Objective:To construct an artificial intelligence (AI)-assisted system based on deep learning for corneal in vivo confocal microscopy (IVCM) image recognition and to evaluate its value in clinical applications. Methods:A diagnostic study was conducted.A total of 18 860 corneal images were collected from 331 subjects who underwent IVCM examination at Renmin Hospital of Wuhan University and Zhongnan Hospital of Wuhan University from May 2021 to September 2022.The collected images were used for model training and testing after being reviewed and classified by corneal experts.The model design included a low-quality image filtering model, a corneal image diagnosis model, and a 4-layer identification model for corneal epithelium, Bowman membrane, stroma, and endothelium, to initially determine normal and abnormal corneal images and corresponding corneal layers.A human-machine competition was conducted with another 360 database-independent IVCM images to compare the accuracy and time spent on image recognition by three senior ophthalmologists and the AI system.In addition, 8 trainees without IVCM training and with less than three years of clinical experience were selected to recognize the same 360 images without and with model assistance to analyze the effectiveness of model assistance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY2021-K148).Results:The accuracy of this diagnostic model in screening high-quality images was 0.954.Its overall accuracy in identifying normal/abnormal corneal images was 0.916 and 0.896 in the internal and external test sets, respectively.Its accuracy reached 0.983, 0.925 in the internal test sets and 0.988, 0.929 in the external test sets in identifying corneal layers of normal and abnormal images, respectively.In the human-machine competition, the overall recognition accuracy of the model was 0.878, which was similar to the average accuracy of the three senior physicians and was approximately 300 times faster than the experts in recognition speed.Trainees assisted by the system achieved an accuracy of 0.816±0.043 in identifying corneal layers of normal and abnormal images, which was significantly higher than 0.669±0.061 without model assistance ( t=6.304, P<0.001). Conclusions:A deep learning-based assistant system for corneal IVCM image recognition is successfully constructed.This system can discriminate normal/abnormal corneal images and diagnose the corresponding corneal layer of the images, which can improve the efficiency of clinical diagnosis and assist doctors in training and learning.

This study reports on three patients with Shwachman-Diamond syndrome (SDS) who underwent allogeneic hematopoietic stem cell transplantation (allo-HSCT) at the First Affiliated Hospital of Zhejiang University School of Medicine. Based on relevant literature, the clinical manifestations and genetic mutation characteristics of SDS were summarized, and the efficacy and timing of allo HSCT for such patients were explored. Three SDS patients were all male, with transplant ages of 32, 33, and 32 years old, respectively. All three patients were diagnosed in childhood. Case 1 presented with anemia as the initial clinical manifestation, which gradually progressed to a decrease in whole blood cells; Case 2 and 3 both present with a decrease in whole blood cells as the initial clinical manifestation. Case 1 and 3 have intellectual disabilities, while case 3 presents with pancreatic steatosis and chronic pancreatitis. All three patients have short stature. Three patients all detected heterozygous mutations in the SBDS: c.258+2T>C splice site. The family members of the three patients have no clinical manifestations of SDS. All three patients were treated with a reduced dose pre-treatment regimen (Fludarabine+Busulfan+Me-CCNU+Rabbit Anti-human Thymocyte Globulin). Case 1 and case 2 underwent haploid hematopoietic stem cell transplantation, while case 3 underwent unrelated donor hematopoietic stem cell transplantation. Case 1 was diagnosed with myelodysplastic syndrome transforming into acute myeloid leukemia before transplantation, but experienced early recurrence and death after transplantation; Case 2 is secondary implantation failure, dependent on platelet transfusion; Case 3 was removed from medication maintenance treatment after transplantation, and blood routine monitoring was normal.

