首页|First Affiliated Hospital of Anhui Medical University Reports Findings in Subdur al Hematoma (Combining Clinical-Radiomics Features With Machine Learning Methods for Building Models to Predict Postoperative Recurrence in Patients With Chroni c ...)
First Affiliated Hospital of Anhui Medical University Reports Findings in Subdur al Hematoma (Combining Clinical-Radiomics Features With Machine Learning Methods for Building Models to Predict Postoperative Recurrence in Patients With Chroni c ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Central Nervous System Diseases and Conditions - Subdural Hematoma is the subject of a report. Accordi ng to news reporting originating from Hefei, People’s Republic of China, by News Rx correspondents, research stated, “Chronic subdural hematoma (CSDH) represents a prevalent medical condition, posing substantial challenges in postoperative m anagement due to risks of recurrence. Such recurrences not only cause physical s uffering to the patient but also add to the financial burden on the family and t he health care system.” Our news editors obtained a quote from the research from the First Affiliated Ho spital of Anhui Medical University, “Currently, prognosis determination largely depends on clinician expertise, revealing a dearth of precise prediction models in clinical settings. This study aims to use machine learning (ML) techniques fo r the construction of predictive models to assess the likelihood of CSDH recurre nce after surgery, which leads to greater benefits for patients and the health c are system. Data from 133 patients were amassed and partitioned into a training set (n=93) and a test set (n=40). Radiomics features were extracted from preoper ative cranial computed tomography scans using 3D Slicer software. These features , in conjunction with clinical data and composite clinical-radiomics features, s erved 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 usi ng data sets from additional health care facilities. Following rigorous experime ntal analysis, the support vector machine model, predicated on clinical-radiomic s features, emerged as the most efficacious for predicting postoperative recurre nce in patients with CSDH. Subsequent to feature selection, key variables exerti ng significant impact on the model were incorporated as the input set, thereby a ugmenting its predictive accuracy. The model demonstrated robust performance, wi th metrics including accuracy of 92.72%, AUC of 91.34% , and recall of 93.16%. External validation further substantiated i ts effectiveness, yielding an accuracy of 90.32%, AUC of 91.32 % , and recall of 88.37%, affirming its clinical applicability. This study substantiates the feasibility and clinical relevance of an ML-based predic tive model, using clinical-radiomics features, for relatively accurate prognosti cation of postoperative recurrence in patients with CSDH.”
HefeiPeople’s Republic of ChinaAsiaCentral Nervous System Diseases and ConditionsClinical ResearchClinical Tri als and StudiesCyborgsEmerging TechnologiesHealth and MedicineMachine Le arningSubdural Hematoma
NETL
NSTL
