Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods

Background: Acute ischemic stroke (AIS) is a leading cause of mortality and disability worldwide. Intravenous thrombolysis (IVT) improves recovery, but predicting outcomes remains challenging. Machine learning (ML) and biomarkers like ubiquitin carboxyl-terminal hydrolase L1 (UCH-L1), S100 calcium-b...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming-Ya Luo, Yang Qu, Peng Zhang, Reziya Abuduxukuer, Li-Juan Wang, Li-Chong Yang, Zhi-Guo Li, Xiao-Dong Liu, Ce Han, Dan Li, Wei-Jia Wang, Dian-Ping Lv, Ming Liu, Jian Gao, Jing Xu, Yongfei Jiang, Hai-Nan Chen, Fu-Jin Li, Li-Ming Sun, Qi-Dong Sun, Yingbin Qi, Si-Yin Sun, Yu Zhang, Zhen-Ni Guo, Yi Yang
Format: Article
Language:English
Published: SAGE Publishing 2025-06-01
Series:Therapeutic Advances in Neurological Disorders
Online Access:https://doi.org/10.1177/17562864251342429
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212263306199040
author Ming-Ya Luo
Yang Qu
Peng Zhang
Reziya Abuduxukuer
Li-Juan Wang
Li-Chong Yang
Zhi-Guo Li
Xiao-Dong Liu
Ce Han
Dan Li
Wei-Jia Wang
Dian-Ping Lv
Ming Liu
Jian Gao
Jing Xu
Yongfei Jiang
Hai-Nan Chen
Fu-Jin Li
Li-Ming Sun
Qi-Dong Sun
Yingbin Qi
Si-Yin Sun
Yu Zhang
Zhen-Ni Guo
Yi Yang
author_facet Ming-Ya Luo
Yang Qu
Peng Zhang
Reziya Abuduxukuer
Li-Juan Wang
Li-Chong Yang
Zhi-Guo Li
Xiao-Dong Liu
Ce Han
Dan Li
Wei-Jia Wang
Dian-Ping Lv
Ming Liu
Jian Gao
Jing Xu
Yongfei Jiang
Hai-Nan Chen
Fu-Jin Li
Li-Ming Sun
Qi-Dong Sun
Yingbin Qi
Si-Yin Sun
Yu Zhang
Zhen-Ni Guo
Yi Yang
author_sort Ming-Ya Luo
collection DOAJ
description Background: Acute ischemic stroke (AIS) is a leading cause of mortality and disability worldwide. Intravenous thrombolysis (IVT) improves recovery, but predicting outcomes remains challenging. Machine learning (ML) and biomarkers like ubiquitin carboxyl-terminal hydrolase L1 (UCH-L1), S100 calcium-binding protein β (S100β), and neuron-specific enolase (NSE) may enhance prognostic accuracy. Objectives: We aimed to assess the predictive value of serum brain injury biomarkers for 3-month outcomes in AIS patients treated with IVT, using an ML-based model. Design: A multicenter prospective cohort study was conducted, enrolling AIS patients treated with recombinant tissue plasminogen activator from 16 hospitals. Methods: Of 1580 patients, 1028 were included and divided into training ( n  = 571), testing ( n  = 243), and external validation ( n  = 214) cohorts. Thirty-three variables, including demographics, clinical data, and biomarkers (UCH-L1, S100β, NSE), were analyzed. Least Absolute Shrinkage and Selection Operator regression was used for feature selection, and six ML algorithms were tested. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), F 1-score, calibration curve, and decision curve analysis. Results: The light gradient boosting machines (LightGBM) model achieved the best performance in the training dataset (AUC: 0.846; F 1-score: 0.789) and external validation dataset (AUC: 0.714). Eight critical predictors, including age, admission National Institutes of Health Stroke Scale (NIHSS) score, Trial of Org 10172 in Acute Stroke Treatment, white blood cell, finger blood glucose, UCH-L1, S100β, and NSE, were identified and incorporated into an ML model for clinical application. Shapley additive interpretation analysis enhances the interpretability of the model, with NIHSS score and NSE as top contributors. External validation confirmed good calibration and consistent net benefit across threshold probabilities (0.1–0.8). Conclusion: Integrating serum biomarkers (UCH-L1, S100β, NSE) with ML significantly improves 3-month outcome prediction in AIS patients. The LightGBM model offers robust performance and clinical interpretability for individualized treatment planning.
