OBJECTIVE: To construct machine learning prediction model for sepsis-associated encephalopathy (SAE), and analyze the application value of the model on early identification of SAE risk in elderly septic patients. METHODS: Patients aged over 60 years with a primary diagnosis of sepsis admitted to intensive care unit (ICU) from 2008 to 2023 were selected from Medical Information Mart for Intensive Care-IV 2.2 (MIMIC-IV 2.2). Demographic variables, disease severity scores, comorbidities, interventions, laboratory indicators, and hospitalization details were collected. Key factors associated with SAE were identified using univariate Logistic regression analysis. The data were randomly divided into training and validation sets in a 7 : 3 ratio. Multivariable Logistic regression analysis was conducted in the training set and visualized using a nomogram model for prediction of SAE. The discrimination of the model was evaluated in the validation set using the receiver operator characteristic curve (ROC curve), and its calibration was assessed using calibration curve. Furthermore, multiple machine learning algorithms, including multi-layer perceptron (MLP), support vector machine (SVM), naive bayes (NB), gradient boosting machine (GBM), random forest (RF), and extreme gradient boosting (XGB), were constructed in the training set. Their predictive performance was subsequently evaluated on the validation set. Taking the XGB model as an example, the interpretability of the model through the SHapley Additive exPlanations (SHAP) algorithm was enhanced to identify the key predictive factors and their contributions. RESULTS: A total of 2 204 septic patients were finally enrolled, of whom 840 developed SAE (38.1%). A total of 21 variables associated with SAE were screened through univariate Logistic regression analysis. Multivariable Logistic regression analysis showed that endotracheal intubation [odds ratio (OR) = 0.40, 95% confidence interval (95%CI) was 0.19-0.88, P < 0.001], oxygen therapy (OR = 0.76, 95%CI was 0.53-0.95, P = 0.023), tracheotomy (OR = 0.20, 95%CI was 0.07-0.53, P < 0.001), continuous renal replacement therapy (CRRT; OR = 0.32, 95%CI was 0.15-0.70, P < 0.001), cerebrovascular disease (OR = 0.31, 95%CI was 0.16-0.60, P < 0.001), rheumatic disease (OR = 0.44, 95%CI was 0.19-0.99, P < 0.001), male (OR = 0.68, 95%CI was 0.54-0.86, P = 0.001), and maximum anion gap (AG; OR = 0.95, 95%CI was 0.93-0.97, P < 0.001) were associated with an decreased probability of SAE, and age (OR = 1.05, 95%CI was 1.03-1.06, P < 0.001), acute physiology score III (APSIII; OR = 1.02, 95%CI was 1.01-1.02, P < 0.001), Oxford acute severity of illness score (OASIS; OR = 1.04, 95%CI was 1.03-1.06, P < 0.001), and length of hospital stay (OR = 1.01, 95%CI was 1.01-1.02, P < 0.001) were associated with an increased probability of SAE. A nomogram model was constructed based on these variables. In the validation set, ROC curve analysis showed that the model achieved an area under the ROC curve (AUC) of 0.723, and the calibration curve showed good consistency between the predicted probability of the model and the observed probability. Among the machine learning algorithms, including MLP, SVM, NB, GBM, RF, and XGB, the SVM model and RF model demonstrated relatively good predictive performance, with AUC of 0.748 and 0.739, respectively, and the sensitivity was both exceeding 85%. The predictive performance of the XGB model was explained through SHAP analysis, and the results indicated that APSIII score (SHAP value was 0.871), age (SHAP value was 0.521), and OASIS score (SHAP value was 0.443) were important factors affecting the predictive performance of the model. CONCLUSIONS The machine learning-based SAE prediction model exhibits good predictive capability and holds significant application value for the early identification of SAE risk in elderly septic patients.
Humans ; Machine Learning ; Aged ; Sepsis-Associated Encephalopathy ; Sepsis/complications* ; Intensive Care Units ; Logistic Models ; Middle Aged ; Male ; ROC Curve ; Female ; Bayes Theorem ; Nomograms ; Support Vector Machine ; Algorithms

