BACKGROUND: Over 20 million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style. METHODS: We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients' records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five main labels and 22 sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases. RESULTS: The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1 score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals. CONCLUSIONS The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.
Humans ; Colonoscopy/methods* ; Deep Learning ; Decision Support Systems, Clinical ; Female ; Male

In the clinical stage, suspected hemolytic plasma may cause hemolysis illness, manifesting as symptoms such as heart failure, severe anemia, etc. Applying a deep learning method to plasma images significantly improves recognition accuracy, so that this paper proposes a plasma quality detection model based on improved "You Only Look Once" 5th version (YOLOv5). Then the model presented in this paper and the evaluation system ‌were introduced‌ into the plasma datasets, and ‌the average accuracy of the final classification reached 98.7%‌. The results of this paper's experiment were obtained through the combination of several key algorithm modules including‌ omni-dimensional dynamic convolution, pooling with separable kernel attention, residual bi-fusion feature pyramid network, ‌and‌ re-parameterization convolution. The method of this paper‌ obtains the feature information of spatial mapping efficiently, and enhances the average recognition accuracy of plasma quality detection. This paper presents a high-efficiency detection method for plasma images, aiming to provide a practical approach to prevent hemolysis illnesses caused by external factors.
Algorithms ; Humans ; Hemolysis ; Plasma ; Deep Learning ; Image Processing, Computer-Assisted/methods*

Objective To construct a prognostic risk model for exploring the prognostic value of copper metabolism related genes(CMRGs)in lung adenocarcinoma(LUAD),thereby providing a reference for personalized treatment of LUAD patients.Methods The RNA-seq data of LUAD tissues and adjacent or normal lung tissues were downloaded from the Cancer Genome Atlas(TCGA)database and Genotype-tissue Expression(GTEx)database.The risk scoring model was established using univariate Cox regression analysis,Lasso analysis and multivariate Cox regression analysis,and the receiver operating characteristic(ROC)curves and nomogram were used to evaluate the model performance.The LUAD data in the Gene Expression Omnibus(GEO),the Tumor Immune Single-cell Hub(TISCH)single-cell sequencing analysis,and the Human Protein Atlas(HPA)immunohistochemistry analysis were used for external validation.Additionally,the immune microenvironment and drug sensitivity of high-and low-risk groups were analyzed.Results A risk model consisting of 6 genes was constructed.The overall survival rate of low-risk group was higher than that of high-risk group(P<0.001).ROC analysis showed that the area under curve of the risk model in training set reached 0.729,0.749 and 0.707 at 1-,3-and 5-year,respectively,and the C index of C-index curve was 0.721(95%CI:0.678-0.764).The immune microenvironment differed significantly between high-and low-risk groups(P<0.001),and the drug sensitivity analysis in high-and low-risk groups revealed that there was statistically significant for gemcitabine,gefitinib,crizotinib and savolitinib(P<0.001).Conclusion The risk model constructed with 6 CMRGs enable the prediction of the prognosis of LUAD patients.The immune microenvironment differs in high-and low-risk group,and high-risk patients are more sensitive to drugs such as gemcitabine,gefitinib,crizotinib and savolitinib,which provide a reference for the personalized treatment of LUAD patients.

BACKGROUND: Lung cancer is one of the most common malignant tumors in the world, and the current lung cancer screening and treatment strategies are constantly improving, but its 5-year survival rate is still very low, which seriously endangers human health. Therefore, it is critical to explore new biomarkers to provide personalized treatment and improve the prognosis. Cuproptosis is a newly discovered type of cell death, which is due to the accumulation of excess copper ions in the cell, eventually leading to cell death, which has been suggested by studies to be closely related to the occurrence and development of lung adenocarcinoma (LUAD). Based on The Cancer Genome Atlas (TCGA) database, this study explored the association between cuproptosis-related genes (CRGs) and LUAD prognosis, established a prognostic risk model, and analyzed the interaction between CRGs and LUAD immune cell infiltration. METHODS: The RNA-seq data of LUAD tissue and paracancerous or normal lung tissue were downloaded from the TCGA database; the RNA-seq data of normal lung tissue was downloaded from the Genotype-tissue Expression (GTEx) database, and the data of 462 lung adenocarcinoma cases were downloaded from the Gene Expression Omnibus repository (GEO) as verification. T the risk score model to assess prognosis was constructed by univariate Cox and Lasso-Cox regression analysis, and the predictive ability of the model was evaluated by receiver operating characteristic (ROC) curve and calibration curve. Immune-related and drug susceptibility analysis was further performed on high- and low-risk groups. RESULTS: A total of 1656 CRGs and 1356 differentially expressed CRGs were obtained, and 13 CRGs were screened out based on univariate Cox and Lasso-Cox regression analysis to construct a prognostic risk model, and the area under the curves (AUCs) of ROC curves 1-, 3- and 5- year were 0.749, 0.740 and 0.689, respectively. Further study of immune-related functions and immune checkpoint differential analysis between high- and low-risk groups was done. High-risk groups were more sensitive to drugs such as Savolitinib, Palbociclib, and Cytarabine and were more likely to benefit from immunotherapy. CONCLUSIONS The risk model constructed based on 13 CRGs has good prognostic value, which can assist LUAD patients in individualized treatment, and provides an important theoretical basis for the treatment and prognosis of LUAD.
Humans ; Adenocarcinoma/genetics* ; Adenocarcinoma of Lung/genetics* ; Early Detection of Cancer ; Lung Neoplasms/genetics* ; Prognosis ; Copper ; Apoptosis

