Visual prediction of outcomes in patients undergoing intravenous thrombolysis.

ABSTRACT:

Background

This research presents a novel visual predictive model aimed at the early identification of patients at elevated risk of poor prognosis following intravenous thrombolysis, assessed six months post-acute ischemic stroke.

Methods

A retrospective cohort of patients who underwent intravenous thrombolysis at advanced stroke centers was analyzed. The latest Least Absolute Shrinkage and Selection Operator (LASSO) regression technique was employed to select relevant variables and develop nomograms. The model's performance was evaluated through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis, culminating in an assessment of the model's reliability.

Results

We identified five principal predictors that are significantly

SUBMITTER: Liang Q 

PROVIDER: S-EPMC12714193 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature