Challenges of Outcome Prediction for Acute Stroke Treatment Decisions

Development of a Natural Language Processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center

INTRODUCTION

Data collection often relies on time-consuming manual inputs, with a vast amount of information embedded in unstructured texts such as patients' medical records and clinical notes. Our study aims to develop a pipeline that combines active learning (AL) and NLP techniques to enhance data extraction in an acute ischemic stroke cohort.

MATERIALS AND METHODS

Consecutive acute ischemic stroke patients who received reperfusion therapies at IRCCS Humanitas Research Hospital were included. The Italian NLP Bidirectional Encoder Representations from Transformers (BERT) model was trained with AL to automatically extract clinical variables from electronic health text. Simulated active learning performances were evaluated on a set of labels representing patients' comorbidities, comparing Bayesian Uncertainty Sampling by Disagreement (BALD) and random text selection. Prognostic models predicting patients' functional outcomes using Gradient Boosting were trained on manually labelled and semi-automatically extracted data and their performance was compared.

RESULTS

The active learning process initially showed null performance until around 20% of texts were labelled, possibly due to root layers freezing in the BERT model, yet overall, active learning improves model learning efficiency across most comorbidities. Prognostic modelling showed no significant difference in performance between models trained on manually labelled versus semi-automatically extracted data, indicating effective prediction capabilities in both settings.

CONCLUSIONS

We developed an efficient language model to automate the extraction of clinical data from Italian unstructured health texts in a cohort of ischemic stroke patients. In a preliminary analysis, we demonstrated its potential applicability for enhancing prediction model accuracy.

Multimodal Machine Learning for Stroke Prognosis and Diagnosis: A Systematic Review

Stroke is a life-threatening medical condition that could lead to mortality or significant sensorimotor deficits. Various machine learning techniques have been successfully used to detect and predict stroke-related outcomes. Considering the diversity in the type of clinical modalities involved during management of patients with stroke, such as medical images, bio-signals, and clinical data, multimodal machine learning has become increasingly popular. Thus, we conducted a systematic literature review to understand the current status of state-of-the-art multimodal machine learning methods for stroke prognosis and diagnosis. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines during literature search and selection, our results show that the most dominant techniques are related to the fusion paradigm, specifically early, joint and late fusion. We discuss opportunities to leverage other multimodal learning paradigms, such as multimodal translation and alignment, which are generally less explored. We also discuss the scale of datasets and types of modalities used to develop existing models, highlighting opportunities for the creation of more diverse multimodal datasets. Finally, we present ongoing challenges and provide a set of recommendations to drive the next generation of multimodal learning methods for improved prognosis and diagnosis of patients with stroke.

A novel prediction score determining individual clinical outcome 3 months after juvenile stroke (PREDICT-score)

BACKGROUND

Juvenile strokes (< 55 years) account for about 15% of all ischemic strokes. Structured data on clinical outcome in those patients are sparse. Here, we aimed to fill this gap by systematically collecting relevant data and modeling a juvenile stroke prediction score for the 3-month functional outcome.

METHODS

We retrospectively integrated and analyzed clinical and outcome data of juvenile stroke and TIA patients treated at the LMU University Hospital, LMU Munich, Munich. Good outcome was defined as a modified Rankin Scale of 0-2 or return to baseline of function. We analyzed candidate predictors and developed a predictive model. Predictive abilities were inspected using Area Under the ROC curve (AUROC) and visual representation of the calibration. The model was validated internally.

RESULTS

346 patients were included in the analysis. We observed a good outcome in n = 293 patients (84.7%). The prediction model for an unfavourable outcome had an AUROC of 89.1% (95% CI 83.3-93.1%). The model includes age NIHSS, ASPECTS, blood glucose and type of vessel occlusion as predictors for the individual patient outcome.

CONCLUSIONS

Here, we introduce the highly accurate PREDICT-score for the 3-month outcome after juvenile stroke derived from clinical routine data. The PREDICT-score might be helpful in guiding individual patient decisions and designing future studies but needs further prospective validation which is already planned. Trial registration The study has been registered at https://drks.de (DRKS00024407) on March 31, 2022.

