Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

OBJECTIVE: To investigate the characteristics of gut microbiota changes in patients with acute myeloid leukemia (AML) undergoing induction chemotherapy and to explore the relationship between infectious complications and gut microbiota. METHODS: Fecal samples were collected from 37 newly diagnosed AML patients at four time points: before induction chemotherapy, during chemotherapy, during the neutropenic phase, and during the recovery phase. Metagenomic sequencing was used to analyze the dynamic changes in gut microbiota. Correlation analyses were conducted to assess the relationship between changes in gut microbiota and the occurrence of infectious complications. RESULTS: During chemotherapy, the gut microbiota α-diversity (Shannon index) of AML patients exhibited significant fluctuations. Specifically, the diversity decreased significantly during induction chemotherapy, further declined during the neutropenic phase (P < 0.05, compared to baseline), and gradually recovered during the recovery phase, though not fully returning to baseline levels.The abundances of beneficial bacteria, such as Firmicutes and Bacteroidetes, gradually decreased during chemotherapy, whereas the abundances of opportunistic pathogens, including Enterococcus, Klebsiella, and Escherichia coli, progressively increased.Analysis of the dynamic changes in gut microbiota of seven patients with bloodstream infections revealed that the bloodstream infection pathogens could be detected in the gut microbiota of the corresponding patients, with their abundance gradually increasing during the course of infection. This finding suggests that bloodstream infections may be associated with opportunistic pathogens originating from the gut microbiota.Compared to non-infected patients, the baseline samples of infected patients showed a significantly lower relative abundance of Bacteroidetes (P < 0.05). Regression analysis indicated that Bacteroidetes abundance is an independent predictive factor for infectious complications (P < 0.05, OR =13.143). CONCLUSION During induction chemotherapy in AML patients, gut microbiota α-diversity fluctuates significantly, and the abundance of opportunistic pathogens increase, which may be associated with bloodstream infections. Patients with lower baseline Bacteroidetes abundance are more prone to infections, and its abundance can serve as an independent predictor of infectious complications.
Humans ; Gastrointestinal Microbiome ; Leukemia, Myeloid, Acute/microbiology* ; Induction Chemotherapy ; Feces/microbiology* ; Male ; Female ; Middle Aged

Objective To elucidate the clinical significance of high expression levels of endonuclease meiosis 1(EME1)in the prognosis of hepatocellular carcinoma(HCC).Methods The Cancer Genome Atlas(TCGA)and Gene Expression Omnibus(GEO)databases were used to screen and analyze differential gene expression between HCC and non-tumor tissues.A retrospective collection of liver tissue samples from 80 HCC patients who underwent hepatectomy in the Fifth Medical Center of Chinese PLA General Hospital between January 2010 and December 2014 was performed.Immunohistochemistry analysis was employed to detect the EME1 expression levels.Survival analysis was then conducted to assess the impact of EME1 expression on 5-year postoperative survival rate of HCC patients.Additionally,gene enrichment analysis was applied to predict the function of EME1 in HCC.Results A total of 371 HCC tissue samples and 50 non-tumor liver tissue samples from TCGA database were analyzed,revealing significantly higher EME1 expression in HCC tissues.Microarray analysis of 107 samples within the GEO database(70 HCC tissues and 37 non-tumor tissues)confirmed that EME1 mRNA expression was markedly elevated in HCC tissues compared with non-tumor tissues(P<0.05).The 5-year overall survival(OS)rate was notably lower in high EME1 expression group than that in low expression group(44.1%vs.53.0%,P<0.05).Semi-quantitative immunohistochemistry analysis demonstrated that patients with high EME1 expression had a significantly lower OS rate than those with low EME1 expression(32.8%vs.45.0%,P<0.05).Multivariate COX regression analysis identified that high EME1 expression(HR=2.234,95%CI 1.073-4.649,P=0.032)and advanced China liver caner(CNLC)staging(HR=4.317,95%CI 1.799-10.359,P=0.001)were independent risk factors for the 5-year OS of post-operation patients with HCC.Conclusion Elevated EME1 expression in HCC tissues correlates with an adverse prognosis of HCC and suggests that EME1 could serve as a potential therapeutic target for HCC.

