Prediction of acute cerebrovascular stroke disability using mSOAR score (Stroke subtype, Oxfordshire Community Stroke Project, age, mRS and NIHSS)

Abdelghany, Hend; Elsayed, Mohamed A.; Elmeligy, Amgad; Hatem, Ghada

doi:10.1186/s41983-023-00626-6

Cited by 1 publication

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patients with mRS > 2 before the latest stroke onset were more likely to have an unfavorable 90-day mRS. Notably, 92.8% of patients with mRS > 2 prior to stroke onset had unfavorable mRS at 90 days, compared to 38.5% of those with mRS ≤ 2 ( 10 , 12 ).…”

Section: Discussionmentioning

confidence: 97%

“…The predictability of various scoring systems was examined, and the modified SOAR (mSOAR) score was reported to be effective in predicting post-stroke disability ( 10 ). Similarly, the impact of factors such as age, stroke history, heart rate, and TOAST classification on the prognosis of transient ischemic attack (TIA) or minor stroke patients was discussed, and they were integrated into machine learning models for predictive purposes ( 11 ).…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Predicting 90-day prognosis for patients with stroke: a machine learning approach

Abujaber,

Alkhawaldeh,

Imam

et al. 2023

Front. Neurol.

View full text Add to dashboard Cite

BackgroundStroke is a significant global health burden and ranks as the second leading cause of death worldwide.ObjectiveThis study aims to develop and evaluate a machine learning-based predictive tool for forecasting the 90-day prognosis of stroke patients after discharge as measured by the modified Rankin Score.MethodsThe study utilized data from a large national multiethnic stroke registry comprising 15,859 adult patients diagnosed with ischemic or hemorrhagic stroke. Of these, 7,452 patients satisfied the study’s inclusion criteria. Feature selection was performed using the correlation and permutation importance methods. Six classifiers, including Random Forest (RF), Classification and Regression Tree, Linear Discriminant Analysis, Support Vector Machine, and k-Nearest Neighbors, were employed for prediction.ResultsThe RF model demonstrated superior performance, achieving the highest accuracy (0.823) and excellent discrimination power (AUC 0.893). Notably, stroke type, hospital acquired infections, admission location, and hospital length of stay emerged as the top-ranked predictors.ConclusionThe RF model shows promise in predicting stroke prognosis, enabling personalized care plans and enhanced preventive measures for stroke patients. Prospective validation is essential to assess its real-world clinical performance and ensure successful implementation across diverse healthcare settings.

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Literature Reviewmentioning

confidence: 99%