Development and Validation of a Nomogram Model for Predicting Unfavorable Functional Outcomes in Ischemic Stroke Patients After Acute Phase
Overview
Authors
Affiliations
Introduction: Prediction of post-stroke functional outcome is important for personalized rehabilitation treatment, we aimed to develop an effective nomogram for predicting long-term unfavorable functional outcomes in ischemic stroke patients after acute phase.
Methods: We retrospectively analyzed clinical data, rehabilitation data, and longitudinal follow-up data from ischemic stroke patients who underwent early rehabilitation at multiple centers in China. An unfavorable functional outcome was defined as a modified Rankin Scale (mRS) score of 3-6 at 90 days after onset. Patients were randomly allocated to either a training or test cohort in a ratio of 4:1. Univariate and multivariate logistic regression analyses were used to identify the predictors for the development of a predictive nomogram. The area under the receiver operating characteristic curve (AUC) was used to evaluate predictive ability in both the training and test cohorts.
Results: A total of 856 patients (training cohort: = 684; test cohort: = 172) were included in this study. Among them, 518 patients experienced unfavorable outcomes 90 days after ischemic stroke. Trial of ORG 10172 in Acute Stroke Treatment classification ( = 0.024), antihypertensive agents use [odds ratio (OR) = 1.86; = 0.041], 15-day Barthel Index score (OR = 0.930; < 0.001) and 15-day mRS score (OR = 13.494; < 0.001) were selected as predictors for the unfavorable outcome nomogram. The nomogram model showed good predictive performance in both the training (AUC = 0.950) and test cohorts (AUC = 0.942).
Conclusion: The constructed nomogram model could be a practical tool for predicting unfavorable functional outcomes in ischemic stroke patients underwent early rehabilitation after acute phase.
Islam M, Alam J, Kumar S, Islam A, Khan M, Rabby S Heliyon. 2024; 10(22):e40246.
PMID: 39605842 PMC: 11600071. DOI: 10.1016/j.heliyon.2024.e40246.
Yassin M, Lu J, Zaman A, Yang H, Cao A, Zeng X Sci Rep. 2024; 14(1):27580.
PMID: 39528656 PMC: 11555321. DOI: 10.1038/s41598-024-78353-y.
Prediction of poststroke independent walking using machine learning: a retrospective study.
Tang Z, Su W, Liu T, Lu H, Liu Y, Li H BMC Neurol. 2024; 24(1):332.
PMID: 39256684 PMC: 11385990. DOI: 10.1186/s12883-024-03849-z.
Huang P, Yi X Int J Immunopathol Pharmacol. 2024; 38:3946320241274231.
PMID: 39167070 PMC: 11339746. DOI: 10.1177/03946320241274231.