OBJECTIVE: To assess the risk of aristolochic acid (AA)-associated cancer in patients with AA nephropathy (AAN). METHODS: A retrospective study was conducted on patients diagnosed with AAN at Peking University First Hospital from January 1997 to December 2014. Long-term surveillance and follow-up data were analyzed to investigate the influence of different factors on the prevalence of cancer. The primary endpoint was the incidence of liver cancer, and the secondary endpoint was the incidence of urinary cancer during 1 year after taking AA-containing medication to 2014. RESULTS: A total of 337 patients diagnosed with AAN were included in this study. From the initiation of taking AA to the termination of follow-up, 39 patients were diagnosed with cancer. No cases of liver cancer were observed throughout the entire follow-up period, with urinary cancer being the predominant type (34/39, 87.17%). Logistic regression analysis showed that age, follow-up period, and diabetes were potential risk factors, however, the dosage of the drug was not significantly associated with urinary cancer. CONCLUSIONS No cases of liver cancer were observed at the end of follow-up. However, a high prevalence of urinary cancer was observed in AAN patients. Establishing a direct causality between AA and HCC is challenging.
Humans ; Retrospective Studies ; Incidence ; Carcinoma, Hepatocellular ; Liver Neoplasms/epidemiology* ; Kidney Diseases/chemically induced* ; Aristolochic Acids/adverse effects*

Objective To explore mechanism of piracetam for the treatment of spinal cord injury in rats through mitogen-activated protein kinase(MAPK)pathway.Methods Fifty-four healthy 6-week-old SD female rats with body weight of 80 to 100 g were divided into sham operation group,spinal cord injury group and piracetam group by random number table method,with 18 rats in each group.Spinal cord injury model was established in spinal cord injury group and piracetam group using percussion apparatus,while sham operation group did not damage spinal cord.Piracetam group was injected with pirac-etam injection through tail vein according to 5 ml·kg-1 standard,once a day for 3 days;the other two groups were injected with normal saline at the same dose,the same frequency and the same duration.The rats were sacrificed at 1,3,and 7 days after surgery,and changes of Basso,Beattie and Bresnahan(BBB)locomotor rating scale was observed and compared.Enzyme-linked immunosorbent assay(ELISA)was used to detect spinal cord inflammatory factors,such as interleukin-6(IL-6),in-terleukin-10(IL-10),interleukin-1β(interleukin-1β),necrosis factor-α(IL-1β)and tumor necrosis factor-α(TNF-α);HE staining was used to observe morphological changes of rats with spinal cord injury,and immunohistochemistry was used to observe expression level of aquaporin 4(AQP4).The activation of MAPK signaling pathway in spinal cord of rats after spinal cord injury was observed by western blotting(WB).Results BBB scores of sham operation group on 1,3 and 7 day were 21 points.In spinal cord injury group,the scores were(1±1),(4±1)and(7±2);piracetam group was(1±1),(5±1),(9±2),re-spectively;the difference between spinal cord injury group and sham operation group was statistically significant(P＜0.05).HE staining showed that no abnormality was found in sham operation group.In spinal cord injury group,bleeding and degeneration of spinal cord tissue appeared at 1 day after operation;flaky necrotic areas were appeared in spinal cord at 3 days after surgery,and spinal cord tissue began to slowly repair at 7 days after surgery.In piracetam group,the bleeding area was less than that of spinal cord injury group at 1 day after surgery;at 3 days after operation,the necrotic area was reduced and the range of nuclear disappearance was reduced;and the spinal cord began to recover slowly at 7 days after surgery.AQP4 staining of spinal cord of rats in sham operation group was weak at 1,3 and 7 days after modeling,AQP4 staining was deepened and area increased in spinal cord injury group,AQP4 staining of piracetam group was lighter than that of spinal cord injury group,and the positive cells were slightly increased and the staining was slightly darker than that of sham operation group.At 1,3 and 7 days,the level of IL-6,IL-10,IL-1β and TNF-α in spinal cord injury group were higher than those in sham operation group and piracetam group(P＜0.05).Compared with spinal cord injury group,the area of spinal cord bleeding and necrosis were de-creased by HE staining in piracetam group,and AQP4 staining was decreased by immunohistochemistry.WB results showed that P-ERK,P-JNK and P-P38 levels in spinal cord injury group at 3 days were higher than those in sham operation group and piracetam group(P＜0.05).Conclusion Piracetam not only showed significant effect in promoting motor function recovery after spinal cord injury,but also showed positive therapeutic potential in reducing lesion area,regulating AQP4 expression to reduce edema,and reducing inflammatory response by regulating MAPK signaling pathway.

