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

Tumor cells expression of programmed death ligand-1 (PD-L1) is a major mechanism of immune escape and a predictor of therapeutic efficacy of immune checkpoint inhibitors. The expression of PD-L1 is regulated by a variety of mechanisms, among which epigenetic modifications such as DNA methylation, histone modification and non-coding RNA can promote the occurrence, development and drug resistance of tumors by regulating the expression of PD-L1. To clarify its regulation mechanism can bring new ideas for clinical immunotherapy of tumors.

OBJECTIVETo explore the possible mechanism and protective effect of BMSCs (bone mesenchymal stem cells) carrying superoxide dismutase (SOD) gene on mice with paraquat-induced acute lung injury.

METHODSTo establish the cell line of BMSCs bringing SOD gene, lentiviral vector bringing SOD gene was built and co-cultured with BMSCs. A total of 100 BALB/c mice were randomly divided into five groups, namely Control group, poisoning group (PQ group) , BMSCs therapy group (BMSC group) , BMSCs-Cherry therapy group (BMSC-Cherry group) , BMSCs-SOD therapy group (BMSC-SOD group) . PQ poisoning model was produced by stomach lavaged once with 1 ml of 25 mg/kg PQ solution, and the equal volume of normal saline (NS) was given to Control group mice instead of PQ. The corresponding BMSCs therapy cell lines were delivered to mice through the tail vein of mice 4h after PQ treatment.Five mice of each group were sacrificed 3 d, 7 d, 14 d and 21 days after corresponding BMSCs therapy cell lines administration, and lung tissues of mice were taken to make sections for histological analysis. The serum levels of glutathione (GSH) , malondialdehyde (MDA) , SOD, and the levels of transforming growth factor-β (TGF-β) and tumor necrosis factor-α (TNF-α) in lung tissue were determined. The level of SOD was assayed by Westen-blot.

RESULTSCompared with Control group, the early (3 days) levels of SOD protein in lung tissue of PQ group obviously decreased, and the late (21 days) levels of SOD obviously increased, while in therapy groups, that was higher than that in PQ group, and the BMSCs-SOD group showed most obvious (all P<0.05) . Compared with Control group, the levels of plasma GSH and SOD of PQ group and each therapy group wae significantly lower than those in Control group, while in therapy groups, those were higher than those of PQ group, and the BMSCs-SOD group showed most obvious (all P<0.05) .Compared with Control group, the level of plasma MDA, TNF-α and TGF-β in PQ group and therapy groups were significantly higher, while in therapy groups, that was lower than that in PQ group, and the BMSCs-SOD group showed most obvious (all P<0.05) . Lung biopsy showed that, the degree of lung tissue damage in each therapy group obviously reduced.

CONCLUSIONSOD is the key factor of the removal of reactive oxygen species (ROS) in cells, that can obviously inhibit the oxidative stress damage and the apoptosis induced by PQ, thus significantly increasing alveolar epithelial cell ability to fight outside harmful environment.

Acute Lung Injury ; chemically induced ; therapy ; Animals ; Antioxidants ; metabolism ; Cell Line ; Glutathione ; blood ; Lung ; pathology ; Malondialdehyde ; blood ; Mesenchymal Stem Cell Transplantation ; Mice ; Mice, Inbred BALB C ; Oxidative Stress ; Paraquat ; poisoning ; Superoxide Dismutase ; blood ; genetics ; Transforming Growth Factor beta ; metabolism ; Tumor Necrosis Factor-alpha ; metabolism