OBJECTIVES: This study aimed to investigate the incidence, imaging characteristics, and clinical manifestations of the eruption failure of deciduous molars using panoramic radiographs to provide a foundation for diagnosis and treatment in this population. METHODS: This study retrospectively reviewed panoramic radiographs of children aged 4-8 years obtained from Stomatology Hospital, Zhejiang University School of Medicine between January 2021 and December 2023. A total of 31 331 subjects were included for the radiographic assessment of the tooth eruption failure of deciduous molars. Incidence, radiographic characteristics, and associated complications were documented. Statistical analysis was performed using SPSS 26.0. RESULTS: The incidence of the eruption failure of deciduous molars among children aged 4-8 years was 0.94% (296/31 331). The rate was 1.55 times higher in females than in males, demonstrating a significant gender difference (P<0.001). Among the affected deciduous molars, mandibular first deciduous molars accounted for 76.4%, followed by the mandibular second deciduous molars (13.8%), and the maxillary deciduous molars collectively comprised 9.8%. The severity of eruption disorders was significantly associated with the mesial and distal tilting of adjacent teeth and elongation of the antagonist (P<0.001). CONCLUSIONS The incidence of the eruption failure of deciduous molars in children aged 4-8 years was 0.94%, with a high prevalence in females and a predilection for the mandible, particularly the mandibular first deciduous molar. For deciduous molars with severe eruption failure, early intervention is crucial to mitigate complications such as malocclusion and space loss.
Humans ; Child ; Child, Preschool ; Tooth, Deciduous/diagnostic imaging* ; Female ; Molar/physiopathology* ; Male ; Retrospective Studies ; Tooth Eruption ; Radiography, Panoramic ; Incidence

The cellular and molecular components of the tumor immune microenvironment (TIME) and their information exchange processes significantly influence the trends of anti-tumor immunity. In recent years, numerous studies have begun to evaluate TIME in the context of previous cancer treatment strategies. This review will systematically summarize the compositional characteristics of TIME and, based on this foundation, explore the impact of current cancer therapies on the remodeling of TIME, aiming to provide new insights for the development of innovative immune combination therapies that can convert TIME into an anti-tumor profile.
Tumor Microenvironment/immunology* ; Humans ; Neoplasms/therapy* ; Immunotherapy/methods* ; Animals

Objective To investigate the differential expression genes(DEGs)related to angiogenesis in rosacea(RA)by utilizing bioinformatics analysis in order to screen the key genes and verify their mRNA expression levels.Methods The gene microarray dataset GSE65914 was retrieved from the Gene Expression Omnibus(GEO)repository.Analyzed by R programming,the dataset was refined to identify DEGs related to RA,and then cross-referenced with angiogenesis-related genes from the GeneCards database to get a subset specific to RA angiogenesis.The process of identifying key genes was augmented by employing protein-protein interaction(PPI)network analysis and Cytoscape-based computational algorithms.The mRNA expression levels of the aforementioned pivotal genes were detected by real-time fluorescent quantitative reverse transcription PCR(RT-qPCR).Results A total of 947 RA-associated DEGs were identified from GEO dataset,and then 202 genes related to RA angiogenesis were further delineated.PPI network analysis and Cytoscape algorithm finally identified 3 key genes,that is,CXCL8,IL-1B,and STAT1.The results of RT-qPCR showed that the mRNA expression levels of MIP-2,GCP-2,IL-1B and STAT1 in RA lesions were significantly higher than those in normal controls(P<0.05).Conclusion With aid of bioinformatics analysis,our study has screened and validated key genes associated with angiogenesis in RA,namely CXCL8,IL-1B,and STAT1,which providing a theoretical basis for elucidating the potential mechanisms underlying RA-induced angiogenesis and developing targeted therapeutic strategies.

