Machine Learning-Based Model for Prediction of Hemorrhage Transformation in Acute Ischemic Stroke After Alteplase

Abstract

Hemorrhage transformation (HT) is the most dreaded complication of intravenous thrombolysis (IVT) in acute ischemic stroke (AIS). The prediction of HT after IVT is important in the treatment decision-making for AIS. We designed and compared different machine learning methods, capable of predicting HT in AIS after IVT. A total of 345 AIS patients who received intravenous alteplase between January 2016 and June 2021 were enrolled in this retrospective study. The demographic characteristics, clinical condition, biochemical data, and neuroimaging variables were included for analysis. HT was confirmed by head computed tomography (CT) or magnetic resonance imaging (MRI) within 48 h after IVT. Based on the neuroimaging results, all of the patients were divided into the non-HT group and the HT group. Then, the variables were applied in logistic regression (LR) and random forest (RF) algorithms to establish HT prediction models. To evaluate the accuracy of the machine learning models, the models were compared to several of the common scales used in clinics, including the multicenter stroke survey (MSS) score, safe implementation of treatments in stroke (SITS) score, and SEDAN score. The performance of these prediction models was evaluated using the receiver operating characteristic (ROC) curve (AUC). Forty-five patients had HT (13.0%) within 48 h after IVT. The ROC curve results showed that the AUCs of HT that were predicted by the RF model, LR model, MSS, SITS, and SEDAN scales after IVT were 0.795 (95% CI, 0.647–0.944), 0.703 (95% CI, 0.515–0.892), 0.657 (95% CI, 0.574–0.741), 0.660 (95% CI, 0.580–0.740) and 0.655 (95% CI, 0.571–0.739), respectively. The RF model performed better than the other models and scales. The top four most influential factors in the RF importance matrix plot were triglyceride, Lpa, the baseline NIHSS, and hemoglobin. The SHapley Additive exPlanation values made the RF prediction model clinically interpretable. In this study, an RF machine learning method was successfully established to predict HT in AIS patients after intravenous alteplase, which the sensitivity was 66.7%, and the specificity was 80.7%.

A weakly supervised deep learning model integrating noncontrasted computed tomography images and clinical factors facilitates haemorrhagic transformation prediction after intravenous thrombolysis in acute ischaemic stroke patients

“…Classical ML methods have been developed for HT prediction using clinical information [ 34 – 38 ]. However, DL algorithms and NCCT have not been used to predict the risk of HT in AIS patients.…”

Risk prediction models for intracranial hemorrhage in acute ischemic stroke patients receiving intravenous alteplase treatment: a systematic review

“…PROBAST evaluates the risk of bias and the applicability of the model across four domains: participants, predictors, outcomes, and analysis. three were conducted in multiple countries (12,13,15), six in China (10,(19)(20)(21)(22)(23), two in Italy (17, 18), one in America (14), and one in Thailand (16). Regarding the type of research, one was a prospective cohort study (10), and the others were retrospective.…”

“…Regarding the type of research, one was a prospective cohort study (10), and the others were retrospective. The earliest included publication year was 2008 (12), with four articles published in the past three years (10,(21)(22)(23). All studies defined participants as patients treated with alteplase for AIS; six specified participants as 18 years or older (10,17,(20)(21)(22)(23), demonstrating high homogeneity in the studies (Table 1).…”

“…In these studies, the modeling sample size ranged from 131 to 13,908, with the incidence of ICH varying from 3.97 to 21.25%. For modeling methods, one study (23) employed machine learning (ML), while the remaining 12 studies (10,(12)(13)(14)(15)(16)(17)(18)(19)(20)(21)(22) used single-factor analysis combined with logistic regression. Regarding model validation, two studies (14,22) used both internal and external validation, seven studies (13,16,17,(19)(20)(21)23) used internal validation, and three studies (10,15,18) used only external validation (Table 1).…”

Machine Learning Models for Predicting Early Neurological Deterioration and Risk Classification of Acute Ischemic Stroke

“… 21 In recent years, the medical research field has extensively explored and adopted machine learning techniques, including their application in predicting the prognosis and forecasting bleeding transformation in AIS patients undergoing endovascular treatment and rt-PA thrombolysis. 22 – 24 These studies have achieved significant advancements, offering novel approaches and perspectives to enhance patient prognosis and treatment decision-making.…”