Objective:To explore the clinical application value of a deep learning algorithm-based ultrasound biomicroscopy (UBM) image analysis system for primary angles-closure glaucoma (PACG) anterior located ciliary body.Methods:A diagnostic test study was conducted.A total of 2 132 UBM images from 726 eyes of 378 PACG patients who underwent UBM examination were collected at Renmin Hospital of Wuhan University from August 2022 to December 2023.The dataset was divided into a training set of 1 599 images and a test set of 533 images, and a deep learning algorithm was employed to construct a model.An additional 334 UBM images from 101 eyes of 69 PACG patients treated at Huangshi Aier Eye Hospital were selected to conduct external testing.A separate set of another 110 UBM images were selected for a human-machine competition to compare the accuracy and speed between anterior located ciliary body evaluation system and three senior ophthalmologists.Furthermore, eight junior ophthalmologists assessed the 110 UBM images independently without and with the assistance of the model, and the differences between the two evaluations were analyzed to assess the assisstance effect of the model.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY-2022-K109).Results:The model achieved an accuracy of 93.43% for anterior located ciliary body identification in the internal test set, with a sensitivity of 84.30% and a specificity of 97.78%.The model also performed well on the external test set with an accuracy of 92.81%.In the human-machine competition, the model's accuracy was comparable to that of the senior ophthalmologists and outperformed two of the three senior ophthalmologists.The average total time of the three senior ophthalmologists was 726.73 seconds, approximately 12.47 times longer than the model's 58.30 seconds.With model assistance, the diagnostic accuracy of the eight junior ophthalmologists was 86.71%, which was significantly higher than 76.25% without model assistance ( χ2=-7.550, P<0.001).And the image evaluation time was (714.91±213.82)seconds, which was significantly lower than (987.90±238.56)seconds without model assistance ( t=2.774, P<0.05). Conclusions:The UBM image analysis system based on a deep learning algorithm demonstrates high accuracy in diagnosing anterior located ciliary body in PACG and provides a strong support for the UBM image recognition training of junior ophthalmologists.

A total of 1 685 school-age children selected from Hangzhou received lung function testing to evaluate the short-term effects of air pollution on their lung function. The results showed that in every 10 μg/m³ increase of average concentration of PM_2.5 and PM₁₀ on the day of the test and the day before the test,peak expiratory flow (PEF) decreased 0.039 (95%CI: 0.012-0.067) L/s and 0.031 (95% CI:0.011-0.051) L/s,respectively. When the average concentration of SO₂ increased 10 μg/m³ on the day of test and the day prior to the test, PEF and 75% of the forced vital capacity that has not been exhaled (MEF₇₅) decreased 0.437 (95%CI: 0.217-0.658) L/s and 0.396 (95%CI: 0.180-0.613) L/s. After being adjusted for NO₂,with every 10 μg/m³ increase of average concentration of PM_2.5 and PM₁₀ on the day of the test and the day before the test,PEF and MEF₇₅ decreased 0.056 (95%CI: 0.028-0.085), 0.053(95%CI: 0.027-0.081) and 0.047 (95%CI: 0.026-0.068) L/s,0.044 (95%CI: 0.023-0.065) L/s on the day before the test, respectively. The results indicate that air pollution have short-term and lag effects on lung function of school-age children in Hangzhou.

Objective: To investigate whether it can reduce the incidence of pressure ulcer caused by ICU equipment, when nurses in ICU use the SKIN model framework to carry out preventive and nursing measures. Methods: To construct the teaching group of nursing workshop based on SKIN mode for preventing pressure ulcer caused by ICU equipment and train 36 ICU nurses. Before and after training course, to collect the behaviors of preventing pressure ulcer caused by ICU equipment during clinical work time and the incidence and severity of pressure ulcer. Results: The nurses′ behaviors of controlling skin status of patients who use Bi-level positive airway pressure non-invasive mask and evaluating nutritional status of patients change a lot (χ²=34.420,10.123, P <0.01). The nurses′ behaviors of checking and evaluating skin status of patients who have stomach tube to reduce skin pressure, shear and friction and assessing nutritional status of patients were improved (χ²=7.547-49.451, P <0.05). The nurses′ behaviors mentioned above of nursing patients who have oral air tube were also changed significantly (χ²=5.225, 23.402, 12.444, P<0.05 or 0.01). The incidence of pressure ulcer caused by ICU equipment dropped from 2.86%(100/3 502) to 1.87%(67/3 580) (χ²=7.445, P<0.05). The decrease in incidence of Ⅱand Ⅲ grade pressure ulcer are from 48%(48/100) to 22.39%(15/67) and 34%(34/100) to 7.46%(5/67) respectively and had significant differences as well (χ²=11.202, 15.784, P<0.01). Conclusions This study explains the training approach based on SKIN mode of prevention of pressure ulcer caused by ICU equipment. The results show that the training approach can decrease the incidence and severity of pressure ulcer caused by ICU equipment, improve the nurses′ nursing behaviors and promote the transform of theory related to pressure ulcer from basement to clinical reality.