OBJECTIVE: To investigate the clinical characteristics and genetic etiology of eight members from a pedigree affected with epidermolysis bullosa (EB). METHODS: A girl presented with recurrent, unexplained blisters on the palmar and plantar skin for 8 years and sought medical care in October 2024 was enrolled as the study subject. A retrospective study was conducted to collect the child's clinical data, and a detailed medical history was taken for her family members. Peripheral venous blood samples were collected from the child and her parents for genomic DNA extraction. Whole-exome sequencing (WES) was performed. Candidate variant was validated by Sanger sequencing. The pathogenicity of the candidate variants was classified in accordance with the Standards and Guidelines for the Interpretation of Sequence Variants issued by the American College of Medical Genetics and Genomics (ACMG, hereinafter referred to as the "ACMG Guidelines"). This study was approved by the Medical Ethics Committee of the 980th Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army (Ethics No.: 2019-KY-01). RESULTS: The proband was an 8-year-and-4-month-old female. Four months after birth, she had developed recurrent blisters on the palmar and plantar skin without obvious triggers, accompanied by significant pain. Symptoms were more severe in summer and slightly relieved in winter. Although symptomatic treatment could alleviate the symptoms, she was unable to participate in physical activities. A detailed family history revealed that her great-grandfather, grandfather, father, half-brother, great-aunt, great-aunt's son and two grandsons, as well as her aunt and aunt's son, had similar clinical manifestations. WES revealed that she has harbored a heterozygous c.556-16(IVS1)C>G (NM_000424.4) variant in the KRT5 gene, which was identified as a splice site mutation. Reverse transcription sequencing confirmed that this variant can disrupt normal splicing, resulting in retention of a 15 bp sequence in the first intron. Sanger sequencing demonstrated that the variant was inherited from the father, and the 6 aforementioned relatives with similar phenotypes have all carried the same variant (the great-grandfather, grandfather, and great-aunt had declined genetic testing due to advanced age). Based on the ACMG guidelines, this variant was classified as pathogenic (PS3+PM2_Supporting+PP3+PP1_strong). CONCLUSION Patients with epidermolysis bullosa simplex may exhibit clinical features including blistering on the skin or mucous membranes of friction-prone sites (e.g. hands, feet, elbows, and knees) following minor trauma or friction, as well as increased skin fragility. The c.556-16(IVS1)C>G (rs376462752) variant of the KRT5 gene probably underlay the pathogenesis of EB in this child. Above findings have enriched the mutational spectrum of the KRT5 gene.
Child ; Female ; Humans ; Infant ; Male ; China ; Epidermolysis Bullosa Simplex/genetics* ; Exome Sequencing ; Keratin-5/genetics* ; Mutation ; Pedigree ; Retrospective Studies ; East Asian People/genetics*

Objective:To develop radiomics score (RS) based on 18F-FDG PET/CT, and construct the machine learning model combining clinical and other relevant factors for personalized prediction of 2-year event-free survival (2-EFS) in patients with diffuse large B-cell lymphoma (DLBCL), and to perform interpretability analysis of the model. Methods:A total of 91 patients (49 males, 42 females; age (57.8±12.8) years) with pathologically confirmed DLBCL from December 2017 to December 2020 at the First Hospital of Shanxi Medical University were retrospectively analyzed. According to the ratio of 7∶3, patients were randomly divided into training set ( n=63) and test set ( n=28), and divided into non-progression group and progression group according to the follow-up results. The whole-body PET semi-quantitative parameters were calculated from the PET/CT images before treatment, and 328 radiomics features were extracted from the largest target lesions of patients. The least absolute shrinkage and selection operator (LASSO) was used to develop the RS. Clinical and PET characteristic difference analysis was performed through χ2 test and Mann-Whitney U test. Extreme gradient boosting (XGBoost) models were constructed based on clinical, PET radiomics features and RS, and the prediction efficiency of each model was evaluated by ROC AUC. The model interpretability was analyzed by using shapely additive explanation (SHAP). Results:Of all patients, 32 had disease progression and 59 did not. There were no significant differences in baseline characteristics between the training set and the test set ( χ2 values: 0.06-1.84, U values: 665.00-763.00, all P>0.05). The comparison between the progression group and non-progression group in the training set showed statistical differences in the international prognostic index (IPI) score ( χ2=4.87, P=0.027), myelocytomatosis viral oncogene (MYC) protein expression ( χ2=4.29, P=0.038), and metabolic tumor volume (MTV; U=307.00, P=0.038). Seven radiomics features were screened by LASSO. Among XGBoost models with different feature combinations, IPI score, MYC protein expression, MTV combined with RS had the highest predictive efficiency (training set: AUC=0.73; test set: AUC=0.70). Through SHAP analysis, RS was the most predictive feature in the optimal model. Conclusion:The machine learning integrated model of IPI score, MYC protein expression and MTV combined with RS can effectively predict the prognosis of DLBCL patients, and baseline 18F-FDG PET/CT radiomics can be used as a potential means to evaluate the prognosis of DLBCL patients.

