Development and assessment of machine learning models for predicting recurrence risk after endovascular treatment in patients with intracranial aneurysms.

Intracranial aneurysms (IAs) remain a major public health concern and endovascular treatment (EVT) has become a major tool for managing IAs. However, the recurrence rate of IAs after EVT is relatively high, which may lead to the risk for aneurysm re-rupture and re-bleed. Thus, we aimed to develop and assess prediction models based on machine learning (ML) algorithms to predict recurrence risk among patients with IAs after EVT in 6 months. Patient population included patients with IAs after EVT between January 2016 and August 2019 in Hunan Provincial People's Hospital, and an adaptive synthetic (ADASYN) sampling approach was applied for the entire imbalanced dataset. We developed five ML models and assessed the models. In addition, we used SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. A total of 425 IAs were enrolled into this study, and 66 (15.5%) of which recurred in 6 months. Among the five ML models, gradient boosting decision tree (GBDT) model performed best. The area under curve (AUC) of the GBDT model on the testing set was 0.842 (sensitivity: 81.2%; specificity: 70.4%). Our study firstly demonstrated that ML-based models can serve as a reliable tool for predicting recurrence risk in patients with IAs after EVT in 6 months, and the GBDT model showed the optimal prediction performance.

[Assessment of facial skeletal growth and response to implanted functional appliance therapy with three-dimensional images].

PURPOSE: To evaluate the facial skeletal growth and response to implanted functional appliance therapy with three-dimensional images. METHODS: Eleven male Beagle dogs (7 months old and in late mixed dentition) were randomly divided into four groups: implanted functional appliance group, semi-implanted functional appliance group, modified Forsus(TM) group and the control group. After the appliances were inserted in the experimental groups for 4, 8, 12 weeks and 4 weeks after the appliances were removed, the facial skeleton and teeth of the Beagle dogs digital information was obtained by using spiral computed tomography, then Mimics 8.1 software and a kind of retro-engineering software called qualify V8.0 were used to establish three-dimensional facial skeletal and dental images of the Beagle dogs. Three-dimensional structure changes of the facial skeleton and teeth in each group at different stages were assessed by the Bjork method, i.e. the superimposition technique based on the "best fit" of anterior cranial base structure and mandible metallic implants. RESULTS: Mandibles in the groups with implanted functional appliance, semi-implanted functional appliance, and modified ForsusTM were obviously displaced forward, while the growth of the maxilla was inhibited in some degree. The displacement of upper teeth in the group with implanted functional appliance was not obvious, while the distal movement of upper teeth in the group with semi-implanted functional appliance and modified ForsusTM was significant compared with that in the control group. CONCLUSIONS: The implanted functional appliance can significantly stimulate the growth of the mandible and avoid the unwanted movement of teeth which is frequently found in other functional appliances. Supported by Wenzhou International Cooperative Research Project (Grant No. B00260027).