was an improvement of the overall performance.

CONCLUSION

Prediction of functional outcome after severe acute ischemic stroke was improved by the blood-based biomarkers serum NfL and GFAP, measured in the acute phase of stroke. These findings have to be replicated in independent external cohorts.Study registration: DRKS00022064.

Cortical atrophy on baseline computed tomography imaging predicts clinical outcome in patients undergoing endovascular treatment for acute ischemic stroke

OBJECTIVE

Multiple variables beyond the extent of recanalization can impact the clinical outcome after acute ischemic stroke due to large vessel occlusions. Here, we assessed the influence of small vessel disease and cortical atrophy on clinical outcome using native cranial computed tomography (NCCT) in a large single-center cohort.

METHODS

A total of 1103 consecutive patients who underwent endovascular treatment (EVT) due to occlusion of the middle cerebral artery territory were included. NCCT data were visually assessed for established markers of age-related white matter changes (ARWMC) and brain atrophy. All images were evaluated separately by two readers to assess the inter-observer variability. Regression and machine learning models were built to determine the predictive relevance of ARWMC and atrophy in the presence of important baseline clinical and imaging metrics.

RESULTS

Patients with favorable outcome presented lower values for all measured metrics of pre-existing brain deterioration (p < 0.001). Both ARWMC (p < 0.05) and cortical atrophy (p < 0.001) were independent predictors of clinical outcome at 90 days when controlled for confounders in both regression analyses and led to a minor improvement of prediction accuracy in machine learning models (p < 0.001), with atrophy among the top-5 predictors.

CONCLUSION

NCCT-based cortical atrophy and ARWMC scores on NCCT were strong and independent predictors of clinical outcome after EVT.

CLINICAL RELEVANCE STATEMENT

Visual assessment of cortical atrophy and age-related white matter changes on CT could improve the prediction of clinical outcome after thrombectomy in machine learning models which may be integrated into existing clinical routines and facilitate patient selection.

KEY POINTS

• Cortical atrophy and age-related white matter changes were quantified using CT-based visual scores. • Atrophy and age-related white matter change scores independently predicted clinical outcome after mechanical thrombectomy and improved machine learning-based prediction models. • Both scores could easily be integrated into existing clinical routines and prediction models.

Development and validation of outcome prediction model for reperfusion therapy in acute ischemic stroke using nomogram and machine learning

OBJECTIVE

To develop logistic regression nomogram and machine learning (ML)-based models to predict 3-month unfavorable functional outcome for acute ischemic stroke (AIS) patients undergoing reperfusion therapy.

METHODS

Patients undergoing reperfusion therapy (intravenous thrombolysis and/or endovascular treatment) were prospectively recruited. Unfavorable outcome was defined as 3-month modified Rankin Scale (mRS) score 3-6. The independent risk factors associated with unfavorable outcome were obtained by regression analysis and included in the prediction model. The performance of nomogram was assessed by the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). ML models were compared with nomogram using AUC; the generalizability of all models was ascertained in an external cohort.

RESULTS

A total of 505 patients were enrolled, with 256 in the model construction, and 249 in the external validation. Five variables were identified as prognostic factors: baseline NIHSS, D-dimer level, random blood glucose (RBG), blood urea nitrogen (BUN), and systolic blood pressure (SBP) before reperfusion. The AUC values of nomogram were 0.865, 0.818, and 0.779 in the training set, test set, and external validation, respectively. The calibration curve and DCA indicated appreciable reliability and good net benefits. The best three ML models were extra trees (ET), CatBoost, and random forest (RF) models; all of them showed favorable discrimination in the training cohort, and confirmed in the test and external sets.

CONCLUSION

Baseline NIHSS, D-dimer, RBG, BUN, and SBP before reperfusion were independent predictors for 3-month unfavorable outcome after reperfusion therapy in AIS patients. Both nomogram and ML models showed good discrimination and generalizability.

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.

Predicting stroke outcome: A case for multimodal deep learning methods with tabular and CT Perfusion data

MOTIVATION

Acute ischemic stroke is one of the leading causes of morbidity and disability worldwide, often followed by a long rehabilitation period. To improve and personalize stroke rehabilitation, it is essential to provide a reliable prognosis to caregivers and patients. Deep learning techniques might improve the predictions by incorporating different data modalities. We present a multimodal approach to predict the functional status of acute ischemic stroke patients after their discharge based on tabular data and CT perfusion imaging.

METHODS

We conducted experiments on tabular, imaging, and multimodal deep learning architectures to predict dichotomized mRS scores 3 months after the event. The dataset was collected from a Dutch hospital and includes 98 CVA patients with a visible occlusion on their CT perfusion scan. Tabular data is based on the Dutch Acute Stroke Audit data, and imaging data consists of summed-up CT perfusion maps.

RESULTS

On the tabular data, TabNet outperformed our baselines with an AUC of 0.71, while ResNet-10 on the imaging data performed comparably with an AUC of 0.70. Our implementation of the multimodal DAFT architecture outperforms baselines as well as comparable studies by achieving an 0.75 AUC, and 0.80 F1 score. This was achieved with a final model of less than a hundred thousand optimizable parameters, and a dataset less than half the size of reference papers.

CONCLUSION

Overall, we demonstrate the feasibility of predicting the functional outcome for ischemic stroke patients and the usability of multimodal deep learning architectures for this purpose.

Online interpretable dynamic prediction models for postoperative delirium after cardiac surgery under cardiopulmonary bypass developed based on machine learning algorithms: A retrospective cohort study

OBJECTIVE

Postoperative delirium (POD) is strongly associated with poor early and long-term prognosis in cardiac surgery patients with cardiopulmonary bypass (CPB). This study aimed to develop dynamic prediction models for POD after cardiac surgery under CPB using machine learning (ML) algorithms.

METHODS

From July 2021 to June 2022, clinical data were collected from patients undergoing cardiac surgery under CPB at Nanjing First Hospital. A dataset from the same center (October 2022 to November 2022) was also used for temporal external validation. We used ML and deep learning to build models in the training set, optimized parameters in the test set, and finally validated the best model in the validation set. The SHapley Additive exPlanations (SHAP) method was introduced to explain the best models.

RESULTS

Of the 885 patients enrolled, 221 (25.0%) developed POD. 22 (22.0%) of 100 validation cohort patients developed POD. The preoperative and postoperative artificial neural network (ANN) models exhibited optimal performance. The validation results demonstrated satisfactory predictive performance of the ANN model, with area under the receiver operator characteristic curve (AUROC) values of 0.776 and 0.684 for the preoperative and postoperative models, respectively. Based on the ANN algorithm, we constructed dynamic, highly accurate, and interpretable web risk calculators for POD.

CONCLUSIONS

We successfully developed online interpretable dynamic ANN models as clinical decision aids to identify patients at high risk of POD before and after cardiac surgery to facilitate early intervention or care.

Clinical value of automated volumetric quantification of early ischemic tissue changes on non-contrast CT

BACKGROUND

Quantitative and automated volumetric evaluation of early ischemic changes on non-contrast CT (NCCT) has recently been proposed as a new tool to improve prognostic performance in patients undergoing endovascular therapy (EVT) for acute ischemic stroke (AIS). We aimed to test its clinical value compared with the Alberta Stroke Program Early CT Score (ASPECTS) in a large single-institutional patient cohort.

METHODS

A total of 1103 patients with AIS due to large vessel occlusion in the M1 or proximal M2 segments who underwent NCCT and EVT between January 2013 and November 2019 were retrospectively enrolled. Acute ischemic volumes (AIV) and ASPECTS were generated from the baseline NCCT through e-ASPECTS (Brainomix). Correlations were tested using Spearman's coefficient. The predictive capabilities of AIV for a favorable outcome (modified Rankin Scale score at 90 days ≤2) were tested using multivariable logistic regression as well as machine-learning models. Performance of the models was assessed using receiver operating characteristic (ROC) curves and differences were tested using DeLong's test.

