Machine learning-based prediction of early neurological deterioration after intravenous thrombolysis for stroke: insights from a large multicenter study

You do realize survivors want prevention of early neurological deterioration rather than this USELESS PREDICTION?  I'd have you all fired!

Machine learning-based prediction of early neurological deterioration after intravenous thrombolysis for stroke: insights from a large multicenter study

Rui Wen¹Miaoran Wang²Wei Bian³Haoyue Zhu⁴Ying Xiao³Jing Zeng⁵Qian He⁴Yu Wang⁴Xiaoqing Liu⁴Yangdi Shi⁴Linzhi Zhang⁴Zhe Hong³Bing Xu^4*

• ¹Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
• ²Affiliated Central Hospital of Shenyang Medical College, Shenyang Medical College, Shenyang, China
• ³Shenyang First People’s Hospital, Shenyang Medical College, Shenyang, China
• ⁴Shenyang Tenth People’s Hospital, Shenyang Medical College, Shenyang, China
• ⁵Chongqing Medical University, Chongqing, China

Background: This investigation seeks to ascertain the efficacy of various machine learning models in forecasting early neurological deterioration (END) following thrombolysis in patients with acute ischemic stroke (AIS).

Methods: Employing data from the Shenyang Stroke Emergency Map database, this multicenter study compiled information on 7,570 AIS patients from 29 comprehensive hospitals who received thrombolytic therapy between January 2019 and December 2021. An independent testing cohort was constituted from 2,046 patients at the First People’s Hospital of Shenyang. The dataset incorporated 15 pertinent clinical and therapeutic variables. The principal outcome assessed was the occurrence of END post-thrombolysis. Model development was executed using an 80/20 split for training and internal validation, employing classifiers like logistic regression with lasso regularization (lasso regression), support vector machine (SVM), random forest (RF), gradient-boosted decision tree (GBDT), and multi-layer perceptron (MLP). The model with the highest area under the curve (AUC) was utilized to delineate feature significance.

Results: Baseline characteristics showed variability in END incidence between the training (n = 7,570; END incidence 22%) and external validation cohorts (n = 2,046; END incidence 10%; p < 0.001). Notably, all machine learning models demonstrated superior AUC values compared to the reference model, indicating their enhanced predictive capacity. The lasso regression model achieved the highest AUC at 0.829 (95% CI: 0.799–0.86; p < 0.001), closely followed by the MLP model with an AUC of 0.828 (95% CI: 0.799–0.858; p < 0.001). The SVM, RF, and GBDT models also showed commendable AUCs of 0.753, 0.797, and 0.774, respectively. Decision curve analysis revealed that the SVM and MLP models demonstrated a high net benefit. Feature importance analysis emphasized “Onset To Needle Time” and “Admission NIHSS Score” as significant predictors.

Conclusion: Our research establishes the MLP and lasso regression as robust tools for predicting early neurological deterioration in acute ischemic stroke patients following thrombolysis. Their superior predictive accuracy, compared to traditional models, highlights the significant potential of machine learning approaches in refining prognosis and enhancing clinical decisions in stroke care management. This advancement paves the way for more tailored therapeutic strategies, ultimately aiming to improve patient outcomes in clinical practice.

Introduction

Early neurological deterioration (END) is a common and critical outcome in patients following an ischemic stroke, marked by a rapid decline in neurological function within the first few days after stroke onset. Identifying individuals at heightened risk for END carries significant clinical implications, from aiding clinicians in informed therapeutic decision-making, providing accurate prognostic information to patients and their families, to tailoring surveillance and intervention strategies.

Despite the critical impact of END, the predictive tools currently available for assessing its occurrence, especially after interventions like intravenous thrombolysis (IVT) or endovascular treatment (EVT), are limited and often lack validation in diverse patient populations (1–4). To ensure these models’ integration into clinical workflows, they must undergo rigorous evaluation, including external validation to establish their wide applicability. While certain biomarkers and clinical indicators have been identified as associated with END risk post-thrombolysis (2, 5–7), the generalizability of these models remains constrained by their limited validation across different demographic and clinical contexts. This challenge underscores the necessity for research to bridge this gap through developing and validating models on broad, multi-center data that can more accurately predict END across various patient cohorts.

The advent of machine learning offers a promising avenue to address these limitations by surpassing traditional analytical methods in risk assessment (8–10). Leveraging computational algorithms to sift through large, complex datasets with numerous, multi-dimensional variables, machine learning can uncover intricate, non-linear relationships between clinical characteristics, thus enhancing the accuracy of prognostic predictions (11). Despite machine learning techniques demonstrating superior predictive capabilities over conventional statistical models in various medical domains, their application in predicting END following ischemic stroke, particularly with large-scale, multicenter datasets, remains underexplored.

In response to these challenges, our study aims to fill these gaps by analyzing data collected from multiple centers across different regions to develop machine learning-based models for predicting the likelihood of END after intravenous thrombolysis. We hypothesize that our models will offer improved accuracy and applicability across varied patient demographics compared to existing risk assessment tools. Further, we plan to externally validate our models’ predictive power in a real-world clinical setting, targeting patients treated with intravenous thrombolysis. Our research seeks to advance patient management strategies by enhancing our ability to predict and thereby mitigate the risk of END in the aftermath of an ischemic stroke.

More at link.