Skip to main content

ORIGINAL RESEARCH article

Front. Neurol.
Sec. Stroke
Volume 16 - 2025 | doi: 10.3389/fneur.2025.1477286
This article is part of the Research Topic Bridging The Gap of Unmet Need in Stroke Care in Developing Countries View all 10 articles

A Predictive Model for Early Neurological Deterioration after Intravenous Thrombolysis in Patients with Ischemic Stroke

Provisionally accepted
Liping He Liping He 1Meng Zhang Meng Zhang 1Fei Xu Fei Xu 2Zhangsong Wu Zhangsong Wu 2Huijuan Chen Huijuan Chen 2Ying Li Ying Li 2Ran Chen Ran Chen 1*
  • 1 Bengbu Medical College, Bengbu, China
  • 2 Lu'an People's Hospital, luan, China

The final, formatted version of the article will be published soon.

    Objective: Intravenous thrombolysis (IVT) is the treatment of choice for acute ischemic stroke (AIS), but some patients develop early neurological deterioration (END) within 24 hours after IVT. Therefore, we aimed to identify predictors of END in AIS patients following treatment with IVT.: We retrospectively analyzed the clinical data of 621 AIS patients who received IVT with recombinant tissue-type plasminogen activator (rt-PA) at the Stroke Centre of the People's Hospital of Lu'an City, China, from July 2018 to July 2023. Clinical data, including demographic characteristics, clinical assessment results, underlying diseases, and laboratory indices, were collected at the time of admission. The patients were divided into training and validation cohorts, after which LASSO regression was applied to select the most important predictor variables, and multivariate logistic regression was used to construct a nomogram. The discriminative power of the model was determined by calculating the area under the curve (AUC), and calibration and decision curve analyses (DCA) were performed.The platelet-to-lymphocyte ratio (PLR) (OR 1.01, 95% CI 1.01-1.01, p < 0.001), mean platelet corpuscular volume (MPV) (OR 2.12, 95% CI 1.67-2.69, p < 0.001), and admission NIHSS score (OR 1.25, 95% CI 1.16-1.36, < 0.001) were significantly associated with the development of END. The AUC of the prediction model constructed from these three factors was 0.896 (95% CI 0.862-0.93), and the calibration curve was close to the diagonal. Conclusions: This predictive model can be used for the early identification of the risk of developing END after IVT and development of active interventions to improve the prognosis of AIS.

    Keywords: Acute ischemic stroke, intravenous thrombolysis, machine learning, Early neurological deterioration, predictive models, nomogram

    Received: 07 Aug 2024; Accepted: 13 Jan 2025.

    Copyright: © 2025 He, Zhang, Xu, Wu, Chen, Li and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Ran Chen, Bengbu Medical College, Bengbu, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.