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 observe the clinical efficacy of Shuangye San(the prescription mainly composed of Mori Folium and Nelumbinis Folium)in the treatment of type 2 diabetes mellitus(T2DM)complicated with non-alcoholic fatty liver disease(NAFLD)of spleen deficiency and phlegm stasis type.Methods A total of 80 patients with T2DM complicated with NAFLD of spleen deficiency and phlegm stasis type were randomly divided into a treatment group and a control group,with 40 cases in each group.The control group was treated with conventional western medicine for lowering blood glucose and lipid,protecting liver and lowering enzymes.The treatment group was treated with the granules of Shuangye San orally on the basis of treatment for the control group.The course of treatment lasted for three months.The changes of traditional Chinese medicine(TCM)syndrome scores,homeostasis model assessment of insulin resistance(HOMA-IR),fasting insulin(FINS),fasting blood glucose(FBG),2-hour postprandial blood glucose(2hPG),glycosylated hemoglobin(HbA1C),total cholesterol(TC),triglyceride(TG),low-density lipoprotein cholesterol(LDL-C),high-density lipoprotein cholesterol(HDL-C),liver function indicators and B-ultrasound grading of fatty liver in the two groups were observed before and after treatment.After treatment,the clinical efficacy and safety of the two groups were evaluated.Results(1)After three months of treatment,the total effective rate of the treatment group was 85.00％(34/40),and that of the control group was 70.00％(28/40).The intergroup comparison(tested by chi-square test)showed that the efficacy of the treatment group was significantly superior to that of the control group(P＜0.01).(2)After treatment,the scores of TCM symptoms of obese physique,heaviness and weakness in the limbs,shortness of breath and unwilling to talk,tightness and stabbing pain in the chest,abdominal distension and poor appetite in the two groups were decreased compared with those before treatment(P＜0.05),and the decrease of TCM syndrome scores in the treatment group was significantly superior to that in the control group(P＜0.05).(3)After treatment,the levels of glucose and lipid metabolism indicators of FINS,HOMA-IR,FBG,2hPG,HbA1C,TC,TG and LDL-C in the two groups were significantly decreased compared with those before treatment(P＜0.05),and the level of HDL-C was significantly increased compared with that before treatment(P＜0.05).The decrease of FINS,HOMA-IR,FBG,2hPG,HbA1C,TC,TG and LDL-C levels and the increase of HDL-C levels in the treatment group were significantly superior to those in the control group(P＜0.05).(4)After treatment,the levels of liver function indicators of alanine aminotransferase(ALT),aspartate aminotransferase(AST)and gamma-glutamyl transpeptidase(GGT)in the two groups were significantly decreased compared with those before treatment(P＜0.05),and the decrease of liver function indicators in the treatment group was significantly superior to that in the control group(P＜0.05).(5)After treatment,the B-ultrasound grading of fatty liver of the two groups was significantly improved compared with that before treatment(P＜0.05),and the improvement of fatty liver B-ultrasound grading in the treatment group was significantly superior to that in the control group,and the difference was statistically significant(P＜0.05).(6)During the treatment,there were no adverse reactions such as impairment of liver and kidney function and abnormalities in routine blood,urine and stool test in the two groups.Conclusion Shuangye San exerts certain effect in the treatment of T2DM complicated with NAFLD of spleen deficiency and phlegm stasis type.It can alleviate the clinical symptoms of patients,correct the disorder of glucose and lipid metabolism,and improve liver function and fatty liver B-ultrasound grading.

