The impact of post-stroke complications on in-hospital mortality depends on stroke severity

Abstract

Introduction: Controversies remain on whether post-stroke complications represent an independent predictor of poor outcome or just a reflection of stroke severity. We aimed to identify which post-stroke complications have the highest impact on in-hospital mortality by using machine learning techniques. Secondary aim was identification of patient's subgroups in which complications have the highest impact.

Patients and methods: Registro Nacional de Ictus de la Sociedad Española de Neurología is a stroke registry from 42 centers from the Spanish Neurological Society. Data from ischemic stroke patients were used to build a random forest by combining 500 classification and regression trees, to weight up the impact of baseline characteristics and post-stroke complications on in-hospital mortality. With the selected variables, a logistic regression analysis was performed to test for interactions.

Results: 12,227 ischemic stroke patients were included. In-hospital mortality was 5.9% and median hospital stay was 7(4-10) days. Stroke severity [National Institutes of Health Stroke Scale > 10, OR = 5.54(4.55-6.99)], brain edema [OR = 18.93(14.65-24.46)], respiratory infections [OR = 3.67(3.02-4.45)] and age [OR = 2.50(2.07-3.03) for >77 years] had the highest impact on in-hospital mortality in random forest, being independently associated with in-hospital mortality. Complications have higher odds ratios in patients with baseline National Institutes of Health Stroke Scale <10.

Discussion: Our study identified brain edema and respiratory infections as independent predictors of in-hospital mortality, rather than just markers of more severe strokes. Moreover, its impact was higher in less severe strokes, despite lower frequency.

Conclusion: Brain edema and respiratory infections were the complications with a greater impact on in-hospital mortality, with the highest impact in patients with mild strokes. Further efforts on the prediction of these complications could improve stroke outcome.

Keywords: Stroke; classification and regression trees; complications; machine learning; mortality; outcome; random forest.

Figure 1.

Random forest. The points represent the mean decrease Gini value, indicative of the importance of each variable, and the discontinuous vertical line represents the mean importance of the model (43.28), correspondent to the mean value of the importance of each variable. NIHSS: National Institutes of Health Stroke Scale; sICH: symptomatic intracerebral hemorrhage; CAD: coronary artery disease.

Figure 2.

Example of one of the classification and regression trees (CARTs) for prediction of in-hospital mortality. Black squares show the variables dividing the dataset and white squares show the predicted in-hospital mortality rate at each node. Sample size in each division of the dataset is also shown. The terminal nodes with the highest and lowest rates for prediction of in-hospital mortality are marked in gray.

Figure 3.

Kaplan–Meier curves with survival rates for the most important complications identified in the random forest. Extreme survival values (>30 days) were removed. A: brain edema; B: respiratory infections; C: sICH; D: cardiologic complications.