Developing machine learning models to predict multi-class functional outcomes and death three months after stroke in Sweden

Globally, stroke is the third-leading cause of mortality and disability combined, and one of the costliest diseases in society. More accurate predictions of stroke outcomes can guide healthcare organizations in allocating appropriate resources to improve care and reduce both the economic and social burden of the disease. We aim to develop and evaluate the performance and explainability of three supervised machine learning models and the traditional multinomial logistic regression (mLR) in predicting functional dependence and death three months after stroke, using routinely-collected data. This prognostic study included adult patients, registered in the Swedish Stroke Registry (Riksstroke) from 2015 to 2020. Riksstroke contains information on stroke care and outcomes among patients treated in hospitals in Sweden. Prognostic factors (features) included demographic characteristics, pre-stroke functional status, cardiovascular risk factors, medications, acute care, stroke type, and severity. The outcome was measured using the modified Rankin Scale at three months after stroke (a scale of 0-2 indicates independent, 3-5 dependent, and 6 dead). Outcome prediction models included support vector machines, artificial neural networks (ANN), eXtreme Gradient Boosting (XGBoost), and mLR. The models were trained and evaluated on 75% and 25% of the dataset, respectively. Model predictions were explained using SHAP values. The study included 102,135 patients (85.8% ischemic stroke, 53.3% male, mean age 75.8 years, and median NIHSS of 3). All models demonstrated similar overall accuracy (69%-70%). The ANN and XGBoost models performed significantly better than the mLR in classifying dependence with F1-scores of 0.603 (95% CI; 0.594-0.611) and 0.577 (95% CI; 0.568-0.586), versus 0.544 (95% CI; 0.545-0.563) for the mLR model. The factors that contributed most to the predictions were expectedly similar in the models, based on clinical knowledge. Our ANN and XGBoost models showed a modest improvement in prediction performance and explainability compared to mLR using routinely-collected data. Their improved ability to predict functional dependence may be of particular importance for the planning and organization of acute stroke care and rehabilitation.

Brain frailty associated with stroke events in anterior circulation large artery occlusion

OBJECTIVE

To investigate the factors associated with brain frailty and the effect of brain frailty in patients with anterior circulation large artery occlusion (AC-LAO).

METHODS

1100 patients with AC-LVO consecutively admitted to the Second Hospital of Hebei Medical University, North China between June 2016 and April 2018 were retrospectively analyzed. The variables associated with brain frailty and stroke outcome were analyzed by ANOVA analysis, the Mann-Whitney U test and multiple linear regression. Based on previous research. Brain frailty score comprises 1 point each for white matter hyperintensity (WMH), old infarction lesions, and cerebral atrophy among 983 participants with baseline brain magnetic resonance imaging or computed tomography.

RESULTS

Among AC-LAO participants, baseline brain frailty score ≥ 1 was common (750/983, 76.3%). Duration of hypertension > 5 years (mean difference [MD] 0.236, 95% CI 0.077, 0.395, p = 0.004), multiple vessel occlusion (MD 0.339, 95% CI 0.068, 0.611, p = 0.014) and basal ganglia infarction (MD -0.308, 95% CI -0.456, -0.160, p < 0.001) were independently associated with brain frailty score. Brain frailty score was independently associated with stroke events, and higher brain frailty scores were associated with higher rates of stroke events (p < 0.001). However, brain frailty has no independent effect on short-term outcome of ACI in AC-LAO patients.

CONCLUSIONS

In AC-LAO patients, older age, duration of hypertension > 5 years, and multiple vessel occlusion influenced the brain frailty score. Brain frailty score was independently associated with the occurrence of stroke events in AC-LAO patients.

Exploring the use of ChatGPT in predicting anterior circulation stroke functional outcomes after mechanical thrombectomy: a pilot study

BACKGROUND

Accurate prediction of functional outcomes is crucial in stroke management, but this remains challenging.

OBJECTIVE

To evaluate the performance of the generative language model ChatGPT in predicting the functional outcome of patients with acute ischemic stroke (AIS) 3 months after mechanical thrombectomy (MT) in order to assess whether ChatGPT can used to be accurately predict the modified Rankin Scale (mRS) score at 3 months post-thrombectomy.

METHODS

We conducted a retrospective analysis of clinical, neuroimaging, and procedure-related data from 163 patients with AIS undergoing MT. The agreement between ChatGPT's exact and dichotomized predictions and actual mRS scores was assessed using Cohen's κ. The added value of ChatGPT was measured by evaluating the agreement of predicted dichotomized outcomes using an existing validated score, the MT-DRAGON.