Objective:To investigate the clinical value of 18F-NaF PET/CT coronary plague imaging in evaluating the long-term prognosis of patients with coronary artery disease (CAD). Methods:A retrospective cohort study was conducted among 54 patients (37 males and 17 females, aged (57.2±9.8) years) diagnosed with CAD from a multicenter study between September 2015 and October 2022. All patients underwent 18F-NaF PET/CT and coronary angiography (CAG) within 1 week, and the PET/CT imaging was performed at the First Hospital of Shanxi Medical University. Major adverse cardiovascular events (MACE) were followed up. ROC curves were established to obtain the optimal thresholds of SUV max and accumulated SUV max of all lesions of main coronary artery branches (S-SUV max) for predicting MACE. Cox proportional risk model and Kaplan-Meier method (log-rank test) were used to analyze the predictive value of PET parameters for MACE. Differences in metabolic parameters between 2 groups were compared by Mann-Whitney U test. Results:The median follow-up time of the 54 patients was 6.0(1.8, 6.6) years, and 13(24.1%) patients developed MACE, including 7 deaths, 5 myocardial infarction and 1 severe arrhythmia. S-SUV max in MACE group was significantly higher than that in the non-MACE group (2.64(2.08, 4.49) vs 1.83(0.95, 2.90); Z=-2.04, P=0.041). ROC curve showed that the optimal threshold of S-SUV max for MACE prediction was 2.05 (AUC=0.690). Multivariate Cox analysis showed that S-SUV max was a strong predictor of MACE (hazard ratio ( HR)=2.434(95% CI: 1.547-3.828), P<0.001). ROC curve showed that the optimal threshold of SUV max to predict MACE was 0.55 (AUC=0.659), and univariate Cox analysis showed that SUV max was a factor to predict MACE ( HR=10.192 (95% CI: 2.667-38.953), P=0.001). In 25 patients with incomplete revascularization (ICR), Kaplan-Meier analysis showed that the incidence of MACE in patients with positive 18F-NaF uptake (single medium stenosis (40%-70%) with SUV max≥0.55) was significantly higher than that in patients with negative 18F-NaF uptake (5/14 vs 0/11; χ2=6.07, P=0.014). Conclusions:18F-NaF PET/CT can be used as an independent predictor of MACE in patients with CAD and can quantitatively assess the long-term progression of moderate coronary artery stenosis. In the future, it is expected to be a new non-invasive way to guide the revascularization treatment decision of multi-vessel CAD.

In recent years, immunotherapy has become another important treatment for non-small cell lung cancer (NSCLC) after surgery, radiotherapy, chemotherapy and targeted therapy. As an emerging non-invasive tool, PET/CT radiomics provides a new way for precise diagnosis and treatment of NSCLC by quantitatively analyzing the metabolic and structural characteristics of tumors, demonstrating significant promise for applications in NSCLC immunotherapy. This article aims to review the research progress of PET/CT radiomics in NSCLC immunotherapy and to explore its potential value in predicting biomarkers, therapeutic efficacy, adverse effects, and evaluating prognosis.