A total of 1 685 school?age children selected from Hangzhou received lung function testing to evaluate the short?term effects of air pollution on their lung function. The results showed that in every 10 μg/m3 increase of average concentration of PM2.5 and PM10 on the day of the test and the day before the test,peak expiratory flow (PEF) decreased 0.039 (95%CI: 0.012-0.067) L/s and 0.031 (95% CI:0.011-0.051) L/s,respectively. When the average concentration of SO2 increased 10 μg/m3 on the day of test and the day prior to the test, PEF and 75% of the forced vital capacity that has not been exhaled (MEF75) decreased 0.437 (95%CI: 0.217-0.658) L/s and 0.396 (95%CI : 0.180-0.613) L/s. After being adjusted for NO2,with every 10 μg/m3 increase of average concentration of PM2.5 and PM10 on the day of the test and the day before the test,PEF and MEF75 decreased 0.056 (95%CI: 0.028-0.085), 0.053(95%CI: 0.027-0.081) and 0.047 (95%CI: 0.026-0.068) L/s, 0.044 (95%CI: 0.023-0.065) L/s on the day before the test, respectively. The results indicate that air pollution have short?term and lag effects on lung function of school?age children in Hangzhou.

A total of 1 685 school?age children selected from Hangzhou received lung function testing to evaluate the short?term effects of air pollution on their lung function. The results showed that in every 10 μg/m3 increase of average concentration of PM2.5 and PM10 on the day of the test and the day before the test,peak expiratory flow (PEF) decreased 0.039 (95%CI: 0.012-0.067) L/s and 0.031 (95% CI:0.011-0.051) L/s,respectively. When the average concentration of SO2 increased 10 μg/m3 on the day of test and the day prior to the test, PEF and 75% of the forced vital capacity that has not been exhaled (MEF75) decreased 0.437 (95%CI: 0.217-0.658) L/s and 0.396 (95%CI : 0.180-0.613) L/s. After being adjusted for NO2,with every 10 μg/m3 increase of average concentration of PM2.5 and PM10 on the day of the test and the day before the test,PEF and MEF75 decreased 0.056 (95%CI: 0.028-0.085), 0.053(95%CI: 0.027-0.081) and 0.047 (95%CI: 0.026-0.068) L/s, 0.044 (95%CI: 0.023-0.065) L/s on the day before the test, respectively. The results indicate that air pollution have short?term and lag effects on lung function of school?age children in Hangzhou.

Objective To improve fresh nurses′ implementation rate of standard clinical administration checking by applying situational simulation method, and enhancetheir ability of identifying hidden perils in nursing. Methods Totally 75 fresh nurses who graduated in 2016 were enrolled and divided into two groups (36 in control group and 39 in experimental group) according to randomized digital table method. Situational simulation method was applied in the experimental group, while the control group applied traditional nursing safety check training method. Then both groups′ satisfaction rate of lessons and self-confidence after training were recorded. Besides, their clinical administration checking behaviors after 3 months, the errors, hidden perilsand examining situations related to administration checking after 6 months,were also evaluated. Results Significant statistical differences were shown in satisfaction score (23.62 ± 2.02 in experimental group vs. 21.39 ± 1.98 in control group, t=4.818, P<0.01) and self-confidential evaluating score (35.67±2.02 in experimental group vs. 21.39±1.98 in control group, t=2.768, P<0.01). Observation of clinical administration checking behaviors 3 months after training had indicated significant differences in the number of nurses who check drug concentration (33 vs. 8, χ2=29.406, P<0.05) and executing time (30vs. 12, χ2=14.436, P<0.05).Statistical differences (χ2= 5.080-29.545, P< 0.01 or < 0.05) were also observed in the number of nurses checking bed number, patient name, drug name, dose, drug concentration and methods in and after operation. The potential nursing perils identified, and the number of nurses who identify hidden nursing perils 3 months and 6 months after training were significantly larger (χ2=50.591, 23.658, 3.914, P<0.05) in experimental group (33, 2, 10) than in control group (18, 1, 3),and there were no significant differences in the rate of potential perils and nursing error between both groups. Conclusion Situational method of administration, which is applied for fresh nurses in their initial working phase, transforms the basic and core checking system into clinical real-situation cases. It also shows an advantage of boosting their self-confidence of learning, improving the implementation rate of standard clinical administration checking and the ability of avoiding potential nursing perils.