format Article
id doaj-art-d25e49de2e694f7b95104d66ed900e1a
institution OA Journals
issn 1756-2864
language English
publishDate 2025-06-01
publisher SAGE Publishing
record_format Article
series Therapeutic Advances in Neurological Disorders
spelling doaj-art-d25e49de2e694f7b95104d66ed900e1a2025-08-20T02:09:22ZengSAGE PublishingTherapeutic Advances in Neurological Disorders1756-28642025-06-011810.1177/17562864251342429Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methodsMing-Ya LuoYang QuPeng ZhangReziya AbuduxukuerLi-Juan WangLi-Chong YangZhi-Guo LiXiao-Dong LiuCe HanDan LiWei-Jia WangDian-Ping LvMing LiuJian GaoJing XuYongfei JiangHai-Nan ChenFu-Jin LiLi-Ming SunQi-Dong SunYingbin QiSi-Yin SunYu ZhangZhen-Ni GuoYi YangBackground: Acute ischemic stroke (AIS) is a leading cause of mortality and disability worldwide. Intravenous thrombolysis (IVT) improves recovery, but predicting outcomes remains challenging. Machine learning (ML) and biomarkers like ubiquitin carboxyl-terminal hydrolase L1 (UCH-L1), S100 calcium-binding protein β (S100β), and neuron-specific enolase (NSE) may enhance prognostic accuracy. Objectives: We aimed to assess the predictive value of serum brain injury biomarkers for 3-month outcomes in AIS patients treated with IVT, using an ML-based model. Design: A multicenter prospective cohort study was conducted, enrolling AIS patients treated with recombinant tissue plasminogen activator from 16 hospitals. Methods: Of 1580 patients, 1028 were included and divided into training ( n  = 571), testing ( n  = 243), and external validation ( n  = 214) cohorts. Thirty-three variables, including demographics, clinical data, and biomarkers (UCH-L1, S100β, NSE), were analyzed. Least Absolute Shrinkage and Selection Operator regression was used for feature selection, and six ML algorithms were tested. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), F 1-score, calibration curve, and decision curve analysis. Results: The light gradient boosting machines (LightGBM) model achieved the best performance in the training dataset (AUC: 0.846; F 1-score: 0.789) and external validation dataset (AUC: 0.714). Eight critical predictors, including age, admission National Institutes of Health Stroke Scale (NIHSS) score, Trial of Org 10172 in Acute Stroke Treatment, white blood cell, finger blood glucose, UCH-L1, S100β, and NSE, were identified and incorporated into an ML model for clinical application. Shapley additive interpretation analysis enhances the interpretability of the model, with NIHSS score and NSE as top contributors. External validation confirmed good calibration and consistent net benefit across threshold probabilities (0.1–0.8). Conclusion: Integrating serum biomarkers (UCH-L1, S100β, NSE) with ML significantly improves 3-month outcome prediction in AIS patients. The LightGBM model offers robust performance and clinical interpretability for individualized treatment planning.https://doi.org/10.1177/17562864251342429
spellingShingle Ming-Ya Luo
Yang Qu
Peng Zhang
Reziya Abuduxukuer
Li-Juan Wang
Li-Chong Yang
Zhi-Guo Li
Xiao-Dong Liu
Ce Han
Dan Li
Wei-Jia Wang
Dian-Ping Lv
Ming Liu
Jian Gao
Jing Xu
Yongfei Jiang
Hai-Nan Chen
Fu-Jin Li
Li-Ming Sun
Qi-Dong Sun
Yingbin Qi
Si-Yin Sun
Yu Zhang
Zhen-Ni Guo
Yi Yang
Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods
Therapeutic Advances in Neurological Disorders
title Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods
title_full Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods
title_fullStr Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods
title_full_unstemmed Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods
title_short Prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum UCH-L1, S100β, and NSE: a multicenter prospective cohort study employing machine learning methods
title_sort prediction of outcomes following intravenous thrombolysis in patients with acute ischemic stroke using serum uch l1 s100β and nse a multicenter prospective cohort study employing machine learning methods
url https://doi.org/10.1177/17562864251342429
work_keys_str_mv AT mingyaluo predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT yangqu predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT pengzhang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT reziyaabuduxukuer predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT lijuanwang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT lichongyang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT zhiguoli predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT xiaodongliu predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT cehan predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT danli predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT weijiawang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT dianpinglv predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT mingliu predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT jiangao predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT jingxu predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT yongfeijiang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT hainanchen predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT fujinli predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT limingsun predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT qidongsun predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT yingbinqi predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT siyinsun predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT yuzhang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT zhenniguo predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods
AT yiyang predictionofoutcomesfollowingintravenousthrombolysisinpatientswithacuteischemicstrokeusingserumuchl1s100bandnseamulticenterprospectivecohortstudyemployingmachinelearningmethods