Objective To study the clinical and pathological characteristics,as well as diagnosis,treatment methods and prognosis of adult patients with chronic active Epstein-Barr virus infection(CAEBVI).Methods Clinical and pathological data of 8 adult patients with CAEBVI admitted to a hospital in Gansu Province from January 2017 to December 2022 were collected retrospectively,clinical and histopathological characteristics,EBV-related test re-sults,as well as treatment and prognosis of patients were analyzed.Results Among 8 CAEBVI patients,3 were males and 5 were females,with the median age of 21.5 years.The median time from onset to diagnosis of CAEBVI was 7 months.The main manifestations were fever,pancytopenia(involving two or three peripheral blood lines),as well as lymph node enlargement,hepatomegaly and splenomegaly.The quantifications of plasma EBV nucleic acid(DNA)were all＞1.0 × 103.The sorting results of EBV infected cells showed that 3 cases were T lymphocytes in-fection,2 were NK cell infection,and 3 were co-infection of T lymphocytes and NK cells.Bone marrow cytological examination of 8 patients showed no atypical lymphocytes,while 6 patients showed hemophagocytic cells.Flow cy-tometey(FCM)typing results showed that no abnormal cell population was detected in all the 8 patients,and no myeloid,B lymphocyte,T lymphocyte and NK cell markers were expressed.The positive rate of T cell receptor(TCR)gene rearrangement was 37.5％(n=3).Histopathology showed that most cases(n=6,75.0％)expressed CD3,partial cases expressed CD4,CD8,CD56,TIA-1,and EBV encoded RNA(EBER),all were positive.The survival rate of patients after treatment was 50.0％(n=4),the follow-up time was 6-51 months,the 1-year sur-vival rate was 85.7％,and the median survival time was 24 months.Conclusion CAEBVI is characterized by varia-ble clinical manifestations that may lead to fatal complications.Early diagnosis and individualized treatment should be performed to reduce mortality of patients.

Abstract: Objective To investigate the current status of streptomycin resistance of Yersinia pestis caused by point mutations of rpsL gene in Qinghai, so as to provide theoretical basis for precise clinical medication and prevention of drug resistance of human plague outbreak in South area of Qinghai Province in the future. Methods A total of 104 representative strains of Yersinia pestis collected from plague patients, vector insects and intermediate hosts in South area of Qinghai Province from 1957 to 2009 were screened, isolated and cultured by Hiss agar plates. The DNA of representative Yersinia pestis was extracted by sodium dodecyl sulfate lysis and phenol-chloroform method. The primers forward primer and reverse primer and TaqMan-MGB probes probe1 [FAM] and probe2 [VIC] were designed for the rpsL gene of streptomycin resistance gene in China. Real-time PCR with TaqMan-MGB fluorescent probe was used to detect the mutations of rpsL gene in streptomycin resistance locus of 104 strains of Yersinia pestis in South area of Qinghai Province. Results The FAM test results of 104 strains in South area of Qinghai Province were positive, corresponding to the detection of rpsL (128 : A ), RFU peak >1 000,negative <200. VIC test results of all tested strains were negative, corresponding to the detection of rpsL (128:G), RFU peak <200, positive >1 000. That is, no strains with rpsL gene mutation related to streptomycin resistance were found in the 104 strains of Yersinia pestis in Qingnan Province. Conclusion This study provides basic data on the distribution of streptomycin resistance of Yersinia pestis in South area of Qinghai Province, and lays a foundation for preventing the occurrence of drug resistance and clinical treatment of Yersinia pestis in South area of Qinghai Province.

