Objective:To establish a set of artificial intelligence (AI) verification rules for blood routine analysis.Methods:Blood routine analysis data of 18 474 hospitalized patients from the First Hospital of Jilin University during August 1st to 31st, 2019, were collected as training group for establishment of the AI verification rules,and the corresponding patient age, microscopic examination results, and clinical diagnosis information were collected. 92 laboratory parameters, including blood analysis report parameters, research parameters and alarm information, were used as candidate conditions for AI audit rules; manual verification combining microscopy was considered as standard, marked whether it was passed or blocked. Using decision tree algorithm, AI audit rules are initially established through high-intensity, multi-round and five-fold cross-validation and AI verification rules were optimized by setting important mandatory cases. The performance of AI verification rules was evaluated by comparing the false negative rate, precision rate, recall rate, F1 score, and pass rate with that of the current autoverification rules using Chi-square test. Another cohort of blood routine analysis data of 12 475 hospitalized patients in the First Hospital of Jilin University during November 1sr to 31st, 2023, were collected as validation group for validation of AI verification rules, which underwent simulated verification via the preliminary AI rules, thus performance of AI rules were analyzed by the above indicators. Results:AI verification rules consist of 15 rules and 17 parameters and do distinguish numeric and morphological abnormalities. Compared with auto-verification rules, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score of AI rules in training group were 22.7%, 1.6%, 74.5%, 1.3%, 75.7%, 97.2%, 93.5%, 94.7%, 94.1, respectively.All of them were better than auto-verification rules, and the difference was statistically significant ( P<0.001), and with no important case missed. In validation group, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score were 19.2%, 8.2%, 70.1%, 2.5%, 72.6%, 89.2%, 70.0%, 88.3%, 78.1, respectively, Compared with the auto-verification rules, The false negative rate was lower, the false positive rate and the recall rate were slightly higher, and the difference was statistically significant ( P<0.001). Conclusion:A set of the AI verification rules are established and verified by using decision tree algorithm of machine learning, which can identify, intercept and prompt abnormal results stably, and is moresimple, highly efficient and more accurate in the report of blood analysis test results compared with auto-vefication.

The discussion on the connotation of children’s subjectivity is not only a response to the lack of children’s subjectivity at the current stage of health management, but also a reference for children’s medical science popularization. Based on the perspective of social critical theory, this study used empirical research methods to review the "Dream Medical College" project of Children’s Hospital of Fudan University. The current situation and influencing factors of health management experience of 1 520 children participating in the "Dream Medical College" project were analyzed. The study showed that 96.35% of 1 316 subjects had diagnosis and treatment experience in specialized hospitals, and the overall negative emotional performance was at a low level (0~12 points). There was significant correlation between diagnosis and treatment, invasive experience and children’s emotional performance (P<0.05). The study revealed that the diagnosis and treatment field is the main practice place of children’s health management, while the subjective of children with different diagnosis and experience perform significantly different. Children over 4 years old have better language anxiety than physical anxiety when receiving diagnosis and treatment. Although medical science popularization is an important practical form of children’s health management, it lacks the science popularization content of invasive diagnosis and treatment and emotional management, and creative popular science form is more suitable for children with long-term and frequent diagnosis and treatment experience.

Objective:To evaluate the clinical efficacy and safety of neuro-endoscopic evacuation and microsurgery via keyhole approach in early spontaneous supertentorial intracerebral hemorrhage (ICH). Methods:A prospective multi-center randomized controlled trial was performed; 114 patients with spontaneous supertentorial ICH (time from onset to surgery<6 h) admitted to Departments of Neurosurgery, Shunde Hospital of Southern Medical University, Jiangmen Central Hospital, Affiliated Hospital of School of Medicine of Yanbian University from January 2019 to December 2021 and met the surgical indications were selected. They were divided into endoscopic group (evacuation of intracerebral hematoma under neuroendoscope, n=71) and microscopic group (microsurgery of intracerebral hematoma via keyhole approach, n=43) according to different surgical methods. After 1:1 propensity score matching of the general data, surgical time, hematoma clearance rate, early postoperative re-bleeding rate, Glasgow coma scale (GCS) scores 7 d after surgery, activity of daily living (ADL) scores 6 months after surgery, mortality, and surgery-related complications of 66 patients (33 from each group after matching) were compared. Results:The difference of surgical time between endoscopic group and microscopic group was statistically significant (125[102, 157] mins vs. 175[125, 260] mins, P<0.05). However, hematoma clearance rate (93.00%[80.88%, 96.52%] vs. 93.31%[88.15%, 96.03%]), early postoperative re-bleeding rate (15.2% vs. 9.1%), GCS scores 7 d after surgery (13[10, 15] vs. 12[8, 14]), ADL scores 6 months after surgery (65[45, 85] vs. 55[0, 85]), mortality rate (18.2% vs. 21.2%) and incidences of postoperative intracranial infection and acquired pulmonary infection were not statistically significant between the two groups ( P>0.05). Conclusion:Comparing with microsurgery via keyhole approach, neuro-endoscopy could shorten the surgical time, but not improve the prognosis or safety in early spontaneous supertentorial ICH patients.

The discussion on the connotation of children’s subjectivity is not only a response to the lack of children’s subjectivity at the current stage of health management, but also a reference for children’s medical science popularization. Based on the perspective of social critical theory, this study used empirical research methods to review the "Dream Medical College" project of Children’s Hospital of Fudan University. The current situation and influencing factors of health management experience of 1 520 children participating in the "Dream Medical College" project were analyzed. The study showed that 96.35% of 1 316 subjects had diagnosis and treatment experience in specialized hospitals, and the overall negative emotional performance was at a low level (0~12 points). There was significant correlation between diagnosis and treatment, invasive experience and children’s emotional performance (P<0.05). The study revealed that the diagnosis and treatment field is the main practice place of children’s health management, while the subjective of children with different diagnosis and experience perform significantly different. Children over 4 years old have better language anxiety than physical anxiety when receiving diagnosis and treatment. Although medical science popularization is an important practical form of children’s health management, it lacks the science popularization content of invasive diagnosis and treatment and emotional management, and creative popular science form is more suitable for children with long-term and frequent diagnosis and treatment experience.

Objective:To analyze the characteristics of viral isolation and unique recombinant from untreated HIV-1 patients infected through sexual transmission and injection drug use, so as to provide evidence for understanding the biological characteristics and precise prevention and control of HIV-1 infection in different transmission routes.Methods:In view of the different HIV-1 transmission risks, newly diagnosed untreated HIV-1 patients from Beijing, Guangxi and Sichuan were carefully selected. Venous blood was collected to detect the viral load and CD4 + T cell count, and peripheral blood lymphocytes were isolated for virus isolation. Viral RNAs were extracted from the virus supernatant, and the near full-length genome sequences were obtained using in-house method, then the recombination patterns were determined. Results:Among the 65 HIV-1 infection, 32(49.2%), 20(30.8%) and 13(20.0%) were infected via men who have sex with men (MSM), heterosexual and injection drug use (IDU), respectively; genotypes mainly included 26(40.0%) CRF07_ BC, 23(35.4%) CRF01_ AE, and 9(13.8%) unique recombinant types (URFs). A total of 46 HIV-1 clinical strains were isolated. The positive rate of HIV-1 isolation was significantly negatively correlated with CD4 + T cells ( X2=4.22, P=0.04), but positively correlated with viral load ( X2=22.4, P<0.001); the multi-variate generalized estimating equations(GEE) model analysis of HIV-1 P24 antigen content showed similar result. In addition, GEE model showed a positive correlation between viral P24 antigen content and virus-producing culture time (52.14, 95% CI: 9.42~94.87, P=0.017). Viral growth curve analysis showed that the level of viral P24 antigen in MSM Group was significantly higher than that in heterosexual group and IDU group (adjusted P values were p<0.01 and P<0.05, respectively), on the 14th day after culture. The proportion of URFs in MSM Group was higher than that in heterosexual group, and the recombinant breakpoints in MSM Group were more than that in heterosexual group. Conclusions:MSM population was more sensitive to HIV-1 virus isolation; there was unique diversity of recombinant forms of HIV-1 among those with sexually transmitted infections, especially in the MSM population.

Quality of medical records is key to hospital′s total quality management, while the establishment and improvement of real-time monitoring feedback system is of great significance to the improvement of the quality of medical records. The authors explored real-time quality control of electronic medical records through artificial intelligence data processing and machine learning. The quality control covers timeliness and completeness in writing the medical records, the consistency and logic of the content, the identification of typos and the quality control of the medical records etc. Its practice showed that the defect rate of medical records has decreased significantly and the quality control management efficiency has greatly improved.

