Objective To evaluate short-term effectiveness of staged management for complex tibial plateau fracture with severe soft tissue injury. Methods A clinical data of 12 patients with complex tibial plateau fractures and severe soft tissue injuries between July 2017 and March 2021 and met the selection criteria was retrospectively analyzed. There were 7 males and 5 females with an average age of 43.1 years (range, 33-58 years). All patients were traffic accident injuries and admitted to hospital within 24 hours after injury. The tibial plateau fractures were closed fractures. According to the Schatzker classification standard, the fractures were rated as type Ⅳ in 3 cases, type Ⅴ in 4 cases, and type Ⅵ in 5 cases. According to the Tscherne classification standard, the soft tissue injuries were rated as grade Ⅱ in 4 cases and grade Ⅲ in 8 cases. The treatment of all patients was divided into 3 stages. In the first stage, emergency trans-articular fracture fixation with external fixator was performed; in the second stage, the fracture reduction and internal fixation were performed and bone cement was implanted to fill the bone defect; in the third stage, the bone cement was removed and the bone graft was performed to repair defect. All patients performed joint function exercise after operation as early as possible. Results There was no neurological symptom after all staged managements, the incisions healed by first intention, and no complications such as incision infection or necrosis occurred. All patients were followed up 6-32 months (mean, 16.9 months). The fractures were all anatomical reduction confirmed by the X-ray films after operation. During follow-up, there was no obvious loss of reduction, loosening and rupture of internal fixator, or collapse of the articular surface. All fractures healed after 14-20 weeks (mean, 17.6 weeks). The posterior slope angle of the tibial plateau was (9.7±2.3)° and the varus angle was (3.9±1.9)° immediately after bone grafting, and were (8.5±2.9)° and (4.3±1.9)° respectively at 6 months after operation. There was no significant difference between the two time points (t=0.658, P=0.514; t=?1.167, P=0.103). At last follow-up, the Hospital for Special Surgery (HSS) score was 85-96 (mean, 91.2), and the range of motion of knee was 110°-135° (mean, 120.9°). Conclusion The staged management for complex tibial plateau fracture with severe soft tissue injury can obtain good short-term effectiveness, but the long-term effectiveness needs to be further followed up.
Objective To develop a computer-aided diagnosis model for lung cancer based on routine health examination data for identifying individuals with a current high risk of lung cancer in health screening settings, thereby providing decision support for subsequent clinical confirmation. Methods Individuals who underwent health examinations at the Health Management Center of West China Hospital, Sichuan University, between 2010 and 2022 were enrolled. After screening, a retrospective cohort of 5257 subjects was retained, comprising 1307 patients with lung cancer and 3950 non-lung cancer controls. A three-tier feature fusion model was designed: Heterogeneous feature encoding module: a multi-layer perceptron and bidirectional encoder representations from transformers (BERT) were employed to extract feature vectors from structured data and unstructured data (medical records and imaging report texts), respectively. Heterogeneous feature fusion architecture: dimensional expansion concatenation coupled with a gated recurrent unit based gating network was implemented to achieve multi-scale feature alignment and deep interaction, thereby addressing dimensional discrepancies and information redundancy. Attention-based decision mechanism: word-level attention with weighted pooling was applied to dynamically capture key features and generate risk probability distributions. Model performance was evaluated using precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). Results The proposed model significantly outperformed both single-data-type models and simple concatenation approaches. On the test set, the proposed model achieved a recall of 0.861, an F1-score of 0.882, and an AUC-ROC of 0.972, substantially surpassing the best-performing model trained on structured data alone (extreme gradient boosting: recall=0.630, F1-score=0.725, AUC-ROC=0.916) and the model trained on unstructured data alone (BERT coupled with a bidirectional long short-term memory network: recall=0.833, F1-score=0.846, AUC-ROC=0.944). Feature elimination experiments demonstrated minimal performance variation across different feature subsets, confirming the model’s capability to effectively identify and mitigate the impact of irrelevant features. Subgroup analyses revealed that the model performed optimally in female subjects (recall=0.835, F1-score=0.838, AUC-ROC=0.950) and individuals aged >69 years (recall=0.913, F1-score=0.875, AUC-ROC=0.911). Conclusion The proposed model based on heterogeneous health examination data can identify high-risk individuals for lung cancer among health examination populations using only routine screening data, thereby facilitating the early diagnosis of lung cancer in this population.