Background In mainland China, patients with neovascular age-related macular degeneration (nAMD) have approximately an 40% prevalence of polypoidal choroidal vasculopathy (PCV). This disease leads to recurrent retinal pigment epithelium detachment (PED), extensive subretinal or vitreous hemorrhages, and severe vision loss. China has introduced various treatment modalities in the past years and gained comprehensive experience in treating PCV.Methods A total of 14 retinal specialists nationwide with expertise in PCV were empaneled to prioritize six questions and address their corresponding outcomes, regarding opinions on inactive PCV, choices of anti-vascular endothelial growth factor (anti-VEGF) monotherapy, photodynamic therapy (PDT) monotherapy or combined therapy, patients with persistent subretinal fluid (SRF) or intraretinal fluid (IRF) after loading dose anti-VEGF, and patients with massive subretinal hemorrhage. An evidence synthesis team conducted systematic reviews, which informed the recommendations that address these questions. This guideline used the GRADE (Grading of Recommendations, Assessment, Development, and Evaluation) approach to assess the certainty of evidence and grade the strengths of recommendations. Results The panel proposed the following six conditional recommendations regarding treatment choices. (1) For patients with inactive PCV, we suggest observation over treatment. (2) For treatment-na?ve PCV patients, we suggest either anti-VEGF monotherapy or combined anti-VEGF and PDT rather than PDT monotherapy. (3) For patients with PCV who plan to initiate combined anti-VEGF and PDT treatment, we suggest later/rescue PDT over initiate PDT. (4) For PCV patients who plan to initiate anti-VEGF monotherapy, we suggest the treat and extend (T&E) regimen rather than the pro re nata (PRN) regimen following three monthly loading doses. (5) For patients with persistent SRF or IRF on optical coherence tomography (OCT) after three monthly anti-VEGF treatments, we suggest proceeding with anti-VEGF treatment rather than observation. (6) For PCV patients with massive subretinal hemorrhage (equal to or more than four optic disc areas) involving the central macula, we suggest surgery (vitrectomy in combination with tissue-plasminogen activator (tPA) intraocular injection and gas tamponade) rather than anti-VEGF monotherapy. Conclusions Six evidence-based recommendations support optimal care for PCV patients' management.

OBJECTIVES: To investigate the risk factors for neonatal asphyxia in Hubei Enshi Tujia and Miao Autonomous Prefecture and establish a nomogram model for predicting the risk of neonatal asphyxia. METHODS: A retrospective study was conducted with 613 cases of neonatal asphyxia treated in 20 cooperative hospitals in Enshi Tujia and Miao Autonomous Prefecture from January to December 2019 as the asphyxia group, and 988 randomly selected non-asphyxia neonates born and admitted to the neonatology department of these hospitals during the same period as the control group. Univariate and multivariate analyses were used to identify risk factors for neonatal asphyxia. R software (4.2.2) was used to establish a nomogram model. Receiver operator characteristic curve, calibration curve, and decision curve analysis were used to assess the discrimination, calibration, and clinical usefulness of the model for predicting the risk of neonatal asphyxia, respectively. RESULTS: Multivariate logistic regression analysis showed that minority (Tujia), male sex, premature birth, congenital malformations, abnormal fetal position, intrauterine distress, maternal occupation as a farmer, education level below high school, fewer than 9 prenatal check-ups, threatened abortion, abnormal umbilical cord, abnormal amniotic fluid, placenta previa, abruptio placentae, emergency caesarean section, and assisted delivery were independent risk factors for neonatal asphyxia (P<0.05). The area under the curve of the model for predicting the risk of neonatal asphyxia based on these risk factors was 0.748 (95%CI: 0.723-0.772). The calibration curve indicated high accuracy of the model for predicting the risk of neonatal asphyxia. The decision curve analysis showed that the model could provide a higher net benefit for neonates at risk of asphyxia. CONCLUSIONS The risk factors for neonatal asphyxia in Hubei Enshi Tujia and Miao Autonomous Prefecture are multifactorial, and the nomogram model based on these factors has good value in predicting the risk of neonatal asphyxia, which can help clinicians identify neonates at high risk of asphyxia early, and reduce the incidence of neonatal asphyxia.
Infant, Newborn ; Humans ; Male ; Pregnancy ; Female ; Nomograms ; Retrospective Studies ; Cesarean Section ; Risk Factors ; Asphyxia Neonatorum/etiology*

Humans ; Adult ; Mucormycosis ; Leukemia, Myeloid, Acute/complications* ; Acute Disease ; Antifungal Agents

Humans ; Anemia, Aplastic ; Leukemia, Large Granular Lymphocytic/diagnosis* ; Immunophenotyping

