External validation of prognostic models predicting outcome after chronic subdural hematoma

Synthetic minority over-sampling technique-enhanced machine learning models for predicting recurrence of postoperative chronic subdural hematoma

Objective

Chronic subdural hematoma (CSDH) is a neurological condition with high recurrence rates, primarily observed in the elderly population. Although several risk factors have been identified, predicting CSDH recurrence remains a challenge. Given the potential of machine learning (ML) to extract meaningful insights from complex data sets, our study aims to develop and validate ML models capable of accurately predicting postoperative CSDH recurrence.

Methods

Data from 447 CSDH patients treated with consecutive burr-hole irrigations at Wenzhou Medical University's First Affiliated Hospital (December 2014-April 2019) were studied. 312 patients formed the development cohort, while 135 comprised the test cohort. The Least Absolute Shrinkage and Selection Operator (LASSO) method was employed to select crucial features associated with recurrence. Eight machine learning algorithms were used to construct prediction models for hematoma recurrence, using demographic, laboratory, and radiological features. The Border-line Synthetic Minority Over-sampling Technique (SMOTE) was applied to address data imbalance, and Shapley Additive Explanation (SHAP) analysis was utilized to improve model visualization and interpretability. Model performance was assessed using metrics such as AUROC, sensitivity, specificity, F1 score, calibration plots, and decision curve analysis (DCA).

Results

Our optimized ML models exhibited prediction accuracies ranging from 61.0% to 86.2% for hematoma recurrence in the validation set. Notably, the Random Forest (RF) model surpassed other algorithms, achieving an accuracy of 86.2%. SHAP analysis confirmed these results, highlighting key clinical predictors for CSDH recurrence risk, including age, alanine aminotransferase level, fibrinogen level, thrombin time, and maximum hematoma diameter. The RF model yielded an accuracy of 92.6% with an AUC value of 0.834 in the test dataset.

Conclusion

Our findings underscore the efficacy of machine learning algorithms, notably the integration of the RF model with SMOTE, in forecasting the recurrence of postoperative chronic subdural hematoma. Leveraging the RF model, we devised an online calculator that may serve as a pivotal instrument in tailoring therapeutic strategies and implementing timely preventive interventions for high-risk patients.

A Linear Regression Equation for Predicting the Residual Volume of Chronic Subdural Hematoma 1 Week After Surgery

Objective

The outcome of chronic subdural hematoma (CSDH) is influenced not only by the choice of treatment but also by various baseline characteristics. The main objective of this study is to identify the risk factors that can affect the prognosis of CSDH and develop a regression equation based on these risk factors.

Methods

A total of 212 patients with CSDH were included in the study. We collected clinical data including age, gender, and so on, and radiological data including preoperative hematoma volume (V1), effusion volume 1 day after surgery (V2), gas volume 1 day after surgery (V3), and so on. These were considered independent variables, while residual volume 1 week after surgery (V4) was the dependent variable. Univariate linear regression analysis was performed to identify factors that were significantly related. Subsequently, multivariate linear regression analysis was conducted to determine the relationship between each independent variable and the dependent variable. Multiple linear regression analysis was used to obtain a regression equation predicting V4.

Results

We have found that age (t = 3.109, P = 0.002), aspirin (t = 2.762, P = 0.006), hemostatic agents (haemocoagulase, t = 3.731, P < 0.001; vitamin K, t = 2.824, P = 0.005 < 0.05), V2 (t = 8.73, P < 0.001), and V3 (t = 5.968, P < 0.001) are significantly associated with V4. Furthermore, we have developed a regression equation that can predict this volume with CSDH. The fit of the model is robust with an R-squared value of 65.2% > 50%.

Conclusion

Age, aspirin, hemostatic agent, V2, and V3 are significantly associated with V4. We developed a regression equation to predict this volume with CSDH.