Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Elderly hypertensive patients diagnosed with transient ischemic attack (TIA) are at a heightened risk for developing acute ischemic stroke (AIS). This underscores the critical need for effective risk prediction and identification of predictive factors. In our study, we utilized patient data from per...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2024-01, Vol.14 (1), p.695-695, Article 695
Main Authors: Shu, Chang, Zheng, Chenguang, Luo, Da, Song, Jie, Jiang, Zhengyi, Ge, Le
Format: Article
Language:English
Subjects:
631/114/1305
631/114/2164
692/499
692/617/375/1370
692/617/375/534
Aged
Factor Analysis, Statistical
Hospital Information Systems
Humanities and Social Sciences
Humans
Hypertension
Information systems
Ischemia
Ischemic Attack, Transient - epidemiology
Ischemic Stroke - epidemiology
Mental Recall
multidisciplinary
Patients
Peripheral blood
Science
Science (multidisciplinary)
Stroke
Transient ischemic attack
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Elderly hypertensive patients diagnosed with transient ischemic attack (TIA) are at a heightened risk for developing acute ischemic stroke (AIS). This underscores the critical need for effective risk prediction and identification of predictive factors. In our study, we utilized patient data from peripheral blood tests and clinical profiles within hospital information systems. These patients were followed for a three-year period to document incident AIS. Our cohort of 11,056 individuals was randomly divided into training, validation, and testing sets in a 5:2:3 ratio. We developed an XGBoost model, developed using selected indicators, provides an effective and non-invasive method for predicting the risk of AIS in elderly hypertensive patients diagnosed with TIA. Impressively, this model achieved a balanced accuracy of 0.9022, a recall of 0.8688, and a PR-AUC of 0.9315. Notably, our model effectively encapsulates essential data variations involving mixed nonlinear interactions, providing competitive performance against more complex models that incorporate a wider range of variables. Further, we conducted an in-depth analysis of the importance and sensitivity of each selected indicator and their interactions. This research equips clinicians with the necessary tools for more precise identification of high-risk individuals, thereby paving the way for more effective stroke prevention and management strategies.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-51402-2