RESULTS

Patients with a favorable outcome had a significantly lower AIV (median 12.0 mL (IQR 5.7-21.7) vs 18.8 mL (IQR 9.4-33.9), p<0.001). AIV was highly correlated with ASPECTS (rho=0.78, p<0.001) and weakly correlated with the National Institutes of Health Stroke Scale score at baseline (rho=0.22, p<0.001), and was an independent predictor of an unfavorable clinical outcome (adjusted OR 0.97, 95% CI 0.96 to 0.98). No significant difference was found between machine-learning models using either AIV or ASPECTS or both metrics for predicting a good clinical outcome (p>0.05).

CONCLUSION

AIV is an independent predictor of clinical outcome and presented a non-inferior performance compared with ASPECTS, without clear advantages for prognostic modelling.

An explainable machine learning model for predicting the outcome of ischemic stroke after mechanical thrombectomy

BACKGROUND

There is high variability in the clinical outcomes of patients with acute ischemic stroke (AIS) after mechanical thrombectomy (MT).

METHODS

217 consecutive patients with anterior circulation large vessel occlusion who underwent MT between August 2018 and January 2022 were analysed. The primary outcome was functional independence defined as a modified Rankin Scale score of 0-2 at 3 months. In the derivation cohort (August 2018 to December 2020), 7 ensemble ML models were trained on 70% of patients and tested on the remaining 30%. The model's performance was further validated on the temporal validation cohort (January 2021 to January 2022). The SHapley Additive exPlanations (SHAP) framework was applied to interpret the prediction model.

RESULTS

Derivation analyses generated a 9-item score (PFCML-MT) comprising age, National Institutes of Health Stroke Scale score, collateral status, and postoperative laboratory indices (albumin-to-globulin ratio, estimated glomerular filtration rate, blood neutrophil count, C-reactive protein, albumin and serum glucose levels). The area under the curve was 0.87 for the test set and 0.84 for the temporal validation cohort. SHAP analysis further determined the thresholds for the top continuous features. This model has been translated into an online calculator that is freely available to the public (https://zhelvyao-123-60-sial5s.streamlitapp.com).

CONCLUSIONS

Using ML and readily available features, we developed an ML model that can potentially be used in clinical practice to generate real-time, accurate predictions of the outcome of patients with AIS treated with MT.

Prognostic estimation for acute ischemic stroke patients undergoing mechanical thrombectomy within an extended therapeutic window using an interpretable machine learning model

Background

Mechanical thrombectomy (MT) is effective for acute ischemic stroke with large vessel occlusion (AIS-LVO) within an extended therapeutic window. However, successful reperfusion does not guarantee positive prognosis, with around 40-50% of cases yielding favorable outcomes. Preoperative prediction of patient outcomes is essential to identify those who may benefit from MT. Although machine learning (ML) has shown promise in handling variables with non-linear relationships in prediction models, its "black box" nature and the absence of ML models for extended-window MT prognosis remain limitations.

Objective

This study aimed to establish and select the optimal model for predicting extended-window MT outcomes, with the Shapley additive explanation (SHAP) approach used to enhance the interpretability of the selected model.

Methods

A retrospective analysis was conducted on 260 AIS-LVO patients undergoing extended-window MT. Selected patients were allocated into training and test sets at a 3:1 ratio following inclusion and exclusion criteria. Four ML classifiers and one logistic regression (Logit) model were constructed using pre-treatment variables from the training set. The optimal model was selected through comparative validation, with key features interpreted using the SHAP approach. The effectiveness of the chosen model was further evaluated using the test set.

Results

Of the 212 selected patients, 159 comprised the training and 53 the test sets. Extreme gradient boosting (XGBoost) showed the highest discrimination with an area under the curve (AUC) of 0.93 during validation, and maintained an AUC of 0.77 during testing. SHAP analysis identified ischemic core volume, baseline NHISS score, ischemic penumbra volume, ASPECTS, and patient age as the top five determinants of outcome prediction.

Conclusion

XGBoost emerged as the most effective for predicting the prognosis of AIS-LVO patients undergoing MT within the extended therapeutic window. SHAP interpretation improved its clinical confidence, paving the way for ML in clinical decision-making.

AutoML accurately predicts endovascular mechanical thrombectomy in acute large vessel ischemic stroke

Background and objective

Automated machine learning or autoML has been widely deployed in various industries. However, their adoption in healthcare, especially in clinical settings is constrained due to a lack of clear understanding and explainability. The aim of this study is to utilize autoML for the prediction of functional outcomes in patients who underwent mechanical thrombectomy and compare it with traditional ML models with a focus on the explainability of the trained models.

Methods

A total of 156 patients of acute ischemic stroke with Large Vessel Occlusion (LVO) who underwent mechanical thrombectomy within 24 h of stroke onset were included in the study. A total of 34 treatment variables including clinical, demographic, imaging, and procedure-related data were extracted. Various conventional machine learning models such as decision tree classifier, logistic regression, random forest, kNN, and SVM as well as various autoML models such as AutoGluon, MLJAR, Auto-Sklearn, TPOT, and H2O were used to predict the modified Rankin score (mRS) at the time of patient discharge and 3 months follow-up. The sensitivity, specificity, accuracy, and AUC for traditional ML and autoML models were compared.

Results

The autoML models outperformed the traditional ML models. For the prediction of mRS at discharge, the highest testing accuracy obtained by traditional ML models for the decision tree classifier was 74.11%, whereas for autoML which was obtained through AutoGluon, it showed an accuracy of 88.23%. Similarly, for mRS at 3 months, the highest testing accuracy of traditional ML was that of the SVM classifier at 76.5%, whereas that of autoML was 85.18% obtained through MLJAR. The 24-h ASPECTS score was the most important predictor for mRS at discharge whereas for prediction of mRS at 3 months, the most important factor was mRS at discharge.

Conclusion

Automated machine learning models based on multiple treatment variables can predict the functional outcome in patients more accurately than traditional ML models. The ease of clinical coding and deployment can assist clinicians in the critical decision-making process. We have developed a demo application which can be accessed at https://mrs-score-calculator.onrender.com/.

Deep Learning-based Assessment of Internal Carotid Artery Anatomy to Predict Difficult Intracranial Access in Endovascular Recanalization of Acute Ischemic Stroke

BACKGROUND

Endovascular thrombectomy (EVT) duration is an important predictor for neurological outcome. Recently it was shown that an angle of ≤ 90° of the internal carotid artery (ICA) is predictive for longer EVT duration. As manual angle measurement is not trivial and time-consuming, deep learning (DL) could help identifying difficult EVT cases in advance.

METHODS

We included 379 CT angiographies (CTA) of patients who underwent EVT between January 2016 and December 2020. Manual segmentation of 121 CTAs was performed for the aortic arch, common carotid artery (CCA) and ICA. These were used to train a nnUNet. The remaining 258 CTAs were segmented using the trained nnUNet with manual verification afterwards. Angles of left and right ICAs were measured resulting in two classes: acute angle ≤ 90° and > 90°. The segmentations together with angle measurements were used to train a convolutional neural network (CNN) determining the ICA angle. The performance was evaluated using Dice scores. The classification was evaluated using AUC and accuracy. Associations of ICA angle and procedural times was explored using median and Whitney‑U test.

RESULTS

Median EVT duration for cases with ICA angle > 90° was 48 min and with ≤ 90° was 64 min (p = 0.001). Segmentation evaluation showed Dice scores of 0.94 for the aorta and 0.86 for CCA/ICA, respectively. Evaluation of ICA angle determination resulted in an AUC of 0.92 and accuracy of 0.85.