The study investigated the effect of Buyang Huanwu Decoction(BYHWD) on endogenous biomarkers in the urine of rats with chronic inflammation induced by lipopolysaccharide(LPS) using ultra-high performance liquid chromatography-quadrupole-time-of-flight-mass spectrometry(UPLC-Q-TOF-MS), aiming to elucidate the molecular mechanism underlying the therapeutic effect of BYHWD on chronic inflammation from a metabolomics perspective. Male SD rats were randomly divided into a normal group, a model group, and low-, medium-, and high-dose BYHWD groups(7.5, 15, and 30 g·kg~(-1)). The model group and BYHWD groups received tail intravenous injection of LPS(200 μg·kg~(-1)) on the first day of each week, followed by oral administration of BYHWD once a day for four consecutive weeks. Urine samples were collected at the end of the administration period, and UPLC-Q-TOF-MS was used to analyze the metabolic profiles of the rat urine in each group. Multivariate statistical analysis methods such as principal component analysis(PCA), partial least squares-discriminant analysis(PLS-DA), and orthogonal partial least squares-discriminant analysis(OPLS-DA) were used to analyze the effect of BYHWD on endogenous metabolites. One-way ANOVA and variable importance for the projection(VIP) were used to screen for potential biomarkers related to chronic inflammation. The identified biomarkers were subjected to pathway and enrichment analysis using MetaboAnalyst 5.0. A total of 25 potential biomarkers were screened and identified in the rat urine in this experiment. Compared with the normal group, the model group showed significant increases in the levels of 14 substances(P<0.05) and significant decreases in the levels of 11 substances(P<0.05). BYHWD was able to effectively reverse the trend of most endogenous biomarkers. Compared with the model group, BYHWD significantly down-regulated 13 biomarkers(P<0.05) and up-regulated 10 biomarkers(P<0.05). The metabolic products were mainly related to the biosynthesis of pantothenic acid and coenzyme A, tryptophan metabolism, retinol metabolism, and propionate metabolism. BYHWD has therapeutic effect on chronic inflammation induced by LPS, which may be related to its ability to improve the levels of endogenous metabolites, enhance the body's anti-inflammatory and antioxidant capabilities, and restore normal metabolic activity.
Rats ; Male ; Animals ; Chromatography, High Pressure Liquid/methods* ; Lipopolysaccharides ; Rats, Sprague-Dawley ; Metabolomics/methods* ; Inflammation/drug therapy* ; Biomarkers/urine*

This study focuses on the microbial quality control of the Chinese herbal decoction pieces. In view of the shortcomings of traditional culture methods such as slow detection speed and inability to detect unculturable microorganisms, a new method based on ATP bioluminescence technology combined with statistical analysis methods was established to rapidly predict and quantitatively detect the total aerobic microbial count (TAMC) and total yeast and mold count (TYMC) contaminated Bupleurum chinense DC. decoction pieces. Based on the optimized ATP bioluminesence detection system, accurate detection of pure bacterial solution of Escherichia coli, Bacillus subtilis and Staphylococcus aureus can be achieved, with detection limits of 47.86, 89.13 and 1 862.09 CFU·mL^-1, respectively. The detection time was 6.5 h, and the detection cost was as low as 2 yuan/time. The upper and lower warning limits of TAMC were determined by the misjudgment rates of 10% and 20%, respectively. And the warning limit of TYMC was determined by the misjudgment rate of 20%. The proposed crossing method could quickly predict the amount of microbial contamination in Bupleurum chinense DC. decoction pieces. The constructed partial least squares regression (PLSR) model could accurately quantify the quantity of microbial contamination in Bupleurum chinense DC. decoction pieces. The optimal PLSR prediction model for TAMC had a correction coefficient (R²) of 0.826, a root mean square error of correction set (RMSE_E) of 0.468 and a root mean square error of cross-validation set (RMSE_CV) of 0.465. The R², RMSE_E and RMSE_CV in the prediction model of TYMC were 0.778, 0.543 and 0.541, respectively. The aim of this study is to establish a kind of rapid detection method and prediction models for the microbial limit of traditional Chinese medicine and Chinese herbal decoction pieces, and to provide a more convenient and sensitive detection technology for the microbial quality process control of traditional Chinese medicine products.