A machine learning-based predictive nomogram for early neurological improvement after thrombolysis in acute ischemic...

Area of Science:

• Neurology
• Biochemistry
• Data Science

Background:

• Early neurological improvement (ENI) is a critical prognostic indicator for acute ischemic stroke (AIS) patients.
• Intravenous thrombolysis with recombinant tissue plasminogen activator (rt-PA) is a standard treatment for AIS.
• Predicting ENI is crucial for optimizing treatment and improving patient outcomes.

Purpose of the Study:

• To develop and validate a machine learning (ML)-based model for predicting ENI in AIS patients undergoing rt-PA treatment.
• To identify key clinical and biochemical predictors of ENI.
• To create a tool for personalized treatment strategies and enhanced clinical decision-making.

Main Methods:

• Retrospective analysis of clinical data from 217 AIS patients (97 ENI, 120 non-ENI).
• Implementation and evaluation of four ML algorithms: Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), and XGBoost.
• Identification of key predictors through feature intersection and logistic regression modeling, followed by nomogram visualization.

Main Results:

• The MLP model achieved the highest predictive performance with an AUC of 0.77 in the testing set.
• Six overlapping parameters were identified as core predictors: APTT, ALT/AST ratio, ONT, MCHC, weight, and NLR.
• The logistic regression model and nomogram demonstrated strong discriminative ability (C-index: 0.817) for predicting ENI.

Conclusions:

• An ML-based model effectively predicts ENI in rt-PA-treated AIS patients by integrating critical clinical and biochemical markers.
• The developed model can optimize personalized treatment strategies and improve clinical decision-making.
• Application of this model holds potential for improving patient outcomes in AIS management.