RESULTS

ChatGPT demonstrated fair (κ=0.354, 95% CI 0.260 to 0.448) and good (κ=0.727, 95% CI 0.620 to 0.833) agreement with the true exact and dichotomized mRS scores at 3 months, respectively, outperforming MT-DRAGON in overall and subgroup predictions. ChatGPT agreement was higher for patients with shorter last-time-seen-well-to-door delay, distal occlusions, and better modified Thrombolysis in Cerebral Infarction scores.

CONCLUSIONS

ChatGPT adequately predicted short-term functional outcomes in post-thrombectomy patients with AIS and was better than the existing risk score. Integrating AI models into clinical practice holds promise for patient care, yet refining these models is crucial for enhanced accuracy in stroke management.

Early flexible endoscopic evaluation of swallowing after mechanical thrombectomy in stroke patients

OBJECTIVE

The aims of the study were to (1) characterize the findings of flexible endoscopic evaluation of swallowing (FEES) in stroke patients undergoing mechanical thrombectomy (MT); (2) analyse the screening performance of the Standardized Swallowing Assessment (SSA); and (3) study the impact of FEES-defined dysphagia on 3-month outcomes.

METHODS

This single-centre study was based on a local registry of consecutive acute ischaemic stroke patients undergoing MT during a 1-year period. Patients received FEES within 5 days of admission regardless of the result of dysphagia screening. We compared baseline demographic and clinical characteristics of patients with and without FEES-defined dysphagia. We collected 3-month modified Rankin Scale (mRS) and individual index values of the European Quality of Life 5 Dimensions (EQ-5D-iv). Using univariable and multivariable regression analyses we predicted 3-month outcomes for presence of dysphagia and for FEES-defined dysphagia severity.

RESULTS

We included 137 patients with a median age of 74 years, 43.1% were female, median NIHSS was 12 and successful recanalization was achieved in 92.7%. Stroke-associated pneumonia occurred in 8% of patients. FEES-defined dysphagia occurred in 81% of patients. Sensitivity of the SSA as a dysphagia screening was 67%. Presence of dysphagia and increasing severity of dysphagia were independently associated with increasing 3-month mRS score. Increasing dysphagia severity dysphagia was independently associated with lower EQ-5D-iv.

INTERPRETATION

Early FEES-defined dysphagia occurs in four in every five patients undergoing MT. SSA has a suboptimal dysphagia screening performance. Presence of dysphagia and increasing dysphagia severity predict worse functional outcome and worse health-related quality-of-life.

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.

Efficacy of endovascular therapy for stroke in developing country: A single-centre retrospective observational study in Indonesia from 2017 to 2021

Background

Indonesia as a developing nation faces a plethora of challenges in applying endovascular therapy (EVT), mostly due to the lack of physicians specialized in neuro-intervention, high operational cost, and time limitation. The efficacy of EVT in improving functional outcomes of stroke in developing countries has not been previously studied.

Methods

This retrospective cohort study was conducted at Dr. Cipto Mangunkusumo Hospital (Jakarta, Indonesia) from January 2017 to December 2021. Large vessel occlusion (LVO) diagnosis was established based on a combination of clinical and imaging characteristics. We assessed patients' functional independence on day-90 based on modified Rankin Scale (mRS) between the endovascular treatment group and the conservative group (those receiving intravascular thrombolysis or medical treatment only). Functional independence was defined as mRS ≤2.

Results

Among 111 stroke patients with LVO, we included 32 patients in the EVT group and 50 patients in the conservative group for this study. Patients with younger age (p = 0.004), lower hypertension rate (p < 0.001), higher intubation rate (p = 0.014), and earlier onset of stroke were observed in the EVT group. The proportion of mRS ≤2 at day-90 in the EVT group was higher than the conservative group (28.1 % vs. 18.0 %; p = 0.280). Patients within mRS ≤2 group had earlier onset-to-puncture time (p = 0.198), onset-to-recanalization time (p = 0.341), lower NIHSS (p = 0.026) and higher ASPECTS (p = 0.001) on admission. In multivariate analysis, ASPECTS (aOR 2.43; 95%CI 1.26-4.70; p = 0.008) defined functional independence in the EVT group.

Conclusion

The endovascular therapy group had a higher proportion of mRS ≤2 at day-90 than the conservative group despite its statistical insignificance.

Data-driven distillation and precision prognosis in traumatic brain injury with interpretable machine learning

Traumatic brain injury (TBI) affects how the brain functions in the short and long term. Resulting patient outcomes across physical, cognitive, and psychological domains are complex and often difficult to predict. Major challenges to developing personalized treatment for TBI include distilling large quantities of complex data and increasing the precision with which patient outcome prediction (prognoses) can be rendered. We developed and applied interpretable machine learning methods to TBI patient data. We show that complex data describing TBI patients' intake characteristics and outcome phenotypes can be distilled to smaller sets of clinically interpretable latent factors. We demonstrate that 19 clusters of TBI outcomes can be predicted from intake data, a ~ 6× improvement in precision over clinical standards. Finally, we show that 36% of the outcome variance across patients can be predicted. These results demonstrate the importance of interpretable machine learning applied to deeply characterized patients for data-driven distillation and precision prognosis.

A framework for integrating artificial intelligence for clinical care with continuous therapeutic monitoring

The complex relationships between continuously monitored health signals and therapeutic regimens can be modelled via machine learning. However, the clinical implementation of the models will require changes to clinical workflows. Here we outline ClinAIOps ('clinical artificial-intelligence operations'), a framework that integrates continuous therapeutic monitoring and the development of artificial intelligence (AI) for clinical care. ClinAIOps leverages three feedback loops to enable the patient to make treatment adjustments using AI outputs, the clinician to oversee patient progress with AI assistance, and the AI developer to receive continuous feedback from both the patient and the clinician. We lay out the central challenges and opportunities in the deployment of ClinAIOps by means of examples of its application in the management of blood pressure, diabetes and Parkinson's disease. By enabling more frequent and accurate measurements of a patient's health and more timely adjustments to their treatment, ClinAIOps may substantially improve patient outcomes.

End to end stroke triage using cerebrovascular morphology and machine learning

Background

Rapid and accurate triage of acute ischemic stroke (AIS) is essential for early revascularization and improved patient outcomes. Response to acute reperfusion therapies varies significantly based on patient-specific cerebrovascular anatomy that governs cerebral blood flow. We present an end-to-end machine learning approach for automatic stroke triage.

Methods

Employing a validated convolutional neural network (CNN) segmentation model for image processing, we extract each patient's cerebrovasculature and its morphological features from baseline non-invasive angiography scans. These features are used to detect occlusion's presence and the site automatically, and for the first time, to estimate collateral circulation without manual intervention. We then use the extracted cerebrovascular features along with commonly used clinical and imaging parameters to predict the 90 days functional outcome for each patient.

Results

The CNN model achieved a segmentation accuracy of 94% based on the Dice similarity coefficient (DSC). The automatic stroke detection algorithm had a sensitivity and specificity of 92% and 94%, respectively. The models for occlusion site detection and automatic collateral grading reached 96% and 87.2% accuracy, respectively. Incorporating the automatically extracted cerebrovascular features significantly improved the 90 days outcome prediction accuracy from 0.63 to 0.83.

Conclusion

The fast, automatic, and comprehensive model presented here can improve stroke diagnosis, aid collateral assessment, and enhance prognostication for treatment decisions, using cerebrovascular morphology.

RCT versus real-world cohorts: Differences in patient characteristics drive associations with outcome after EVT

Background:

The selection of patients with large-vessel occlusion (LVO) stroke for endovascular treatment (EVT) depends on patient characteristics and procedural metrics. The relation of these variables to functional outcome after EVT has been assessed in numerous datasets from both randomized controlled trials (RCT) and real-world registries, but whether differences in their case mix modulate outcome prediction is unknown.

Methods:

We leveraged data from individual patients with anterior LVO stroke treated with EVT from completed RCTs from the Virtual International Stroke Trials Archive ( N = 479) and from the German Stroke Registry ( N = 4079). Cohorts were compared regarding (i) patient characteristics and procedural pre-EVT metrics, (ii) these variables’ relation to functional outcome, and (iii) the performance of derived outcome prediction models. Relation to outcome (functional dependence defined by a modified Rankin Scale score of 3–6 at 90 days) was analyzed by logistic regression models and a machine learning algorithm.