Objective:To investigate the effects of acute sleep deprivation (ASD) on hippocampal glucose metabolism and neuroinflammation in rat models.Methods:Twenty SD rats (10 males and 10 females) were divided into four groups (five in each group) by random sampling method: female ASD group, male ASD group, female control group, and male control group. Among them, the ASD group constructed the ASD model. After 72h sleep deprivation, all rats underwent 18F-FDG and N, N-diethyl-2-(2-(4-(2- 18F-fluoroethoxy)phenyl)-5, 7-dimethylpyrazolo[1, 5-a]pyrimidin-3-yl)acetamide ( 18F-DPA-714) microPET/CT brain imaging in 2d to compare the changes of 18F-FDG and 18F-DPA-714 SUV mean in the hippocampus of rats. Brain histopathology, immunohistochemistry and immunofluorescence staining were detected in rats. Independent-sample t test was used to analyze the data. Results:18F-FDG imaging showed the hippocampal SUV mean between ASD group and control group (female: 4.11±0.35 vs 1.89±0.28; male: 3.43±0.47 vs 2.02±0.54) were statistically significant ( t values: 9.65, 3.92, P values: <0.001, 0.002). 18F-DPA-714 imaging showed the hippocampal SUV mean between ASD group and control group (females: 0.28±0.01 vs 0.28±0.02; male: 0.26±0.02 vs 0.31±0.04) were not statistically significant ( t values: -0.18, -2.24, P values: 0.859, 0.056). The 18×10 3 translocator protein (TSPO) immunohistochemistry showed the expression in the hippocampal region of the brain between ASD group and control group (female: 0.19±0.02 vs 0.19±0.01; male: 0.21±0.01 vs 0.20±0.01) were not statistically different ( t values: -0.48, -1.67, P values: 0.651, 0.139). Immunofluorescence staining showed that microglial cytosol in the hippocampal region of the brain decreased after 72h of ASD, and the protrusion points and surrounding branches were significantly reduced. Conclusion:Increased hippocampal glucose metabolism in rats is observed after 72 h of ASD without significant neuroinflammation.

OBJECTIVE To observe intervention effect of salvianolic acid B based on JAK2/STAT3 pathways on the rats with Escherichia coli infection-induced pyelonephritis.METHODS Totally 60 SPF grade male SD rats were in-cluded in the study and were randomly divided into the control group with 21 rats,the model group(Escherichia coli infection-induced pyelonephritis)with 18 rats and the salvianolic acid B group(Escherichia coli infection-in-duced pyelonephritis+salvianolic acid B)with 18 rats.The control group and the model group were treated with same volume of normal saline for gavage,the salvianolic acid B group was given 12.5 mg/kg salvianolic acid B wa-ter solution for gavage.The levels of related biochemical indexes[secretory immunoglobulin A(SlgA),urine cre-atinine and serum creatinine]were detected for the groups.The organ indexes and relative expression levels of JAK2/STAT3 signaling pathways were observed and compared among the groups.RESULTS There were significant differences in the levels of blood indexes among the three groups of rats(P＜0.05).The SlgA level of the model group was(13.51±1.18)μg/ml,lower than(25.64±4.51)μg/ml of the control group(P＜0.05);the SlgA level of the salvian-olic acid B group was(25.34±2.95)μg/ml,higher than that of the model group(P＜0.05).There were no significant differences in the bladder indexes among the three groups;the ratio of left kidney to right kidney and the renal indexes were higher in the model group than in the control group(P＜0.05);the ratio of left kidney to right kidney and the renal indexes were lower in the salvianolic acid B group than in the model group(P＜0.05).There were significant differences in the relative expression levels of JAK2/STAT 3 signaling pathways among the three groups(P＜0.05);the levels of JAK2 and STAT 3 of the model group were higher than those of the control group(P＜0.05);the levels of JAK2 and STAT 3 of the salvianolic acid B group were lower than those of the model group(P＜0.05).CONCLUSION The salvian-olic acid B based on JAK2/STAT3 pathways may improve the indexes of the rats with E.coli infection-induced pyelonephritis and effectively improve the overall symptoms.