A clinical-radiomics nomogram for functional outcome predictions in ischemic stroke

Abstract

Background: Stroke remains the reading cause of death and disability worldwide. Effective and prompt prognostic evaluation is vital for management strategy choice. Radiomics is an emerging non-invasive method used to identify the quantitative imaging indicators for predicting important clinical outcomes. This study was to investigate and validate a radiomics nomogram for predicting ischemic stroke prognosis using the modified Rankin scale (mRS).Methods: Totally 598 consecutive patients with subacute infarction confirmed by diffusion-weighted imaging (DWI) in 2018-2019 were retrospectively assessed. They were assigned to the good (mRS ≤ 2) and poor (mRS > 2) functional outcome groups, respectively. Then, 399 and 199 patients examined by MR scanners 1 and 2, respectively, were assigned to the training and validation cohorts, respectively. Infarction lesions underwent manual segmentation on DWI, extracting 402 radiomic properties, including infarction volume. A radiomics nomogram encompassing patient characteristics and the radiomics signature was built using a multivariate logistic regression model. The performance of the nomogram was evaluated in the training and validation cohorts. Ultimately, decision curve analysis was implemented to assess the clinical value of the nomogram.Results: Stroke lesion volume showed average performance with an area under the curve (AUC) of 0.678. The radiomics signature, including 11 radiomics features, exhibited good prediction performance. Meanwhile, the radiomics nomogram, encompassing clinical characteristics (age, hemorrhage and 24 h National Institutes of Health Stroke Scale score) and the radiomics signature, presented good discriminatory potential in the training cohort (AUC=0.80; 95% confidence interval [CI] 0.75–0.86), which was validated in the validation cohort (AUC=0.73; 95%CI 0.63–0.82). In addition, it demonstrated good calibration in the training (p=0.55) and validation (p=0.21) cohorts. Decision curve analysis confirmed the clinical value of this nomogram.Conclusions: The novel noninvasive clinical-radiomics nomogram shows good performance in predicting ischemic stroke prognosis.