Results:

Ten out of 11 analyzed baseline variables differed between the RCT and real-world cohort: RCT patients were younger, had higher admission NIHSS scores, and received thrombolysis more often (all p < 0.0001). Largest differences at the level of individual outcome predictors were observed for age (RCT: adjusted odds ratio (aOR), 1.29 (95% CI, 1.10–1.53) vs real-world aOR, 1.65 (95% CI, 1.54–1.78) per 10-year increments, p < 0.001). Treatment with intravenous thrombolysis was not significantly associated with functional outcome in the RCT cohort (aOR, 1.64 (95 % CI, 0.91–3.00)), but in the real-world cohort (aOR, 0.81 (95% CI, 0.69–0.96); p for cohort heterogeneity = 0.056). Outcome prediction was more accurate when constructing and testing the model using real-world data compared to construction with RCT data and testing on real-world data (area under the curve, 0.82 (95% CI, 0.79–0.85) vs 0.79 (95% CI, 0.77–0.80), p = 0.004).

Conclusions:

RCT and real-world cohorts considerably differ in patient characteristics, individual outcome predictor strength, and overall outcome prediction model performance.

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.

Fatty Acids and Lipid Paradox-Neuroprotective Biomarkers in Ischemic Stroke

Stroke is the primary cause of death and disability worldwide, with ischemic stroke up to 80% of the total cases. Lipid profile was established as a major risk factor for stroke, but recent studies show a paradoxical relationship between serum values and the outcome of stroke patients. Our study aims to analyze the impact of the classic extended lipid profile, including fatty acids as potential neuroprotective biomarkers for the outcome of ischemic stroke patients. We included 298 patients and collected clinical, paraclinical, and outcome parameters. We used a method consisting of high-performance liquid chromatography coupled with mass spectrometry to quantify serum fatty acids. We observed a negative correlation between National Institutes of Health Stroke Scale (NIHSS) at admission and total cholesterol (p = 0.040; r = −0.120), respectively triglycerides (p = 0.041; r = −0.122). The eicosapentaenoic to arachidonic acid ratio has a negative correlation, while the docosahexaenoic to eicosapentaenoic acid ratio positively correlates with all the prognostic parameters, showing a potential neuroprotective role for eicosapentaenoic acid in preventing severe ischemic stroke. The impact of the lipid profile paradox and the dependency relationship with the fatty acids represent a significant predictive factor for the functional and disability prognostic of ischemic stroke patients.

Full Reperfusion Without Functional Independence After Mechanical Thrombectomy in the Anterior Circulation : Performance of Prediction Models Before Versus After Treatment Initiation

BACKGROUND AND PURPOSE

Prediction of futile recanalization (FR), i.e. failure of long-term functional independence despite full reperfusion in mechanical thrombectomy (MT), is instrumental in patients undergoing endovascular therapy.

METHODS

Retrospective single-center analysis of patients treated for anterior circulation LVO ensuing successful MT (mTICI 2c-3) between January 2014 and April 2019. FR was defined as modified Rankin Scale (mRS) 90 days after stroke onset > 2 or mRS > pre-stroke mRS. Multivariable analysis was performed with variables available before treatment initiation regarding their association with FR. Performance of the regression model was then compared with a model including parameters available after MT.

RESULTS

Successful MT was experienced by 549/1146 patients in total. FR occurred in 262/549 (47.7%) patients. Independent predictors of FR were male sex, odds ratio (OR) with 95% confidence interval (CI) 1.98 (1.31-3.05, p 0.001), age (OR 1.05, CI 1.03-1.07, p < 0.001), NIHSS on admission (OR 1.10, CI 1.06-1.13, p < 0.001), pre-stroke mRS (OR 1.22, CI 1.03-1.46, p 0.025), neutrophile-lymphocyte ratio (OR 1.03, CI 1.00-1.06, p 0.022), baseline ASPECTS (OR 0.77, CI 0.68-0.88, p < 0.001), and absence of bridging i.v. lysis (OR 1.62, 1.09-2.42, p 0.016). The prediction model's Area Under the Curve was 0.78 (CI 0.74-0.82) and increased with parameters available after MT to 0.86 (CI 0.83-0.89) with failure of early neurological improvement being the most important predictor of FR (OR 15.0, CI 7.2-33.8).

