Machine learning is an effective method to predict the 3-month prognosis of patients with acute ischemic stroke

• Published in: Frontiers in neurology Vol. 15; p. 1407152
• Main Authors: Huang, Qing, Shou, Guang-Li, Shi, Bo, Li, Meng-Lei, Zhang, Sai, Han, Mei, Hu, Fu-Yong
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 12.06.2024
• Subjects: ischemic stroke; machine learning; Neurology; prediction model; prognosis; random forest; prediction model; random forest; machine learning; prognosis; ischemic stroke
• ISSN: 1664-2295; 1664-2295
• DOI: 10.3389/fneur.2024.1407152

Upwards of 50% of acute ischemic stroke (AIS) survivors endure varying degrees of disability, with a recurrence rate of 17.7%. Thus, the prediction of outcomes in AIS may be useful for treatment decisions. This study aimed to determine the applicability of a machine learning approach for forecasting early outcomes in AIS patients. A total of 659 patients with new-onset AIS admitted to the Department of Neurology of both the First and Second Affiliated Hospitals of Bengbu Medical University from January 2020 to October 2022 included in the study. The patient' demographic information, medical history, Trial of Org 10,172 in Acute Stroke Treatment (TOAST), National Institute of Health Stroke Scale (NIHSS) and laboratory indicators at 24 h of admission data were collected. The Modified Rankine Scale (mRS) was used to assess the 3-mouth outcome of participants' prognosis. We constructed nine machine learning models based on 18 parameters and compared their accuracies for outcome variables. Feature selection through the Least Absolute Shrinkage and Selection Operator cross-validation (Lasso CV) method identified the most critical predictors for early prognosis in AIS patients as white blood cell (WBC), homocysteine (HCY), D-Dimer, baseline NIHSS, fibrinogen degradation product (FDP), and glucose (GLU). Among the nine machine learning models evaluated, the Random Forest model exhibited superior performance in the test set, achieving an Area Under the Curve (AUC) of 0.852, an accuracy rate of 0.818, a sensitivity of 0.654, a specificity of 0.945, and a recall rate of 0.900. These findings indicate that RF models utilizing general clinical and laboratory data from the initial 24 h of admission can effectively predict the early prognosis of AIS patients.