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.

Fabrication of Nerve Growth Factor Encapsulated Aligned Poly(ε-Caprolactone) Nanofibers and Their Assessment as a Potential Neural Tissue Engineering Scaffold.

Peripheral nerve injury is a serious clinical problem to be solved. There has been no breakthrough so far and neural tissue engineering offers a promising approach to promote the regeneration of peripheral neural injuries. In this study, emulsion electrospinning technique was introduced as a flexible and promising technique for the fabrication of random (R) and aligned (A) Poly(ε-caprolactone) (PCL)-Nerve Growth Factor (NGF)&Bovine Serum Albumin (BSA) nanofibrous scaffolds [(R/A)-PCL-NGF&BSA], where NGF and BSA were encapsulated in the core while PCL form the shell. Random and aligned pure PCL, PCL-BSA, and PCL-NGF nanofibers were also produced for comparison. The scaffolds were characterized by Field Emission Scanning Electron Microscopy (FESEM) and water contact angle test. Release study showed that, with the addition of stabilizer BSA, a sustained release of NGF from emulsion electrospun PCL nanofibers was observed over 28 days. [3-(4,5-dimethylthiazol-2-yl)-5-(3-carboxymethoxyphenyl)-2-(4-sulfophenyl)-2H-tetrazolium, inner salt; MTS] assay revealed that (R/A)-PCL-NGF and (R/A)-PCL-NGF&BSA scaffolds favored cell growth and showed no cytotoxicity to PC12 cells. Laser scanning confocal microscope images exhibited that the A-PCL-NGF&BSA scaffold increased the length of neurites and directed neurites extension along the fiber axis, indicating that the A-PCL-NGF&BSA scaffold has a potential for guiding nerve tissue growth and promoting nerve regeneration.