[[getLangText('background')]]
Chronic Subdural Hematoma (CSDH) is a prevalent neurological disorder, primarily originating from slow venous bleeding from the brain's bridging veins. Manifesting approximately three weeks post-injury, its symptoms encompass focal neurological deficits, cognitive alterations, and signs of elevated intracranial pressure, primarily headaches and reduced consciousness2. In severe cases, CSDH can be fatal3. The elderly population, particularly those above 65 years of age, faces heightened risk due to widespread anticoagulation treatments, natural cerebral atrophy, and increased susceptibility to trauma, While post-traumatic bleeding is commonly recognized as a key contributor, recent research indicates that CSDH's onset and recurrence are multifactorial, involving inflammation, angiogenesis, coagulation disturbances, microbleeds, and exudation.
[[getLangText('parameter_description')]]
UN:Urea Nitrogen, mmol/L
AST:Aspartate Aminotransferase , U/L
DB:Direct Bilirubin, umol/L
TT:Thrombin Time, umol/L
Fibrinogen:Fibrinogen, g/L
SBP:Systolic Blood Pressure, mmHg
HWD:Hematoma's Widest Diameter, mm
Diabetes:The history of diabetes
Age:Age, years
Heart Disease:The history of heart disease
In the Random Forest (RF) model, the clinically significant variables were ranked as follows: age, Aspartate Aminotransferase (AST), Fibrinogen, Thrombin Time (TT), Hematoma's Widest Diameter (HWD), Urea Nitrogen (UN), Direct Bilirubin (DB), Systolic Blood Pressure (SBP), and the presence of heart diseases and diabetes in medical history.
Principle:
First divide the data into training set and test set, then use the cross-validation method to train the model in the training set, train the optimal model as the final model and record the threshold at this time as the final threshold, and finally observe the model in the test performance on the set. By continuously adjusting the parameters of the model, the generalization ability of the model is improved, and the performance of the model in the training set, validation set and test set is relatively optimal.
By the predicted sample into the optimal model, the model will predict the probability of occurrence, generate the SHAP force plot, and then evaluate the risk according to the predicted probability and prediction.