CONCLUSION

A variety of preinterventional factors may predict FR with substantial certainty, but the prediction model can still be improved by considering parameters only available after MT, in particular early neurological improvement.

Assessment of Discrepancies Between Follow-up Infarct Volume and 90-Day Outcomes Among Patients With Ischemic Stroke Who Received Endovascular Therapy

IMPORTANCE

Some patients have poor outcomes despite small infarcts after endovascular therapy (EVT), while others with large infarcts do well. Understanding why these discrepancies occur may help to optimize EVT outcomes.

OBJECTIVE

To validate exploratory findings from the Endovascular Treatment for Small Core and Anterior Circulation Proximal Occlusion with Emphasis on Minimizing CT to Recanalization Times (ESCAPE) trial regarding pretreatment, treatment-related, and posttreatment factors associated with discrepancies between follow-up infarct volume (FIV) and 90-day functional outcome.

DESIGN, SETTING, AND PARTICIPANTS

This cohort study is a post hoc analysis of the Safety and Efficacy of Nerinetide in Subjects Undergoing Endovascular Thrombectomy for Stroke (ESCAPE-NA1) trial, a double-blind, randomized, placebo-controlled, international, multicenter trial conducted from March 2017 to August 2019. Patients who participated in ESCAPE-NA1 and had available 90-day modified Rankin Scale (mRS) scores and 24-hour to 48-hour posttreatment follow-up parenchymal imaging were included.

EXPOSURES

Small FIV (volume ≤25th percentile) and large FIV (volume ≥75th percentile) on 24-hour computed tomography/magnetic resonance imaging. Baseline factors, outcomes, treatments, and poststroke serious adverse events (SAEs) were compared between discrepant cases (ie, patients with 90-day mRS score ≥3 despite small FIV or those with mRS scores ≤2 despite large FIV) and nondiscrepant cases.

MAIN OUTCOMES AND MEASURES

Area under the curve (AUC) and goodness of fit of prespecified logistic models, including pretreatment (eg, age, cancer, vascular risk factors) and treatment-related and posttreatment (eg, SAEs) factors, were compared with stepwise regression-derived models for ability to identify small FIV with higher mRS score and large FIV with lower mRS score.

RESULTS

Among 1091 patients (median [IQR] age, 70.8 [60.8-79.8] years; 549 [49.7%] women; median [IQR] FIV, 24.9 mL [6.6-92.2 mL]), 42 of 287 patients (14.6%) with FIV of 7 mL or less (ie, ≤25th percentile) had an mRS score of at least 3; 65 of 275 patients (23.6%) with FIV of 92 mL or greater (ie, ≥75th percentile) had an mRS score of 2 or less. Prespecified models of pretreatment factors (ie, age, cancer, vascular risk factors) associated with low FIV and higher mRS score performed similarly to models selected by stepwise regression (AUC, 0.92 [95% CI, 0.89-0.95] vs 0.93 [95% CI, 0.90-0.95]; P = .42). SAEs, specifically infarct in new territory, recurrent stroke, pneumonia, and congestive heart failure, were associated with low FIV and higher mRS scores; stepwise models also identified 24-hour hemoglobin as treatment-related/posttreatment factor (AUC, 0.92 [95% CI, 0.90-0.95] vs 0.94 [95% CI, 0.91-0.96]; P = .14). Younger age was associated with high FIV and lower mRS score; stepwise models identified absence of diabetes and higher baseline hemoglobin as additional pretreatment factors (AUC, 0.76 [95% CI, 0.70-0.82] vs 0.77 [95% CI, 0.71-0.83]; P = .82). Absence of SAEs, especially stroke progression, symptomatic intracerebral hemorrhage, and pneumonia, was associated with high FIV and lower mRS score2; stepwise models also identified 24-hour hemoglobin level, glucose, and diastolic blood pressure as posttreatment factors associated with discrepant cases (AUC, 0.80 [95% CI, 0.74-0.87] vs 0.79 [95% CI, 0.72-0.86]; P = .92).

CONCLUSIONS AND RELEVANCE

In this study, discrepancies between functional outcome and post-EVT infarct volume were associated with differences in pretreatment factors, such as age and comorbidities, and posttreatment complications related to index stroke evolution, secondary prevention, and quality of stroke unit care. Besides preventing such complications, optimization of blood pressure, glucose levels, and hemoglobin levels are potentially modifiable factors meriting further study.