Objective:To evaluate the recurrence and progression of patients with pT1 high grade urothelial carcinoma of bladder (UCB) and glandular differentiation.Methods:We retrospectively analyzed the clinical and pathological information of 208 patients diagnosed as pT1 high grade urothelial carcinoma in the Fifth Central Hospital of Tianjin from January 2006 to February 2019.Among them, 78 cases were diagnosed as glandular differentiation (UCGD), the other 130 patients without histologic variants were served as control. The UCGD group included 62 male and 16 female, whose median age was 67 years old (range 38-81 years old). The control group contained 105 male and 25 female, whose median age was 66 years old (range 40-82 years old). Kaplan-Meier and Cox proportional hazard regression analyses were used to evaluate the predictors of oncologic outcomes.Results:The disease recurrence rate and progression rate in UCGD group were 65.4% (51/78) and 28.2% (22/78), higher than 38.5%(50/130) and 14.6%(19/130) of control group ( P<0.05). The median recurrence time in UCGD group was 41 months while 55 months in the control group. The median progression time in UCGD group was 39 months while 54 months in the control group. According to the univariate analysis, largest tumor size ( P=0.030), UCGD ( P=0.003) and lymphovascular invasion (LVI) ( P=0.032) were associated with disease recurrence. UCGD ( P=0.036) and LVI ( P=0.011) were associated with progression. Additionally, Cox multivariate analysis revealed that UCGD ( P=0.001), LVI ( P=0.038) were the independent factors of disease recurrence. UCGD ( P=0.007) and LVI ( P=0.037) were also found to be the independent factors of disease progression. Conclusions:Patients with T1 stage UCB and UCGD are at higher risk of disease recurrence and progression. Therefore, these patients should be followed up closely after being diagnosed and undergo individual treatment according to the situation.

Objective:To evaluate the recurrence and progression of patients with pT1 high grade urothelial carcinoma of bladder (UCB) and glandular differentiation.Methods:We retrospectively analyzed the clinical and pathological information of 208 patients diagnosed as pT1 high grade urothelial carcinoma in the Fifth Central Hospital of Tianjin from January 2006 to February 2019.Among them, 78 cases were diagnosed as glandular differentiation (UCGD), the other 130 patients without histologic variants were served as control. The UCGD group included 62 male and 16 female, whose median age was 67 years old (range 38-81 years old). The control group contained 105 male and 25 female, whose median age was 66 years old (range 40-82 years old). Kaplan-Meier and Cox proportional hazard regression analyses were used to evaluate the predictors of oncologic outcomes.Results:The disease recurrence rate and progression rate in UCGD group were 65.4% (51/78) and 28.2% (22/78), higher than 38.5%(50/130) and 14.6%(19/130) of control group ( P<0.05). The median recurrence time in UCGD group was 41 months while 55 months in the control group. The median progression time in UCGD group was 39 months while 54 months in the control group. According to the univariate analysis, largest tumor size ( P=0.030), UCGD ( P=0.003) and lymphovascular invasion (LVI) ( P=0.032) were associated with disease recurrence. UCGD ( P=0.036) and LVI ( P=0.011) were associated with progression. Additionally, Cox multivariate analysis revealed that UCGD ( P=0.001), LVI ( P=0.038) were the independent factors of disease recurrence. UCGD ( P=0.007) and LVI ( P=0.037) were also found to be the independent factors of disease progression. Conclusions:Patients with T1 stage UCB and UCGD are at higher risk of disease recurrence and progression. Therefore, these patients should be followed up closely after being diagnosed and undergo individual treatment according to the situation.

