BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

Objective:To explore the impact of standardized training on the career planning of undergraduate nursing students, and to provide a reference for the formulation of reasonable interventions.Methods:Semi-structured in-depth interviews were conducted among 15 undergraduate nursing students to obtain their real experience, and the data were analyzed using phenomenological methods.Results:Some undergraduates expressed their understanding and acceptance of the training policy and adopted a positive coping attitude; some undergraduates had negative emotions and chose to study or change careers; the main reasons for negative emotions were high economic pressure, family support, and lack of belonging. And lack of relevant information sources and guidance on training.Conclusion:The relevant departments should strengthen the publicity and interpretation of the standardized training system, cultivate professional identity, guide nursing students to choose the appropriate employment direction, and at the same time, they should improve the comprehensive treatment of regulated students and reduce the worries of nursing students when choosing a career, so that they can correctly view standardized training and make correct and reasonable career plans to reduce the brain drain of the nursing team.

Objective To compare the sonographic features as well as clinical histopathological features of follicular variant papillary thyroid carcinoma(FVPTC) and conventional papillary thyroid carcinoma (CPTC) in pediatric patients.Methods From Jan.2006 to Dec.2017,26 FVPTC patients and 82 CPTC patients were enrolled in this study.The clinical histopathological findings and the sonographic features were compared between the two groups.FVPTCs and CPTCs were divided into PTC-like and follicular neoplasm(FN)-like based on sonographic characteristics.Results The mean nodule size of FVPTCs was larger than that of conventional PTCs.Extrathyroid invasion and cervical lymph node metastasis did not have significant difference between CPTC and FVPTC patients(53.8％ vs 62.2％ and 76.9％ vs 82.9％,respectively).Multiple nodules(P=0.000)and distant pulmonary metastases(P=0.024) were more frequent in CPTCs than in FVPTCs(P＜0.05).The rate of an ill-defined margin (P=0.000) and calcification (P=0.003)in terms of sonographic features were lower in FVPTCs than conventional PTCs(P＜0.05).A Ⅴ+Ⅵ diagnosis of PTC on FNAC of FVPTCs was less common than that of conventional PTCs (P=0.014).Multifocality(P=0.000),extrathyroidal invasion (P=0.000),and lymph node metastasis (P=0.000) were significantly different between PTC-like FVPTCs and FN-like FVPTCs.Conclusion FVPTC in children and adolescents shows a relatively larger size,more benign sonographic features,and a lower diagnostic rate of PTC by FNAC compared with conventional PTCs in pediatric patients.

Objective: To analyze the infection characteristics of patients in acute gastroenteritis outbreaks caused by noroviruses. Methods: Between April 2014 and March 2016, the clinical data and samples were collected from the patients in acute gastroenteritis outbreaks caused by noroviruses in Beijing. Noroviruses were detected and genotyped using real time RT-PCR, and the infection characteristics of norovirus gastroenteritis were analyzed using the descriptive epidemiological method. Results: A total of 1743 clinical diagnosed cases of norovirus gastroenteritis were collected, and children under 12 years old accounted for 77.68% (1354/1743). The detection rate of noroviruses was 73.98% (509/688). The detection rates of noroviruses in fecal, swab and vomitus samples were gradually decreased (χ²=67.798, P<0.001). Among these clinical diagnosed cases, vomiting was the most common symptom (93.98%), followed by abdominal pain (40.34%), diarrhea (30.35%) and fever (27.94%). The most common symptom of patients under 6 years old was vomiting(98.14%), whereas diarrhea was most common among over 18 years old patients (68.12%). With the increase of age of the patients, the incidence of vomiting was gradually decreased (χ²=100.913, P<0.001), whereas the incidence of diarrhea was gradually increased (χ²=261.164, P<0.001). There was no statistical difference in vomiting, diarrhea and abdominal pain symptoms between patients infected with genogroup Ⅰ and Ⅱ noroviruses, and patients infected with genogroup Ⅱ (34.49%, 149/432) had the higher incidence rate of fever than that of genogroup Ⅰ (18.18%, 14/77) (χ²=7.985, P<0.01). Conclusions Noroviruses mainly infected children under 12 years old in acute gastroentertis outbreaks. The most common symptom of patients with acute gastroenteritis caused by noroviruses was vomiting, and the incidences of vomiting and diarrhea were significantly correlated with age of the patients. Patients infected with genogroup Ⅱ had the higher incidence rate of fever than genogroup Ⅰ infection.