Coronavirus disease 2019 (COVID-19) has spread rapidly around the world. In order to diagnose COVID-19 more quickly, in this paper, a depthwise separable DenseNet was proposed. The paper constructed a deep learning model with 2 905 chest X-ray images as experimental dataset. In order to enhance the contrast, the contrast limited adaptive histogram equalization (CLAHE) algorithm was used to preprocess the X-ray image before network training, then the images were put into the training network and the parameters of the network were adjusted to the optimal. Meanwhile, Leaky ReLU was selected as the activation function. VGG16, ResNet18, ResNet34, DenseNet121 and SDenseNet models were used to compare with the model proposed in this paper. Compared with ResNet34, the proposed classification model of pneumonia had improved 2.0%, 2.3% and 1.5% in accuracy, sensitivity and specificity respectively. Compared with the SDenseNet network without depthwise separable convolution, number of parameters of the proposed model was reduced by 43.9%, but the classification effect did not decrease. It can be found that the proposed DWSDenseNet has a good classification effect on the COVID-19 chest X-ray images dataset. Under the condition of ensuring the accuracy as much as possible, the depthwise separable convolution can effectively reduce number of parameters of the model.
Betacoronavirus ; Coronavirus Infections ; diagnostic imaging ; Deep Learning ; Humans ; Pandemics ; Pneumonia, Viral ; diagnostic imaging ; X-Rays

Diffuse intrinsic pontine glioma (DIPG) is the main cause of brain tumor-related death among children. Until now, there is still a lack of effective therapy with prolonged overall survival for this disease. A typical strategy for preclinical cancer research is to find out the molecular differences between tumor tissue and para-tumor normal tissue, in order to identify potential therapeutic targets. Unfortunately, it is impossible to obtain normal tissue for DIPG because of the vital functions of the pons. Here we report the human fetal hindbrain-derived neural progenitor cells (pontine progenitor cells, PPCs) as normal control cells for DIPG. The PPCs not only harbored similar cell biological and molecular signatures as DIPG glioma stem cells, but also had the potential to be immortalized by the DIPG-specific mutation H3K27M in vitro. These findings provide researchers with a candidate normal control and a potential medicine carrier for preclinical research on DIPG.
Animals ; Brain Stem Neoplasms ; genetics ; metabolism ; pathology ; Cell Line, Tumor ; Cellular Senescence ; Female ; Glioma ; genetics ; metabolism ; pathology ; Histones ; genetics ; Humans ; Mice, Inbred NOD ; Mice, SCID ; Neoplasm Transplantation ; Neoplastic Stem Cells ; drug effects ; metabolism ; pathology ; Neural Stem Cells ; drug effects ; metabolism ; pathology ; Pons ; embryology ; metabolism ; pathology ; Primary Cell Culture

Objective To establish a quality control method for bomeol and artificial musk in Xinfufang-Zhenzhusan and Xinfufang-Zhenzhugao.Methods We used petroleum ether-toluene-ethyl acetate (9:3:2)as developer for TLC to identify isoborneol and borneol and petroleum ether-dichloromethane (2:3) as developer for TLC to identificate musk ketone.Agilent 7890 B gas chromatograph,FDI detector;Column:Thermo-TG-WaxMS GC (0.25 mm × 30 m,0.25 mm) was employed;the carrier gas was high purity nitrogen and flow rate for 1 mg/ml,the injection port temperature is 200 C and detector temperature is 250 ℃;the split ratio is 10:1 and injection volume was 1 μl,using temperature programmed.Results The isoborneol,borneol and musk ketone in the range of 0.001-10 mg/ml showed good linearity.The recovery of the method is in the range of 95 ％ to 105 ％.The TLC for isobomeol,bomeol,musk ketone can be identified easily.Conclusions The method was simple and reasonable,which can be used for the quality control of borneol and artificial musk in the Xinfufang-Zhenzhusan and Xinfufang-Zhenzhugao.

Adult ; Branchio-Oto-Renal Syndrome ; diagnosis ; Child, Preschool ; Craniofacial Abnormalities ; diagnosis ; Diagnostic Errors ; Female ; Humans ; Male