Objective To investigate the effect and mechanism of interleukin (IL)-17C in mice undergoing kidney transplantation. Methods The life-supporting kidney transplantation mice models were established using Balb/c (H-2K^d) mice as the donors, IL-17C gene knock out (IL-17CKO) mice (knockout group) and C57BL/6J(H-2K^b) mice (wild group) were chosen as the recipients. The postoperative body mass and survival time of mice were statistically compared between two groups. Pathological examination of the kidney graft was performed by using hematoxylin-eosin (HE) staining and periodic acid-Schiff (PAS) staining. The expression levels of granzyme B, interferon (IFN)-γ, tumor necrosis factor (TNF)-α, IL-6 and IL-1β messenger ribonucleic acid (mRNA) in the kidney graft tissue were quantitatively measured by reverse transcription polymerase chain reaction (RT-PCR). The proportion of inflammatory cell infiltration in the kidney graft tissue was detected by flow cytometry. Results In the knockout group, the survival time of mice after kidney transplantation was significantly shorter than that of the wild mice (P=0.031). The body mass was more evidently decreased in the knockout group with no statistical significance from that in the wild group. Pathological examination demonstrated that the kidney graft injury in the knockout group was significantly worse than that in the wild group. The mRNA expression levels of granzyme B, IFN-γ, TNF-α, IL-6 mRNA in the knockout group were significantly up-regulated compared with those in the wild group (all P < 0.01). The mRNA expression level of IL-1β showed a decreasing trend with no statistical significance (P=0.16). Flow cytometry analysis revealed that the infiltration of CD45⁺CD11b⁺Ly6G⁺ neutrophil and CD45⁺CD11b⁺Ly6C^hi monocyte in the kidney graft of knockout mice was significantly higher compared with that of the wild mice (P < 0.05, P < 0.01), whereas the infiltration of CD45⁺Ly6C^hiF4/80⁺ macrophage did not significantly differ between two groups (P > 0.05). Conclusions IL-17C participates in the regulation of inflammatory response after kidney transplantation. It can alleviate acute rejection and improve the survival of kidney graft by down-regulating the expression of pro-inflammatory cytokines and infiltration of inflammatory cells.

Objective To study the effect of T-2 toxin on proliferation and cell cycle of rat chondrocytes,in order to provide a new idea in molecular mechanism of T-2 toxin-induced chondrocyte damage.Methods Primary chondrocytes of neonatal Wistar rats were isolated and stained by toluidine blue staining and type Ⅱ collagen immunofluorescence staining.The effects of different concentrations of T-2 toxin [0 (control),1,5,10,20,50,100 μg/L)] on proliferation of chondrocytes for 24 h were detected by cell counting kit-8 (CCK-8) method,and control,1 (low dose),5 (medium dose),and 10 μg/L (high dose) T-2 toxin were selected for subsequent experiment;cell cycle changes were detected by flow cytometry;Real-time PCR and Western blotting were used to detect the effects of T-2 toxin on mRNA and protein expressions of proliferating cell nuclear antigen (PCNA) and Cyclin D1 in chondrocytes.Results With increase of T-2 toxin concentration (control,1,5,10,20,50,100 μg/L),the cell survival rates [(100.00 ± 0.00)％,(93.12 ± 1.66)％,(77.12 ± 1.11)％,(59.44 ± 4.09)％,(46.64 ± 3.86)％,(38.15 ± 3.37)％,(33.79 ± 0.99)％] were decreased,and the differences were statistically significant (F =139.21,P ＜0.05).The percentages of quiescent phase/pre-DNA synthesis phase (G0/G1 phase) ceils in 1,5,10 μg/L T-2 toxin groups [(22.03 ± 0.42)％,(30.54 ± 2.61)％,(36.01 ± 1.51)％] were significantly higher than that in control group [(13.79 ± 1.65)％,P ＜ 0.05];the percentages of DNA synthesis phase (S phase) cells [(60.27 ± 3.53)％,(53.88 ±4.38)％,(49.55 ± 2.49)％] were significantly lower than that in control group [(76.72 ± 4.24)％,P ＜ 0.05].The differences of mRNA levels of PCNA and Cyclin D1 between groups were statistically significant (F =46.80,17.97,P ＜ 0.05),and 5,10 μg/L T-2 toxin groups (0.77 ± 0.13,0.79 ± 0.08,0.60 ± 0.07,0.56 ± 0.05) were lower than the control group (0.99 ± 0.02,1.01 ± 0.01,P ＜ 0.05).The expressions of PCNA protein in 5,10 μg/L T-2 toxin groups (0.69 ± 0.03,0.49 ± 0.03) were lower than that in control group (0.92 ± 0.05,P ＜ 0.05);the expressions of Cyclin D1 protein in 1,5,10 μg/L T-2 toxin groups (0.80 ± 0.06,0.60 ± 0.07,0.33 ± 0.13) were lower than that in control group (0.95 ± 0.07,P ＜ 0.05).Conclusion T-2 toxin can inhibit the proliferation of chondrocytes,which may be worked through influencing the expression of cell cycle protein,causing cell cycle arrest,thereby inhibiting DNA synthesis.