CONCLUSION

The association between ICA angle and EVT duration could be verified and a DL-based method for semi-automatic assessment with the potential for full automation was developed. More anatomical features of interest could be examined in a similar fashion.

Preprocedural determination of an occlusion pathomechanism in endovascular treatment of acute stroke: a machine learning-based decision

OBJECTIVE

To evaluate whether an occlusion pathomechanism can be accurately determined by common preprocedural findings through a machine learning-based prediction model (ML-PM).

METHODS

A total of 476 patients with acute stroke who underwent endovascular treatment were retrospectively included to derive an ML-PM. For external validation, 152 patients from another tertiary stroke center were additionally included. An ML algorithm was trained to classify an occlusion pathomechanism into embolic or intracranial atherosclerosis. Various common preprocedural findings were entered into the model. Model performance was evaluated based on accuracy and area under the receiver operating characteristic curve (AUC). For practical utility, a decision flowchart was devised from an ML-PM with a few key preprocedural findings. Accuracy of the decision flowchart was validated internally and externally.

RESULTS

An ML-PM could determine an occlusion pathomechanism with an accuracy of 96.9% (AUC=0.95). In the model, CT angiography-determined occlusion type, atrial fibrillation, hyperdense artery sign, and occlusion location were top-ranked contributors. With these four findings only, an ML-PM had an accuracy of 93.8% (AUC=0.92). With a decision flowchart, an occlusion pathomechanism could be determined with an accuracy of 91.2% for the study cohort and 94.7% for the external validation cohort. The decision flowchart was more accurate than single preprocedural findings for determining an occlusion pathomechanism.

CONCLUSIONS

An ML-PM could accurately determine an occlusion pathomechanism with common preprocedural findings. A decision flowchart consisting of the four most influential findings was clinically applicable and superior to single common preprocedural findings for determining an occlusion pathomechanism.

Prediction of response to thrombolysis in acute stroke using neural network analysis of CT perfusion imaging

BACKGROUND

In ischaemic stroke patients undergoing reperfusion therapy, the amount of salvageable tissue, that is, extent of the ischaemic penumbra, predicts the clinical outcomes. CT perfusion (CTP) enables quantification of penumbral tissues to guide decision making, and current programmes have automated its analysis. More advanced machine learning techniques utilising the CTP maps may improve prediction beyond the ischaemic volume measures.

METHOD

We determined whether applying convolutional neural networks (CNN), a key machine learning technique in modelling image-label relationships, to post-processed CTP maps improved prediction of outcome, assessed by 3 months modified Rankin scale (mRS). Patients who underwent thrombolysis but not thrombectomy were included. CTP maps of a retrospective cohort of 230 patients with middle cerebral artery stroke were used to develop the model, which was validated in an independent cohort of 129 patients.

RESULTS

We constructed a CNN model that predicted a favourable post-thrombolysis outcome (mRS 0-2 at 3 months) with an area under receiver-operator characteristics curve (AUC) of 0.792 (95% CI, 0.707-0.877). This model outperformed a currently clinically used MISTAR software using previously validated thresholds (AUC = 0.583, 95% CI, 0.480-0.686) and a model modified using thresholds from the derivation cohort (AUC = 0.670, 95% CI, 0.571-0.769). By combining CNN-derived features and baseline demographic features, the prediction AUC was improved to 0.865 (95% CI, 0.794-0.936).

CONCLUSION

CNN improved prediction of post-thrombolysis outcome, and may be useful in selecting which patients benefit from thrombolysis.

Functional Outcome Prediction in Acute Ischemic Stroke Using a Fused Imaging and Clinical Deep Learning Model

BACKGROUND

Predicting long-term clinical outcome based on the early acute ischemic stroke information is valuable for prognostication, resource management, clinical trials, and patient expectations. Current methods require subjective decisions about which imaging features to assess and may require time-consuming postprocessing. This study's goal was to predict ordinal 90-day modified Rankin Scale (mRS) score in acute ischemic stroke patients by fusing a Deep Learning model of diffusion-weighted imaging images and clinical information from the acute period.

METHODS

A total of 640 acute ischemic stroke patients who underwent magnetic resonance imaging within 1 to 7 days poststroke and had 90-day mRS follow-up data were randomly divided into 70% (n=448) for model training, 15% (n=96) for validation, and 15% (n=96) for internal testing. Additionally, external testing on a cohort from Lausanne University Hospital (n=280) was performed to further evaluate model generalization. Accuracy for ordinal mRS, accuracy within ±1 mRS category, mean absolute prediction error, and determination of unfavorable outcome (mRS score >2) were evaluated for clinical only, imaging only, and 2 fused clinical-imaging models.

RESULTS

The fused models demonstrated superior performance in predicting ordinal mRS score and unfavorable outcome in both internal and external test cohorts when compared with the clinical and imaging models. For the internal test cohort, the top fused model had the highest area under the curve of 0.92 for unfavorable outcome prediction and the lowest mean absolute error (0.96 [95% CI, 0.77-1.16]), with the highest proportion of mRS score predictions within ±1 category (79% [95% CI, 71%-88%]). On the external Lausanne University Hospital cohort, the best fused model had an area under the curve of 0.90 for unfavorable outcome prediction and outperformed other models with an mean absolute error of 0.90 (95% CI, 0.79-1.01), and the highest percentage of mRS score predictions within ±1 category (83% [95% CI, 78%-87%]).

CONCLUSIONS

A Deep Learning-based imaging model fused with clinical variables can be used to predict 90-day stroke outcome with reduced subjectivity and user burden.

Novel inflammatory biomarkers associated with stroke severity: results from a cross-sectional stroke cohort study

BACKGROUND

Stroke is a leading cause of mortality and disability worldwide and its occurrence is expected to increase in the future. Blood biomarkers have proven their usefulness in identification and monitoring of the disease. Stroke severity is a major factor for estimation of prognosis and risk of recurrent events, but knowledge on respective blood biomarkers is still scarce. Stroke pathophysiology comprises a multitude of ischemia-induced inflammatory and immune mediated responses. Therefore, the assessment of an immune-related panel in correlation with stroke severity seems promising.

METHODS

In the present cross-sectional evaluation, a set of 92 blood biomarkers of a standardized immune panel were gathered (median 4.6 days after admission) and related to stroke severity measures, assessed at hospital admission of acute stroke patients. Multivariable logistic regression models were used to determine associations between biomarkers and modified Rankin Scale (mRS), linear regression models were used for associations with National Institute of Health Stroke Scale.

RESULTS

415 patients (mean age 69 years; 41% female) were included for biomarker analysis. C-type lectin domain family 4 member G (CLEC4G; OR = 2.89, 95% CI [1.49; 5.59], p_adj = 0.026, Cytoskeleton-associated protein 4 (CKAP4; OR = 2.38, 95% CI [1.43; 3.98], p_adj = 0.019), and Interleukin-6 (IL-6) (IL6; OR = 1.97, 95% CI [1.49; 2.62], p_adj < 0.001) were positively associated with stroke severity measured by mRS, while Lymphocyte antigen 75 (LY75; OR = 0.37, 95% CI [0.19; 0.73], p_adj = 0.049) and Integrin alpha-11 (ITGA11 OR = 0.24, 95% CI [0.14, 0.40] p_adj < 0.001) were inversely associated. When investigating the relationships with the NIHSS, IL-6 (β = 0.23, 95% CI [0.12, 0.33] p_adj = 0.001) and ITGA11 (β =  - 0.60, 95% CI [- 0.83, - 0.37] p_adj < 0.001) were significantly associated.

CONCLUSIONS

Higher relative concentrations of plasma CLEC4G, CKAP4, and IL-6 were associated with higher stroke severity, whereas LY75 and ITGA11 showed an inverse association. Future research might show a possible use as therapeutic targets and application in individual risk assessments.