Objective To investigate the clinical characteristics and prognosis of pneumococcal meningitis(PM),and drug sensitivity of Streptococcus pneumoniae(SP)isolates in Chinese children.Methods A retrospective analysis was conducted on clinical information,laboratory data,and microbiological data of 160 hospitalized children under 15 years old with PM from January 2019 to December 2020 in 33 tertiary hospitals across the country.Results Among the 160 children with PM,there were 103 males and 57 females.The age ranged from 15 days to 15 years,with 109 cases(68.1% )aged 3 months to under 3 years.SP strains were isolated from 95 cases(59.4% )in cerebrospinal fluid cultures and from 57 cases(35.6% )in blood cultures.The positive rates of SP detection by cerebrospinal fluid metagenomic next-generation sequencing and cerebrospinal fluid SP antigen testing were 40% (35/87)and 27% (21/78),respectively.Fifty-five cases(34.4% )had one or more risk factors for purulent meningitis,113 cases(70.6% )had one or more extra-cranial infectious foci,and 18 cases(11.3% )had underlying diseases.The most common clinical symptoms were fever(147 cases,91.9% ),followed by lethargy(98 cases,61.3% )and vomiting(61 cases,38.1% ).Sixty-nine cases(43.1% )experienced intracranial complications during hospitalization,with subdural effusion and/or empyema being the most common complication[43 cases(26.9% )],followed by hydrocephalus in 24 cases(15.0% ),brain abscess in 23 cases(14.4% ),and cerebral hemorrhage in 8 cases(5.0% ).Subdural effusion and/or empyema and hydrocephalus mainly occurred in children under 1 year old,with rates of 91% (39/43)and 83% (20/24),respectively.SP strains exhibited complete sensitivity to vancomycin(100% ,75/75),linezolid(100% ,56/56),and meropenem(100% ,6/6).High sensitivity rates were also observed for levofloxacin(81% ,22/27),moxifloxacin(82% ,14/17),rifampicin(96% ,25/26),and chloramphenicol(91% ,21/23).However,low sensitivity rates were found for penicillin(16% ,11/68)and clindamycin(6% ,1/17),and SP strains were completely resistant to erythromycin(100% ,31/31).The rates of discharge with cure and improvement were 22.5% (36/160)and 66.2% (106/160),respectively,while 18 cases(11.3% )had adverse outcomes.Conclusions Pediatric PM is more common in children aged 3 months to under 3 years.Intracranial complications are more frequently observed in children under 1 year old.Fever is the most common clinical manifestation of PM,and subdural effusion/emphysema and hydrocephalus are the most frequent complications.Non-culture detection methods for cerebrospinal fluid can improve pathogen detection rates.Adverse outcomes can be noted in more than 10% of PM cases.SP strains are high sensitivity to vancomycin,linezolid,meropenem,levofloxacin,moxifloxacin,rifampicin,and chloramphenicol.[Chinese Journal of Contemporary Pediatrics,2024,26(2):131-138]