AUTHOR=Sui He , Wu Jiaojiao , Zhou Qing , Liu Lin , Lv Zhongwen , Zhang Xintan , Yang Haibo , Shen Yi , Liao Shu , Shi Feng , Mo Zhanhao 

TITLE=Nomograms predict prognosis and hospitalization time using non-contrast CT and CT perfusion in patients with ischemic stroke

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.912287

DOI=10.3389/fnins.2022.912287

ISSN=1662-453X

ABSTRACT=Background: Stroke is a major disease with high morbidity and mortality worldwide. Currently, there is no quantitative method to evaluate the short-term prognosis and length of hospitalization of patients. 

Purpose: We aimed to develop nomograms as prognosis predictors based on imaging characteristics from non-contrast CT (NCCT), CT perfusion (CTP) and clinical characteristics for predicting activity of daily living (ADL) and hospitalization time of ischemic stroke patients. 

Methods: A total of 476 patients were enrolled in the study and divided into the training set (n = 381) and testing set (n = 95). Each of them owned NCCT and CTP images. We propose to extract representing imaging features, as the ASPECTS values from NCCT, and ischemic lesion volumes from CBF and TMAX maps from CTP. Based on imaging features and clinical characteristics, we addressed two main issues: 1) Predicting prognosis according to Barthel index (BI). Binary logistic regression analysis was employed for feature selection, and resulting nomogram was assessed in terms of discrimination capability, calibration and clinical utility; 2) Predicting the hospitalization time of patients. Cox proportional hazard model was used for this purpose. After feature selection, another specific nomogram was established with calibration curves and time-dependent ROC curves for evaluation.

Results: In the task of predicting binary prognosis outcome, a nomogram was constructed with the area under the curve (AUC) value of 0.883 (95% CI: 0.781-0.985), accuracy of 0.853, and F1-scores of 0.909 in testing set. We further tried to predict discharge BI into four classes. Similar performance was achieved as AUC of 0.890 in testing set. In the task of predicting hospitalization time, Cox proportional hazard model was used. Concordance index of the model was 0.700 (se = 0.019), and AUCs for predicting discharge at specific week were higher than 0.80, which demonstrated the superior performance of the model.

Conclusion: The novel noninvasive NCCT- and CTP-based nomograms could predict short-term ADL and hospitalization time of patients with ischemic stroke, thus allowing a personalized clinical outcome prediction and showing a great potential in improving the clinical efficiency.