Machine learning prediction of motor function in chronic stroke patients: a systematic review and meta-analysis

Background

Recent studies have reported that machine learning (ML), with a relatively strong capacity for processing non-linear data and adaptive ability, could improve the accuracy and efficiency of prediction. The article summarizes the published studies on ML models that predict motor function 3-6 months post-stroke.

Methods

A systematic literature search was conducted in PubMed, Embase, Cochorane and Web of Science as of April 3, 2023 for studies on ML prediction of motor function in stroke patients. The quality of the literature was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). A random-effects model was preferred for meta-analysis using R4.2.0 because of the different variables and parameters.

Results

A total of 44 studies were included in this meta-analysis, involving 72,368 patients and 136 models. Models were categorized into subgroups according to the predicted outcome Modified Rankin Scale cut-off value and whether they were constructed based on radiomics. C-statistics, sensitivity, and specificity were calculated. The random-effects model showed that the C-statistics of all models were 0.81 (95% CI: 0.79; 0.83) in the training set and 0.82 (95% CI: 0.80; 0.85) in the validation set. According to different Modified Rankin Scale cut-off values, C-statistics of ML models predicting Modified Rankin Scale>2(used most widely) in stroke patients were 0.81 (95% CI: 0.78; 0.84) in the training set, and 0.84 (95% CI: 0.81; 0.87) in the validation set. C-statistics of radiomics-based ML models in the training set and validation set were 0.81 (95% CI: 0.78; 0.84) and 0.87 (95% CI: 0.83; 0.90), respectively.

Conclusion

ML can be used as an assessment tool for predicting the motor function in patients with 3-6 months of post-stroke. Additionally, the study found that ML models with radiomics as a predictive variable were also demonstrated to have good predictive capabilities. This systematic review provides valuable guidance for the future optimization of ML prediction systems that predict poor motor outcomes in stroke patients.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022335260, identifier: CRD42022335260.

Artificial Intelligence for Clinical Decision Support in Acute Ischemic Stroke: A Systematic Review

BACKGROUND

Established randomized trial-based parameters for acute ischemic stroke group patients into generic treatment groups, leading to attempts using various artificial intelligence (AI) methods to directly correlate patient characteristics to outcomes and thereby provide decision support to stroke clinicians. We review AI-based clinical decision support systems in the development stage, specifically regarding methodological robustness and constraints for clinical implementation.

METHODS

Our systematic review included full-text English language publications proposing a clinical decision support system using AI techniques for direct decision support in acute ischemic stroke cases in adult patients. We (1) describe data and outcomes used in those systems, (2) estimate the systems' benefits compared with traditional stroke diagnosis and treatment, and (3) reported concordance with reporting standards for AI in healthcare.

RESULTS

One hundred twenty-one studies met our inclusion criteria. Sixty-five were included for full extraction. In our sample, utilized data sources, methods, and reporting practices were highly heterogeneous.

CONCLUSIONS

Our results suggest significant validity threats, dissonance in reporting practices, and challenges to clinical translation. We outline practical recommendations for the successful implementation of AI research in acute ischemic stroke treatment and diagnosis.

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.

Big Data in Stroke: How to Use Big Data to Make the Next Management Decision

The last decade has seen significant advances in the accumulation of medical data, the computational techniques to analyze that data, and corresponding improvements in management. Interventions such as thrombolytics and mechanical thrombectomy improve patient outcomes after stroke in selected patients; however, significant gaps remain in our ability to select patients, predict complications, and understand outcomes. Big data and the computational methods needed to analyze it can address these gaps. For example, automated analysis of neuroimaging to estimate the volume of brain tissue that is ischemic and salvageable can help triage patients for acute interventions. Data-intensive computational techniques can perform complex risk calculations that are too cumbersome to be completed by humans, resulting in more accurate and timely prediction of which patients require increased vigilance for adverse events such as treatment complications. To handle the accumulation of complex medical data, a variety of advanced computational techniques referred to as machine learning and artificial intelligence now routinely complement traditional statistical inference. In this narrative review, we explore data-intensive techniques in stroke research, how it has informed the management of stroke patients, and how current work could shape clinical practice in the future.

A DWI-based radiomics-clinical machine learning model to preoperatively predict the futile recanalization after endovascular treatment of acute basilar artery occlusion patients

OBJECTIVE

To develop an effective machine learning model to preoperatively predict the occurrence of futile recanalization (FR) of acute basilar artery occlusion (ABAO) patients with endovascular treatment (EVT).

MATERIALS AND METHODS

Data from 132 ABAO patients (109 male [82.6 %]; mean age ± standard deviation, 59.1 ± 12.5 years) were randomly divided into the training (n = 106) and test cohort (n = 26) with a ratio of 8:2. FR is defined as a poor outcome [modified Rankin Scale (mRS) 4-6] despite a successful recanalization [modified Thrombolysis in Cerebral Infarction (mTICI) ≥ 2b]. A total of 1130 radiomics features were extracted from diffusion-weighted imaging (DWI) images. The least absolute shrinkage and selection operator (LASSO) regression method was applicated to select features. Support vector machine (SVM) was applicated to construct radiomics and clinical models. Finally, a radiomics-clinical model that combined clinical with radiomics features was developed. The models were evaluated by receiver operating characteristic (ROC) curve and decision curve.

RESULTS

The area under the receiver operating characteristic (ROC) curve (AUC) of the radiomics-clinical model was 0.897 (95 % confidence interval, 0.837-0.958) in the training cohort and 0.935 (0.833-1.000) in the test cohort. The AUC of the radiomics model was 0.887 (0.824-0.951) in the training cohort and 0.840 (0.680-1.000) in the test cohort. The AUC of the clinical model was 0.746 (0.652-0.840) in the training cohort and 0.766 (0.569-0.964) in the test cohort. The AUC of the radiomics-clinical model was significantly larger than the clinical model (p = 0.016). A radiomics-clinical nomogram was developed. The decision curve analysis indicated its clinical usefulness.

CONCLUSION

The DWI-based radiomics-clinical machine learning model achieved satisfactory performance in predicting the FR of ABAO patients preoperatively.

Radiomics Analysis of Diffusion-Weighted Imaging and Long-Term Unfavorable Outcomes Risk for Acute Stroke

BACKGROUND

Diffusion-weighted imaging radiomics could be used as prognostic biomarkers in acute ischemic stroke. We aimed to identify a clinical and diffusion-weighted imaging radiomics model for individual unfavorable outcomes risk assessment in acute ischemic stroke.

METHODS

A total of 1716 patients with acute ischemic stroke from 2 centers were divided into a training cohort and a validation cohort. Patient outcomes were measured with the modified Rankin Scale score. An unfavorable outcome was defined as a modified Rankin Scale score greater than 2. The primary end point was all-cause mortality or outcomes 1 year after stroke. The MRI-DRAGON score was calculated based on previous publications. We extracted and selected the infarct features on diffusion-weighted imaging to construct a radiomic signature. The clinic-radiomics signature was built by measuring the Cox proportional risk regression score (CrrScore) and compared with the MRI-DRAGON score and the ClinicScore. CrrScore model performance was estimated by 1-year unfavorable outcomes prediction.

RESULTS

A high radiomic signature predicted a higher probability of unfavorable outcomes than a low radiomic signature in the training (hazard ratio, 3.19 [95% CI, 2.51-4.05]; P<0.0001) and validation (hazard ratio, 3.25 [95% CI, 2.20-4.80]; P<0.0001) cohorts. The diffusion-weighted imaging Alberta Stroke Program Early CT Score, age, glucose level before therapy, National Institutes of Health Stroke Scale score on admission, glycated hemoglobin' radiomic signature, hemorrhagic infarction, and malignant cerebral edema were associated with an unfavorable outcomes risk after multivariable adjustment. A CrrScore nomogram was developed to predict outcomes and had the best performance in the training (area under the curve, 0.862) and validation cohorts (area under the curve, 0.858). The CrrScore model time-dependent areas under the curve of the probability of unfavorable outcomes at 1 year in the training and validation cohorts were 0.811 and 0.801, respectively.

