Cheng-Chi James Chu

Background: Tibial plateau fractures represent a diverse group of intra-articular injuries that can be difficult to detect and characterize on initial imaging. The aim of the present study was to develop an artificial intelligence (AI) diagnostic tool for identifying tibial plateau fractures on radiographs. Methods: In this retrospective study, we analyzed radiographs that had been made from January 2018 to December 2020 for 1,809 patients, with an equal distribution of male and female adults. A total of 3,821 anteroposterior and lateral knee radiographs were evaluated with use of the EfficientNet B3 AI model, with computed tomography (CT) images being used as the ground truth. Evaluation metrics focused on the area under the receiver operating characteristic curve (AUC) and positive predictive values across different subgroups. Results: Our AI model attained AUCs of 0.98 and 0.97 for detecting tibial plateau fractures in the test and external validation datasets, respectively. Subgroup analysis revealed diverse positive predictive values across different Schatzker types and 3-column classifications. Conclusions: Our deep learning model exhibits newfound ability for identifying tibial plateau fractures. However, we encountered several limitations, such as imbalances among the sizes of various subgroups in the dataset and an inability to identify radiographs containing foreign objects or other defects. Level of Evidence: Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs.