Development and Validation of Prediction Models for Severe Complications After Acute Ischemic Stroke: A Study Based on the Stroke Registry of Northwestern Germany

Abstract

Background The treatment of stroke has been undergoing rapid changes. As treatment options progress, prediction of those under risk for complications becomes more important. Available models have, however, frequently been built based on data no longer representative of today’s care, in particular with respect to acute stroke management. Our aim was to build and validate prediction models for 4 clinically important, severe outcomes after stroke. Methods and Results We used German registry data from 152 710 patients with acute ischemic stroke obtained in 2016 (development) and 2017 (validation). We took into account potential predictors that were available at admission and focused on in‐hospital mortality, intracranial mass effect, secondary intracerebral hemorrhage, and deep vein thrombosis as outcomes. Validation cohort prediction and calibration performances were assessed using the following 4 statistical approaches: logistic regression with backward selection, l 1‐regularized logistic regression, k‐nearest neighbor, and gradient boosting classifier. In‐hospital mortality and intracranial mass effects could be predicted with high accuracy (both areas under the curve, 0.90 [95% CI, 0.90–0.90]), whereas the areas under the curve for intracerebral hemorrhage (0.80 [95% CI, 0.80–0.80]) and deep vein thrombosis (0.73 [95% CI, 0.73–0.73]) were considerably lower. Stroke severity was the overall most important predictor. Models based on gradient boosting achieved better performances than those based on logistic regression for all outcomes. However, area under the curve estimates differed by a maximum of 0.02. Conclusions We validated prediction models for 4 severe outcomes after acute ischemic stroke based on routinely collected, recent clinical data. Model performance was superior to previously proposed approaches. These predictions may help to identify patients at risk early after stroke and thus facilitate an individualized level of care.

Machine learning approach for hemorrhagic transformation prediction: Capturing predictors' interaction

“…The predictive performance of RFC and GBC models significantly outperformed LRC and MLPC as assessed by the AUC difference. The superior predictive performance of GBC models over classical regression was previously documented in a large study conducted to predict severe complications after acute ischemic stroke ( 8 ). In general, the performance metrics of the best ML models in our study were either better or comparable to previous models developed to predict HT incidence in previous studies taking into consideration differences in the utilized HT definition, study design, ethnicity, and sample size of the study group ( 40 , 41 ).…”

“…Among the most commonly used supervised ML classifiers are logistic regression classifier (LRC), support vector classifiers (SVC), random forest classifier (RFC), decision tree-based gradient boosting classifier (GBC), and multilayer perceptron classifier (MLPC). Machine learning algorithms were reported to efficiently analyze complex non-linear interactions between variables and were utilized to develop prediction models in a variety of clinical settings ( 8 – 10 ).…”

Machine learning prediction of symptomatic intracerebral hemorrhage after stroke thrombolysis: a cross-cultural validation in Caucasian and Han Chinese cohort

“…Age and NIHSS score are the two most commonly used variables employed in sICH prediction. 7,8 In addition, Bonkhoff et al 26 also found that stroke severity (NIHSS score) was the overall most important predictor in their model for predicting severe complications after ischemic stroke including secondary intracerebral hemorrhage. It is consistent with our domain analysis, which showed clinical characteristics (NIHSS score, SBP and DBP) yielded the highest prediction measures in both the Caucasian and Han Chinese samples.…”

Ischemic stroke and concomitant gastrointestinal complications- a fatal combination for patient recovery

“…Several studies have demonstrated GIT disturbances in stroke patients such as dysphagia, gastrointestinal bleeding, or constipation ( 17 ). A recent stroke registry study showed that 19.6% of patients experience swallowing problems and indicate dysphagia frequency of 75.4% which is associated with a high risk of death during hospital admissions ( 5 ). Approximately 50% of the dysphagia complications persisted even after hospital discharge ( 4 , 6 , 17 ), causing a persistent burden on patients’ health.…”