CONCLUSIONS

The CrrScore model allows the accurate prediction of patients with acute ischemic stroke outcomes and can potentially guide rehabilitation therapies for patients with different risks of unfavorable outcomes.

Evaluation of Blood Biomarkers and Parameters for the Prediction of Stroke Survivors' Functional Outcome upon Discharge Utilizing Explainable Machine Learning

Despite therapeutic advancements, stroke remains a leading cause of death and long-term disability. The quality of current stroke prognostic models varies considerably, whereas prediction models of post-stroke disability and mortality are restricted by the sample size, the range of clinical and risk factors and the clinical applicability in general. Accurate prognostication can ease post-stroke discharge planning and help healthcare practitioners individualize aggressive treatment or palliative care, based on projected life expectancy and clinical course. In this study, we aimed to develop an explainable machine learning methodology to predict functional outcomes of stroke patients at discharge, using the Modified Rankin Scale (mRS) as a binary classification problem. We identified 35 parameters from the admission, the first 72 h, as well as the medical history of stroke patients, and used them to train the model. We divided the patients into two classes in two approaches: "Independent" vs. "Non-Independent" and "Non-Disability" vs. "Disability". Using various classifiers, we found that the best models in both approaches had an upward trend, with respect to the selected biomarkers, and achieved a maximum accuracy of 88.57% and 89.29%, respectively. The common features in both approaches included: age, hemispheric stroke localization, stroke localization based on blood supply, development of respiratory infection, National Institutes of Health Stroke Scale (NIHSS) upon admission and systolic blood pressure levels upon admission. Intubation and C-reactive protein (CRP) levels upon admission are additional features for the first approach and Erythrocyte Sedimentation Rate (ESR) levels upon admission for the second. Our results suggest that the said factors may be important predictors of functional outcomes in stroke patients.

Machine learning and acute stroke imaging

BACKGROUND

In recent years, machine learning (ML) has had notable success in providing automated analyses of neuroimaging studies, and its role is likely to increase in the future. Thus, it is paramount for clinicians to understand these approaches, gain facility with interpreting ML results, and learn how to assess algorithm performance.

OBJECTIVE

To provide an overview of ML, present its role in acute stroke imaging, discuss methods to evaluate algorithms, and then provide an assessment of existing approaches.

METHODS

In this review, we give an overview of ML techniques commonly used in medical imaging analysis and methods to evaluate performance. We then review the literature for relevant publications. Searches were run in November 2021 in Ovid Medline and PubMed. Inclusion criteria included studies in English reporting use of artificial intelligence (AI), machine learning, or similar techniques in the setting of, and in applications for, acute ischemic stroke or mechanical thrombectomy. Articles that included image-level data with meaningful results and sound ML approaches were included in this discussion.

RESULTS

Many publications on acute stroke imaging, including detection of large vessel occlusion, detection and quantification of intracranial hemorrhage and detection of infarct core, have been published using ML methods. Imaging inputs have included non-contrast head CT, CT angiograph and MRI, with a range of performances. We discuss and review several of the most relevant publications.

CONCLUSIONS

ML in acute ischemic stroke imaging has already made tremendous headway. Additional applications and further integration with clinical care is inevitable. Thus, facility with these approaches is critical for the neurointerventional clinician.

A Deep Learning-Based Automatic Collateral Assessment in Patients with Acute Ischemic Stroke

This study aimed to develop a supervised deep learning (DL) model for grading collateral status from dynamic susceptibility contrast magnetic resonance perfusion (DSC-MRP) images from patients with large vessel occlusion (LVO) acute ischemic stroke (AIS) and compare its performance against experts' manual grading. Among consecutive LVO-AIS at three medical center sites, DSC-MRP data were processed to generate collateral flow maps consisting of arterial, capillary, and venous phases. With the use of expert readings as a reference, a DL model was developed to analyze collateral status with output classified into good and poor grades. The resulting model was externally validated in a later-collected population from one medical center site. The model was trained on 255 patients and externally validated on 72 patients. In the all-site internal validation population, DL grading of good collateral probability yielded a c statistic of 0.91; in the external validation population, the c statistic was 0.85. In the external validation population, there was moderate agreement between the experts' grades and DL grades (kappa = 0.53, 95% CI = 0.32-0.73, p < 0.0001). Day 7 infarct growth volume was higher in DL-graded poor collateral group than good collateral group patients (median volume [26 mL vs. 6 mL], p = 0.01) in patients with successful reperfusion (modified treatment in cerebral infarction (mTICI) = 2b-3). In all patients with a 90-day modified Rankin Scale (mRS) score, there was a shift to more favorable outcomes in the good collateral group, with a common odds ratio of 2.99 (95% CI = 1.89-4.76, p < 0.0001). The DL-based collateral grading was in good agreement with expert manual grading in both development and validation populations. After exclusion of patients with large infarct volume, early reperfusion is more likely to benefit patients with the poor collateral flow, and the DL method has the potential to aid the assessment of collateral status.

Prediction of Functional Outcome in Stroke Patients with Proximal Middle Cerebral Artery Occlusions Using Machine Learning Models

At present, clinicians are expected to manage a large volume of complex clinical, laboratory, and imaging data, necessitating sophisticated analytic approaches. Machine learning-based models can use this vast amount of data to create forecasting models. We aimed to predict short- and medium-term functional outcomes in acute ischemic stroke (AIS) patients with proximal middle cerebral artery (MCA) occlusions using machine learning models with clinical, laboratory, and quantitative imaging data as inputs. Included were consecutive AIS patients with MCA M1 and proximal M2 occlusions. The XGBoost, LightGBM, CatBoost, and Random Forest were used to predict the outcome. Minimum redundancy maximum relevancy was used for selecting features. The primary outcomes were the National Institutes of Health Stroke Scale (NIHSS) shift and the modified Rankin Score (mRS) at 90 days. The algorithm with the highest area under the receiver operating characteristic curve (AUROC) for predicting the favorable and unfavorable outcome groups at 90 days was LightGBM. Random Forest had the highest AUROC when predicting the favorable and unfavorable groups based on the NIHSS shift. Using clinical, laboratory, and imaging parameters in conjunction with machine learning, we accurately predicted the functional outcome of AIS patients with proximal MCA occlusions.

Identification of anoikis-related genes classification patterns and immune infiltration characterization in ischemic stroke based on machine learning

Introduction

Ischemic stroke (IS) is a type of stroke that leads to high mortality and disability. Anoikis is a form of programmed cell death. When cells detach from the correct extracellular matrix, anoikis disrupts integrin junctions, thus preventing abnormal proliferating cells from growing or attaching to an inappropriate matrix. Although there is growing evidence that anoikis regulates the immune response, which makes a great contribution to the development of IS, the role of anoikis in the pathogenesis of IS is rarely explored.

Methods

First, we downloaded GSE58294 set and GSE16561 set from the NCBI GEO database. And 35 anoikis-related genes (ARGs) were obtained from GSEA website. The CIBERSORT algorithm was used to estimate the relative proportions of 22 infiltrating immune cell types. Next, consensus clustering method was used to classify ischemic stroke samples. In addition, we used least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) algorithms to screen the key ARGs in ischemic stroke. Next, we performed receiver operating characteristics (ROC) analysis to assess the accuracy of each diagnostic gene. At the same time, the nomogram was constructed to diagnose IS by integrating trait genes. Then, we analyzed the correlation between gene expression and immune cell infiltration of the diagnostic genes in the combined database. And gene ontology (GO) and kyoto encyclopedia of genes and genomes (KEGG) analysis were performed on these genes to explore differential signaling pathways and potential functions, as well as the construction and visualization of regulatory networks using NetworkAnalyst and Cytoscape. Finally, we investigated the expression pattern of ARGs in IS patients across age or gender.