Objective: To study the effect of WT1 expression on the prognosis of allogeneic hematopoietic stem cell transplantation (allo-HSCT) in acute leukemia (AL) and its significance as molecular marker to dynamically monitor minimal residual disease (MRD) . Methods: Retrospectively analyzed those AL patients who underwent allo-HSCT in the First Hospital Affiliated to Zhejiang University School of Medicine during Jan 2016 to Dec 2017, a total number of 314 cases, 163 males and 151 females, median age was 30 (9-64) years old. Comparing the difference of WT1 expression at diagnosed, pre-HSCT and after HSCT. Using the receiver operating characteristic (ROC) curve to determine the WT1 threshold at different time so as to predict relapse. The threshold of WT1 expression before transplantation was 1.010%, within 3 months after HSCT was 0.079% and 6 months after HSCT was 0.375%. According to these thresholds, WT1 positive patients were divided into low expression groups and high expression groups. Analyzed the relationship between overall survival (OS) , disease-free survival (DFS) , cumulative incidence of relapse (CIR) and WT1 expression. Results: The OS and DFS of high expression group pre-HSCT were lower than low expression group [69.2% (9/13) vs 89.1% (57/64) , χ²=4.086, P=0.043; 53.8% (7/13) vs 87.5% (56/64) , χ²=9.766, P=0.002], CIR was higher than low expression group [30.8% (4/13) vs 7.8% (5/64) , P=0.017]. There was no significant difference of OS and DFS between high expression and low expression group of 3 months after HSCT (P=0.558, P=0.269) . The OS and DFS of high expression group of 6 months after transplantation were both lower than low expression group (P=0.049, P=0.035) . Multivariate analysis showed that WT1>0.375% when 6 months after transplantation was the only independent prognostic factor for shorter DFS (P=0.022) . There was no statistically significant difference in CIR between the high-expression group and the low-expression group 3 months after transplantation and 6 months after transplantation (P=0.114, P=0.306) . Conclusion High expression of WT1 before and after HSCT was an adverse prognosis factor. It is of clinical practical value to use WT1 as a transplant recommendation index for patients with acute leukemia and as a marker to monitor MRD dynamically.

We investigated the third-generation cephalosporins-resistant Shigella and its genotype in Ningbo,China,providing a basis for disease prevention and control.Pathogenic bacteria were analyzed by direct isolation combined with enrichment culture isolation.Antimicrobial susceptibility was determined by K-B disk diffusion method and PCR was used for detecting multidrug resistance genes like CTX-M,OXA,TEM and SHV.BLAST analysis was used to determine the genotype.Results showed that 69 strains of third-generation cephalosporins-resistant Shigella were detected by drug sensitivity screening,accounting for 74.19％ of ESBLs Shigella.Drug resistance gene CTX-M(CTM-M-1 and CTM-M-9),OXA and TEM were detected.The detection rate were 79.71％,79.01％ and 26.09％ respectively.With no CTX-M-2 and SHV,DNA sequence alignment showed CTX-M-1 group were mainly of CTX-M-15 type besides seven other types;CTX-M-9 group were mainly of CTX-M-14 type besides six other types;49 strains of OXA and 18 strains of TEM were sequenced to be type 1 (OXA-1 and TEM-1 type).The 21 Shigella strains carrying more than two drug resistance genes accounts for 30.43 ％.Shigella in Ningbo has high third-generation cephalosporins-resistance rate and many kinds of ESBLs enzymes were detected.The mainstream enzyme type was CTX-M,meanwhile they also carried a variety of drug resistance genes,which could bring difficulties to disease prevention and control.The high carrying rate of OXA-1 type suggests that we should pay more attention.The detection rate of group B was higher than that of group D,including not only the phenotype resistance but also the drug-resistance genes;these findings will be useful in the study of the drug resistance prevalence of Shigella.