ObjectiveTo predict the in-hospital mortality risk among patients with ischemic stroke combined by dysphagia using interpretable machine learning methods, so as to provide more evidence-based support for the prognosis prediction of patients with ischemic stroke combined by dysphagia. MethodsMedical record of 308 patients diagnosed with ischemic stroke combined by dysphagia in the Medical Information Mart for Intensive Care Ⅳ (MIMIC-Ⅳ) (2.0) in the United States were retrospectively analyzed. Features of the research data were screened based on the least absolute shrinkage and selection operator, and which were randomly divided into a training set and a test set at a ratio of 7∶3. Then ten models, including logistic regression, random forest, K-nearest neighbor, linear discriminant analysis, naive bayes (NB), neural network, quadratic discriminant analysis, recursive partitioning tree, extreme gradient boosting tree, and support vector machine, etc. were constructed. The predictive effect was measured by calculating the area under the curve (AUC) of receiver operating characteristics. In addition, the calibration curve and Brier score were used to evaluate the calibration degree of the model, and the decision curve was drawn to reflect the clinical net benefit. The Shapley additive explanation method was used to analyze the interpretability of the black box model and explore the important decision-making factors. ResultsThe NB model in the test set showed better predictive ability compared with other models (AUC=0.85, 95%CI: 0.83‒0.88). After interpretability analysis, it was found that blood urea nitrogen (BUN), age, sequential organ failure assessment, bicarbonate, chloride, and hypertension were important risk factors for in-hospital mortality in patients with ischemic stroke combined by dysphagia. ConclusionThe comprehensive performance of the NB model is better than that of the other nine models in predicting the risk of in-hospital mortality in patients with ischemic stroke combined by dysphagia. The interpretability of the model can help clinicians better understand the reasons behind the results and take further reasonable intervention measures for risk factors to improve the survival probability of patients.

Traumatic cerebrospinal fluid leakage commonly presents in traumatic brain injury patients, and it may lead to complications such as meningitis, ventriculitis, brain abscess, subdural hematoma or tension pneumocephalus. When misdiagnosed or inappropriately treated, traumatic cerebrospinal fluid leakage may result in severe complications and may be life-threatening. Some traumatic cerebrospinal fluid leakage has concealed manifestations and is prone to misdiagnosis. Due to different sites and mechanisms of trauma and degree of cerebrospinal fluid leak, treatments for traumatic cerebrospinal fluid leakage varies greatly. Hence, the Craniocerebral Trauma Professional Group of Neurosurgery Branch of Chinese Medical Association and the Neurological Injury Professional Group of Trauma Branch of Chinese Medical Association organized relevant experts to formulate the " Chinese expert consensus on the diagnosis and treatment of traumatic cerebrospinal fluid leakage in adults ( version 2023)" based on existing clinical evidence and experience. The consensus consisted of 16 recommendations, covering the leakage diagnosis, localization, treatments, and intracranial infection prevention, so as to standardize the diagnosis and treatment of traumatic cerebrospinal fluid leakage and improve the overall prognosis of the patients.

Objective:To observe the efficacy of sintilimab combined with apatinib in the treatment of advanced non-small cell lung cancer (NSCLC).Methods:Eighty-two patients with advanced NSCLC who were admitted to Nantong Cancer Hospital from October 2019 to September 2020 were selected for a prospective controlled study. They were divided into control group (treated with apatinib) and combination group (treated with sintilimab + apatinib) using the random number table method, with 41 cases in each group. The short-term clinical efficacy, tumor markers [neuron specific enolase (NSE), cytokeratin 19 fragment antigen (CYFRA21-1)], adverse reactions during treatment and survival were compared between the two groups.Results:The objective remission rate and clinical control rate in the combination group were higher than those in the control group [41.46% (17/41) vs. 19.51% (8/41), 85.37% (35/41) vs. 58.54% (24/41)], and the differences were statistically significant ( χ2 values were 4.66 and 7.31, both P < 0.05). The levels of NSE and CYFRA21-1 in the combination group were lower than those in the control group after treatment [(19.04±2.54) ng/ml vs. (21.35±3.11) ng/ml, (4.58±1.02) μg/L vs. (6.07±1.84) μg/L], and the differences were statistically significant ( t values were 3.68 and 4.54, both P < 0.001). There were no statistical differences in the incidence rates of gastrointestinal reaction, bone marrow depression, fatigue, and liver and kidney function damage between the combination group and the control group during treatment (all P > 0.05). The survival rate of the combination group was higher than that of the control group (71.79% vs. 47.50%), and the difference was statistically significant ( χ2 = 4.84, P = 0.028). Conclusions:Sintilimab combined with apatinib may improve clinical efficacy, reduce tumor marker levels, and improve short-term survival rate of advanced NSCLC patients.