Results

Our study comprehensively analyzed the role of ARGs in IS for the first time. We revealed the expression profile of ARGs in IS and the correlation with infiltrating immune cells. And The results of consensus clustering analysis suggested that we can classify IS patients into two clusters. The machine learning analysis screened five signature genes, including AKT1, BRMS1, PTRH2, TFDP1 and TLE1. We also constructed nomogram models based on the five risk genes and evaluated the immune infiltration correlation, gene-miRNA, gene-TF and drug-gene interaction regulatory networks of these signature genes. The expression of ARGs did not differ by sex or age.

Discussion

This study may provide a beneficial reference for further elucidating the pathogenesis of IS, and render new ideas for drug screening, individualized therapy and immunotherapy of IS.

Neuroimaging of Acute Ischemic Stroke: Multimodal Imaging Approach for Acute Endovascular Therapy

Advances in acute ischemic stroke (AIS) treatment have been contingent on innovations in neuroimaging. Neuroimaging plays a pivotal role in the diagnosis and prognosis of ischemic stroke and large vessel occlusion, enabling triage decisions in the emergent care of the stroke patient. Current imaging protocols for acute stroke are dependent on the available resources and clinicians' preferences and experiences. In addition, differential application of neuroimaging in medical decision-making, and the rapidly growing evidence to support varying paradigms have outpaced guideline-based recommendations for selecting patients to receive intravenous or endovascular treatment. In this review, we aimed to discuss the various imaging modalities and approaches used in the diagnosis and treatment of AIS.

Machine Learning Models for Predicting Early Neurological Deterioration and Risk Classification of Acute Ischemic Stroke

This study aimed to create machine learning models for predicting early neurological deterioration and risk classification in acute ischemic stroke (AIS) before intravenous thrombolysis (IVT). The study included 704 AIS patients categorized into END and non-END groups. The least absolute shrinkage and selection operator (LASSO) regression was employed to select the best predictors from clinical indicators, leading to the creation of Model 1. Univariate and multivariate logistic regression analyses identified independent predictive factors for END from inflammatory cell ratios. These factors were combined with clinical indicators, forming Model 2. Receiver operating characteristic (ROC) curves assessed the models' predictive performance. Key variables for Model 1 included the NIHSS score, systolic blood pressure, and lymphocyte percentage. Neutrophil-to-Lymphocyte ratio, Platelet-to-Neutrophil ratio, and Platelet-to-Lymphocyte ratio independently predicted END. Model 1 exhibited moderate predictive ability (AUC 0.721 in training, AUC 0.635 in test). Model 2, which integrated clinical indicators and inflammatory cell ratios, demonstrated strong performance in both training (AUC 0.862) and test (AUC 0.816). Machine learning models, combining clinical indicators and inflammatory cell ratios before IVT, accurately predict END and associated risk in AIS.

Predicting functional outcome in acute ischemic stroke patients after endovascular treatment by machine learning

Background

Endovascular therapy (EVT) was the standard treatment for acute ischemic stroke with large vessel occlusion. Prognosis after EVT is always a major concern. Here, we aimed to explore a predictive model for patients after EVT.

Method

A total of 156 patients were retrospectively enrolled. The primary outcome was functional dependence (defined as a 90-day modified Rankin Scale score ≤ 2). Least absolute shrinkage and selection operator and univariate logistic regression were used to select predictive factors. Various machine learning algorithms, including multivariate logistic regression, linear discriminant analysis, support vector machine, k-nearest neighbors, and decision tree algorithms, were applied to construct prognostic models.

Result

Six predictive factors were selected, namely, age, baseline National Institute of Health Stroke Scale (NIHSS) score, Alberta Stroke Program Early CT (ASPECT) score, modified thrombolysis in cerebral infarction score, symptomatic intracerebral hemorrhage (sICH), and complications (pulmonary infection, gastrointestinal bleeding, and cardiovascular events). Based on these variables, various models were constructed and showed good discrimination. Finally, a nomogram was constructed by multivariate logistic regression and showed a good performance.

Conclusion

Our nomogram, which was composed of age, baseline NIHSS score, ASPECT score, recanalization status, sICH, and complications, showed a very good performance in predicting outcome after EVT.

The Combination of Whole-Brain Features and Local-Lesion Features in DSC-PWI May Improve Ischemic Stroke Outcome Prediction

Accurate and reliable outcome predictions can help evaluate the functional recovery of ischemic stroke patients and assist in making treatment plans. Given that recovery factors may be hidden in the whole-brain features, this study aims to validate the role of dynamic radiomics features (DRFs) in the whole brain, DRFs in local ischemic lesions, and their combination in predicting functional outcomes of ischemic stroke patients. First, the DRFs in the whole brain and the DRFs in local lesions of dynamic susceptibility contrast-enhanced perfusion-weighted imaging (DSC-PWI) images are calculated. Second, the least absolute shrinkage and selection operator (Lasso) is used to generate four groups of DRFs, including the outstanding DRFs in the whole brain (Lasso (WB)), the outstanding DRFs in local lesions (Lasso (LL)), the combination of them (combined DRFs), and the outstanding DRFs in the combined DRFs (Lasso (combined)). Then, the performance of the four groups of DRFs is evaluated to predict the functional recovery in three months. As a result, Lasso (combined) in the four groups achieves the best AUC score of 0.971, which improves the score by 8.9% compared with Lasso (WB), and by 3.5% compared with Lasso (WB) and combined DRFs. In conclusion, the outstanding combined DRFs generated from the outstanding DRFs in the whole brain and local lesions can predict functional outcomes in ischemic stroke patients better than the single DRFs in the whole brain or local lesions.

Machine learning based outcome prediction of large vessel occlusion of the anterior circulation prior to thrombectomy in patients with wake-up stroke

PURPOSE

Outcome prediction of large vessel occlusion of the anterior circulation in patients with wake-up stroke is important to identify patients that will benefit from thrombectomy. Currently, mismatch concepts that require MRI or CT-Perfusion (CTP) are recommended to identify these patients. We evaluated machine learning algorithms in their ability to discriminate between patients with favorable (defined as a modified Rankin Scale (mRS) score of 0-2) and unfavorable (mRS 3-6) outcome and between patients with poor (mRS5-6) and non-poor (mRS 0-4) outcome.

METHODS

Data of 8395 patients that were treated between 2018 and 2020 from the nationwide registry of the German Society for Neuroradiology was retrospectively analyzed. Five models were trained with clinical variables and Alberta Stroke Program Early CT Score (ASPECTS). The model with the highest accuracy was validated with a test dataset with known stroke onset and with a test dataset that consisted only of wake-up strokes.

RESULTS

2419 patients showed poor and 3310 patients showed favorable outcome. The best performing Random Forest model achieved a sensitivity of 0.65, a specificity of 0.81 and an AUC of 0.79 on the test dataset of patients with wake-up stroke in the classification analysis between favorable and unfavorable outcome and a sensitivity of 0.42, a specificity of 0.83 and an AUC of 0.72 in the classification analysis between poor and non-poor outcome.

CONCLUSION

Machine learning algorithms have the potential to aid in the decision making for thrombectomy in patients with wake-up stroke especially in hospitals, where emergency CTP or MRI imaging is not available.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

Assessment of Primary Collateral Grades Based on the Integrity of Willis' Circle: Predicting the Prognosis of Acute Intracranial Internal Carotid Artery Occlusion Before Thrombectomy

OBJECTIVE

Endovascular mechanical thrombectomy (EVMT) has shown significant efficacy in improving neurological functions in patients with intracranial internal carotid artery occlusion (IICAO), but its clinical outcomes are variable. We examined the relationship between favorable clinical outcomes after EVMT in IICAO and a set of predictors.

METHODS

In this retrospective study, 189 patients with IICAO treated by EVMT at 3 centers from November 2015 to December 2020 were included and analyzed. Non-contrast computed tomography and computed tomography angiography were evaluated on admission. The morphology of IICAO was categorized into Ia, Ib, L, or T types, depending on the involvement of the posterior communicating artery origin, proximal anterior cerebral artery, and middle cerebral artery. The Willis' circle was categorized as integrated or compromised Willis' circle. In combination with the involvement of the IICAO and the integrity of Willis' circle, we used the primary collateral grade (PCG) to describe the presence of functional Willisian collaterals. Baseline data including demographics, characteristics, vascular risk factors, and initial National Institutes of Health Stroke Scale scores were collected. Hemorrhagic transformation was evaluated using the 24-hour non-contrast computed tomography after EVMT. Favorable outcomes based on modified Rankin scale, were defined as 0-2 at 90 days.

RESULTS

A total of 189 patients were included (median age, 69 years; 126 male [66.7%]). 104 patients [55.0%] showed reperfusion after EVMT, but 72 patients [38.1%] achieved favorable outcomes at 90 days. The mortality rate of type Ib was significantly higher than that with type Ia (χ² = 14.21, P = 0.001). The outcome with different structure of Willis' circle was not statistically different between the 2 groups. A multivariate logistic regression analysis showed that IICAO T-type (odds ratio, 0.028 [95% confidence interval: 0.323-3.829], P = 0.042) and PCG 2 (odds ratio 9.427[95% confidence interval:1.863-47.698], P = 0.007) were predictors of favorable outcomes.

CONCLUSIONS

Evaluation of PCG by determining the type of IICAO and the integrity of Willis' circle may serve as a valuable indicator for the prognosis and as an essential reference for screening patients before EVMT.

Artificial intelligence-based methods for fusion of electronic health records and imaging data

Healthcare data are inherently multimodal, including electronic health records (EHR), medical images, and multi-omics data. Combining these multimodal data sources contributes to a better understanding of human health and provides optimal personalized healthcare. The most important question when using multimodal data is how to fuse them-a field of growing interest among researchers. Advances in artificial intelligence (AI) technologies, particularly machine learning (ML), enable the fusion of these different data modalities to provide multimodal insights. To this end, in this scoping review, we focus on synthesizing and analyzing the literature that uses AI techniques to fuse multimodal medical data for different clinical applications. More specifically, we focus on studies that only fused EHR with medical imaging data to develop various AI methods for clinical applications. We present a comprehensive analysis of the various fusion strategies, the diseases and clinical outcomes for which multimodal fusion was used, the ML algorithms used to perform multimodal fusion for each clinical application, and the available multimodal medical datasets. We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We searched Embase, PubMed, Scopus, and Google Scholar to retrieve relevant studies. After pre-processing and screening, we extracted data from 34 studies that fulfilled the inclusion criteria. We found that studies fusing imaging data with EHR are increasing and doubling from 2020 to 2021. In our analysis, a typical workflow was observed: feeding raw data, fusing different data modalities by applying conventional machine learning (ML) or deep learning (DL) algorithms, and finally, evaluating the multimodal fusion through clinical outcome predictions. Specifically, early fusion was the most used technique in most applications for multimodal learning (22 out of 34 studies). We found that multimodality fusion models outperformed traditional single-modality models for the same task. Disease diagnosis and prediction were the most common clinical outcomes (reported in 20 and 10 studies, respectively) from a clinical outcome perspective. Neurological disorders were the dominant category (16 studies). From an AI perspective, conventional ML models were the most used (19 studies), followed by DL models (16 studies). Multimodal data used in the included studies were mostly from private repositories (21 studies). Through this scoping review, we offer new insights for researchers interested in knowing the current state of knowledge within this research field.

Quantitative collateral score for the prediction of clinical outcomes in stroke patients: Better than visual grading

Objectives

To identify preoperative prognostic factors for acute ischemic stroke (AIS) patients receiving mechanical thrombectomy (MT) and compare the performance of quantitative collateral score (qCS) and visual collateral score (vCS) in outcome prediction.

Methods

Fifty-five patients with AIS receiving MT were retrospectively enrolled. qCS was defined as the percentage of the volume of collaterals of both hemispheres. Based on the dichotomous outcome assessed using a 90-day modified Rankin Scale (mRS), we compared qCS, vCS, age, sex, National Institute of Health stroke scale score, etiological subtype, platelet count, international normalized ratio, glucose levels, and low-density lipoprotein cholesterol (LDL-C) levels between favorable and unfavorable outcome groups. Logistic regression analysis was performed to determine the effect on the clinical outcome. The discriminatory power of qCS, vCS, and their combination with cofounders for determining favorable outcomes was tested with the area under the receiver-operating characteristic curve (AUC).

Results

vCS, qCS, LDL-C, and age could all predict clinical outcomes. qCS is superior over vCS in predicting favorable outcomes with a relatively higher AUC value (qCS vs. vCS: 0.81 vs. 0.74) and a higher sensitivity rate (qCS vs. vCS: 72.7% vs. 40.9%). The prediction power of qCS + LDL-C + age was best with an AUC value of 0.91, but the accuracy was just increased slightly compared to that of qCS alone.

Conclusion

Collateral scores, LDL-C and age were independent prognostic predictors for patients with AIS receiving MT; qCS was a better predictor than vCS. Furthermore, qCS + LDL-C + age offers a strong prognostic prediction power and qCS alone was another good choice for predicting clinical outcome.

Predicting futile recanalization, malignant cerebral edema, and cerebral herniation using intelligible ensemble machine learning following mechanical thrombectomy for acute ischemic stroke

Purpose

To establish an ensemble machine learning (ML) model for predicting the risk of futile recanalization, malignant cerebral edema (MCE), and cerebral herniation (CH) in patients with acute ischemic stroke (AIS) who underwent mechanical thrombectomy (MT) and recanalization.

Methods

This prospective study included 110 patients with premorbid mRS ≤ 2 who met the inclusion criteria. Futile recanalization was defined as a 90-day modified Rankin Scale score &gt;2. Clinical and imaging data were used to construct five ML models that were fused into a logistic regression algorithm using the stacking method (LR-Stacking). We added the Shapley Additive Explanation method to display crucial factors and explain the decision process of models for each patient. Prediction performances were compared using area under the receiver operating characteristic curve (AUC), F1-score, and decision curve analysis (DCA).

Results

A total of 61 patients (55.5%) experienced futile recanalization, and 34 (30.9%) and 22 (20.0%) patients developed MCE and CH, respectively. In test set, the AUCs for the LR-Stacking model were 0.949, 0.885, and 0.904 for the three outcomes mentioned above. The F1-scores were 0.882, 0.895, and 0.909, respectively. The DCA showed that the LR-Stacking model provided more net benefits for predicting MCE and CH. The most important factors were the hypodensity volume and proportion in the corresponding vascular supply area.

Conclusion

Using the ensemble ML model to analyze the clinical and imaging data of AIS patients with successful recanalization at admission and within 24 h after MT allowed for accurately predicting the risks of futile recanalization, MCE, and CH.

A machine learning approach for predicting suicidal ideation in post stroke patients

Currently, the identification of stroke patients with an increased suicide risk is mainly based on self‐report questionnaires, and this method suffers from a lack of objectivity. This study developed and validated a suicide ideation (SI) prediction model using clinical data and identified SI predictors. Significant variables were selected through traditional statistical analysis based on retrospective data of 385 stroke patients; the data were collected from October 2012 to March 2014. The data were then applied to three boosting models (Xgboost, CatBoost, and LGBM) to identify the comparative and best performing models. Demographic variables that showed significant differences between the two groups were age, onset, type, socioeconomic, and education level. Additionally, functional variables also showed a significant difference with regard to ADL and emotion (p < 0.05). The CatBoost model (0.900) showed higher performance than the other two models; and depression, anxiety, self-efficacy, and rehabilitation motivation were found to have high importance. Negative emotions such as depression and anxiety showed a positive relationship with SI and rehabilitation motivation and self-efficacy displayed an inverse relationship with SI. Machine learning-based SI models could augment SI prevention by helping rehabilitation and medical professionals identify high-risk stroke patients in need of SI prevention intervention.

A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke

Background: The ability to accurately detect ischemic stroke and predict its neurological recovery is of great clinical value. This study intended to evaluate the performance of whole-brain dynamic radiomics features (DRF) for ischemic stroke detection, neurological impairment assessment, and outcome prediction. Methods: The supervised feature selection (Lasso) and unsupervised feature-selection methods (five-feature dimension-reduction algorithms) were used to generate four experimental groups with DRF in different combinations. Ten machine learning models were used to evaluate their performance by ten-fold cross-validation. Results: In experimental group_A, the best AUCs (0.873 for stroke detection, 0.795 for NIHSS assessment, and 0.818 for outcome prediction) were obtained by outstanding DRF selected by Lasso, and the performance of significant DRF was better than the five-feature dimension-reduction algorithms. The selected outstanding dimension-reduction DRF in experimental group_C obtained a better AUC than dimension-reduction DRF in experimental group_A but were inferior to the outstanding DRF in experimental group_A. When combining the outstanding DRF with each dimension-reduction DRF (experimental group_B), the performance can be improved in ischemic stroke detection (best AUC = 0.899) and NIHSS assessment (best AUC = 0.835) but failed in outcome prediction (best AUC = 0.806). The performance can be further improved when combining outstanding DRF with outstanding dimension-reduction DRF (experimental group_D), achieving the highest AUC scores in all three evaluation items (0.925 for stroke detection, 0.853 for NIHSS assessment, and 0.828 for outcome prediction). By the method in this study, comparing the best AUC of Ft-test in experimental group_A and the best_AUC in experimental group_D, the AUC in stroke detection increased by 19.4% (from 0.731 to 0.925), the AUC in NIHSS assessment increased by 20.1% (from 0.652 to 0.853), and the AUC in prognosis prediction increased by 14.9% (from 0.679 to 0.828). This study provided a potential clinical tool for detailed clinical diagnosis and outcome prediction before treatment.

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

Introduction

Machine learning (ML) methods are being increasingly applied to prognostic prediction for stroke patients with large vessel occlusion (LVO) treated with endovascular thrombectomy. This systematic review aims to summarize ML-based pre-thrombectomy prognostic models for LVO stroke and identify key research gaps.

Methods

Literature searches were performed in Embase, PubMed, Web of Science, and Scopus. Meta-analyses of the area under the receiver operating characteristic curves (AUCs) of ML models were conducted to synthesize model performance.

Results

Sixteen studies describing 19 models were eligible. The predicted outcomes include functional outcome at 90 days, successful reperfusion, and hemorrhagic transformation. Functional outcome was analyzed by 10 conventional ML models (pooled AUC=0.81, 95% confidence interval [CI]: 0.77–0.85, AUC range: 0.68–0.93) and four deep learning (DL) models (pooled AUC=0.75, 95% CI: 0.70–0.81, AUC range: 0.71–0.81). Successful reperfusion was analyzed by three conventional ML models (pooled AUC=0.72, 95% CI: 0.56–0.88, AUC range: 0.55–0.88) and one DL model (AUC=0.65, 95% CI: 0.62–0.68).

Conclusions

Conventional ML and DL models have shown variable performance in predicting post-treatment outcomes of LVO without generally demonstrating superiority compared to existing prognostic scores. Most models were developed using small datasets, lacked solid external validation, and at high risk of potential bias. There is considerable scope to improve study design and model performance. The application of ML and DL methods to improve the prediction of prognosis in LVO stroke, while promising, remains nascent.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021266524, identifier CRD42021266524

[Artificial intelligence in orthopaedic and trauma surgery imaging]

Artificial intelligence (AI) is playing an increasing role in radiological imaging in orthopaedics and trauma surgery. The algorithms available to date are predominantly used in the detection of (occult) fractures and in length and angle measurements in conventional X‑ray images. However, current AI solutions also enable the analysis and pattern recognition of CT datasets, e.g. in the detection of rib or vertebral body fractures. A special application is EOS™ (ATEC Spine Group, Paris, France), which enables a 3‑D simulation of the axial skeleton and semi-automatic length and angle calculations based on a digital 2‑D X‑ray image. In this paper, the current spectrum of AI applications for orthopaedics and trauma surgery is presented and discussed.

Machine learning to predict futile recanalization of large vessel occlusion before and after endovascular thrombectomy

Background and purpose

Futile recanalization occurs when the endovascular thrombectomy (EVT) is a technical success but fails to achieve a favorable outcome. This study aimed to use machine learning (ML) algorithms to develop a pre-EVT model and a post-EVT model to predict the risk of futile recanalization and to provide meaningful insights to assess the prognostic factors associated with futile recanalization.

Methods

Consecutive acute ischemic stroke patients with large vessel occlusion (LVO) undergoing EVT at the National Advanced Stroke Center of Nanjing First Hospital (China) between April 2017 and May 2021 were analyzed. The baseline characteristics and peri-interventional characteristics were assessed using four ML algorithms. The predictive performance was evaluated by the area under curve (AUC) of receiver operating characteristic and calibration curve. In addition, the SHapley Additive exPlanations (SHAP) approach and partial dependence plot were introduced to understand the relative importance and the influence of a single feature.

Results

A total of 312 patients were included in this study. Of the four ML models that include baseline characteristics, the “Early” XGBoost had a better performance {AUC, 0.790 [95% confidence intervals (CI), 0.677–0.903]; Brier, 0.191}. Subsequent inclusion of peri-interventional characteristics into the “Early” XGBoost showed that the “Late” XGBoost performed better [AUC, 0.910 (95% CI, 0.837–0.984); Brier, 0.123]. NIHSS after 24 h, age, groin to recanalization, and the number of passages were the critical prognostic factors associated with futile recanalization, and the SHAP approach shows that NIHSS after 24 h ranks first in relative importance.

Conclusions

The “Early” XGBoost and the “Late” XGBoost allowed us to predict futile recanalization before and after EVT accurately. Our study suggests that including peri-interventional characteristics may lead to superior predictive performance compared to a model based on baseline characteristics only. In addition, NIHSS after 24 h was the most important prognostic factor for futile recanalization.

Interpretable classifiers for prediction of disability trajectories using a nationwide longitudinal database

OBJECTIVES

To explore the heterogeneous disability trajectories and construct explainable machine learning models for effective prediction of long-term disability trajectories and understanding the mechanisms of predictions among the elderly Chinese at community level.

METHODS

This study retrospectively collected data from the Chinese Longitudinal Healthy Longevity and Happy Family Study between 2002 and 2018. A total of 4149 subjects aged 65 + in 2002 with completed activities of daily living (ADL) information for at least three waves were included. The mixed growth model was used to identify disability trajectories, and five machine learning models were further established to predict disability trajectories using epidemiological variables. An explainable approach was deployed to understand the model's decisions.

RESULTS

Three distinct disability trajectories, including normal class (77.3%), progressive class (15.5%), and high-onset class (7.2%), were identified for three-class prediction. The latter two were further merged into abnormal class, accompanied by normal class for two-class prediction. Machine learning, especially random forest and extreme gradient boosting achieved good performance in both two tasks. ADL, age, leisure activity, cognitive function, and blood pressure were key predictors.

CONCLUSION

The findings suggest that machine learning showed good performance and maybe of additional value in analyzing quality indicators in predicting disability trajectories, thereby providing basis to personalize intervention measures.