Objective To investigate the effect of fluoride exposure on expression of miRNA (miR)-200c and its target in human osteoblast Saos-2 cells.Methods Saos-2 cells were cultured in DMEM/F-12 medium and treated with fluoride (sodium fluoride,NaF).There were two groups including:control group (0 mg/L) and fluoride group (4 mg/L).Cells were harvested after 48 hours of culture with fluoride.The expression of miR-200c,the mRNA of alkaline phosphatase (ALP),osteocalcin (BGP),the target phosphatase and tensin homolog deleted on chromosome ten (PTEN) and dual-specific phosphatase 1 (DUSP1) of miR-200c was detected by qRT-PCR.The protein expression of PTEN and DUSP1 was detected by Western blotting.Results The expressions of ALP,BGP mRNA and miR-200c in Saos-2 cells in the fluoride group (23.60 ± 1.87,9.41 ± 0.94,8.61 ± 0.26) were higher than those in the control group (1.00 ± 0.11,1.00 ± 0.07,1.00 ± 0.12).The differences were statistically significant (t =-24.084,-18.388,-8.687,P ＜ 0.05).The mRNA expressions of PTEN and DUSP1 in the fluoride group (0.63 ± 0.02,0.38 ± 0.02) were lower than those in the control group (1.02 ± 0.24,1.02 ± 0.24).The differences were statistically significant (t =3.327,5.454,P ＜ 0.05).The protein expressions of PTEN and DUSP1 in Saos-2 cells in the fluoride group (1.19 ± 0.10,0.83 ± 0.07) were lower than those in the control group (1.81 ± 0.14,1.44 ± 0.25).The differences were statistically significant (t =6.250,4.171,P ＜ 0.05).Conclusion Exposure to fluorine may increase the expression of miR-200c in Saos-2 cells,and fluorine may act on PTEN and DUSP1 through miR-200c,downregulates the mRNA and protein expression levels of PTEN and DUSP1.

OBJECTIVETo observe the effect of different doses of acetamide on the histopathology in the cerebral cortex of rats with tetramine (TET) poisoning and to provide a basis for the treatment of fluoroacetamide poisoning with acetamide.

METHODSEighty clean Sprague-Dawley rats were randomly divided into five groups: saline control group,dimethylsulfoxide water solution control group,TET poisoning group, acetamide (2.88 g/kg/d) treatment group, and acetamide (5.68 g/kg/d) treatment group, with 16 rats in each group. Rats in the poisoning group and treatment groups were poisoned with TET by intragastric administration after fasting; then, saline was injected intramuscularly into rats of the poisoning group, and different doses of acetamide were injected intramuscularly into rats of treatment groups; the course of treatment was 5 d. At 3 h, 12 h, 48 h, and 7 d after treatment, the cerebral cortex was harvested from rats in each group, and the histopathological changes in the cerebral cortex were evaluated under light and electron microscopes.

RESULTSThe light microscopy showed that the TET poisoning group had hypoxia changes in the cerebral cortex, which worsened over time; the treatment groups had reduced hypoxia changes, and the acetamide (2.88 g/kg/d) treatment group had more reduction than the acetamide (5.68 g/kg/d) treatment group. The electron microscopy showed that the apoptosis of neuronal cells were the main pathological changes in the TET poisoning group; the treatment groups had reduced apoptotic changes, and the acetamide (2.88 g/kg/d) treatment group had more reduction than the acetamide (5.68 g/kg/d) treatment group.

CONCLUSIONNo pathological changes associated with the synergistic toxic effect of acetamide and TET are found in the cerebral cortex. Acetamide (2.88 g/kg/d) could reduce central nervous lesions, but the efficacy is not improved after increasing the dose. For patients who cannot be identified with TET or fluoroacetamide poisoning, acetamide could be considered for treatment.

Acetamides ; pharmacology ; Animals ; Bridged-Ring Compounds ; toxicity ; Cerebral Cortex ; drug effects ; pathology ; Disease Models, Animal ; Male ; Rats ; Rats, Sprague-Dawley