Combining Clinical-Radiomics Features With Machine Learning Methods for Building Models to Predict Postoperative Recurrence in Patients With Chronic Subdural Hematoma: Retrospective Cohort Study

Abstract

BackgroundChronic subdural hematoma (CSDH) represents a prevalent medical condition, posing substantial challenges in postoperative management due to risks of recurrence. Such recurrences not only cause physical suffering to the patient but also add to the financial burden on the family and the health care system. Currently, prognosis determination largely depends on clinician expertise, revealing a dearth of precise prediction models in clinical settings. ObjectiveThis study aims to use machine learning (ML) techniques for the construction of predictive models to assess the likelihood of CSDH recurrence after surgery, which leads to greater benefits for patients and the health care system. MethodsData from 133 patients were amassed and partitioned into a training set (n=93) and a test set (n=40). Radiomics features were extracted from preoperative cranial computed tomography scans using 3D Slicer software. These features, in conjunction with clinical data and composite clinical-radiomics features, served as input variables for model development. Four distinct ML algorithms were used to build predictive models, and their performance was rigorously evaluated via accuracy, area under the curve (AUC), and recall metrics. The optimal model was identified, followed by recursive feature elimination for feature selection, leading to enhanced predictive efficacy. External validation was conducted using data sets from additional health care facilities. ResultsFollowing rigorous experimental analysis, the support vector machine model, predicated on clinical-radiomics features, emerged as the most efficacious for predicting postoperative recurrence in patients with CSDH. Subsequent to feature selection, key variables exerting significant impact on the model were incorporated as the input set, thereby augmenting its predictive accuracy. The model demonstrated robust performance, with metrics including accuracy of 92.72%, AUC of 91.34%, and recall of 93.16%. External validation further substantiated its effectiveness, yielding an accuracy of 90.32%, AUC of 91.32%, and recall of 88.37%, affirming its clinical applicability. ConclusionsThis study substantiates the feasibility and clinical relevance of an ML-based predictive model, using clinical-radiomics features, for relatively accurate prognostication of postoperative recurrence in patients with CSDH. If the model is integrated into clinical practice, it will be of great significance in enhancing the quality and efficiency of clinical decision-making processes, which can improve the accuracy of diagnosis and treatment, reduce unnecessary tests and surgeries, and reduce the waste of medical resources.