Objective To develop an accurate deep learning prediction model of YOLO-V5 capable of accurately iden-tifying medication packaging boxes in outpatient and emergency pharmacies,aiming to assist pharmacists in achieving"zero dis-pensing error".Methods A total of 2 560 images of packaging boxes from 136 different drugs were collected and labeled to form the deep learning dataset.The dataset was split into training and validation sets at a ratio of 4∶1.YOLO-V5 deep-learning algorithm was employed for training the data using images from our dataset(train epochs:500,batch size:4,learning rate:0.01).The values of the precision(Pr)and mean average precision(mAP)were used as measures for model performance evaluation.Results The Pr of the four sub-models of YOLO-V5 in the training set all reached 1.00.The mAP_0.5 of YOLO-V5x was 0.95,which was higher than those of YOLO-V5s(0.94),YOLO-V5l(0.94),and YOLO-V5m(0.94).The mAP_0.5:0.95 of YOLO-V5l and YOLO-V5x were 0.85 which were higher than those of YOLO-V5s(0.84)and YOLO-V5m(0.84).Training time and model size were 82.56 hours and 166.00MB for YOLO-V5x which were the highest among the four models.The speed of detection in one im-age was 11ms for YOLO-V5s which was the fastest among the four models.Conclusion YOLO-V5 can accurately identify the packaging of drugs in outpatient and emergency pharmacies.Implementing an artificial-intelligence-assisted drug dispensation sys-tem is feasible for pharmacists to achieve"zero dispensing error".

Objective To investigate the value of modified YOLO-V5 model for identifying inflammatory bowel disease(IBD)displayed on CT enterography(CTE).Methods Totally 192 patients with IBD(103 cases of Crohn disease[CD subgroup]and 89 cases of ulcerative colitis[UC subgroup])and 103 patients with clinically suspected IBD but CTE showed no abnormality(no abnormality subgroup)were retrospectively collected as study group,while 5 patients with CD and 3 with UC were collected as test group.CTE images with diseased intestinal tubes present as thickened intestinal wall or no abnormality intestinal tubes were selected as data set(n=3 511).CTE in study group were divided into training set(n=3 160,including 1 063 from CD subgroup,931 from UC subgroup and 1 166 from no abnormality subgroup)and verification set(n=351,including 118 from CD subgroup,103 from UC subgroup and 130 from no abnormality subgroup)at the ratio of 9∶1,while 25 CET images(17 from 5 cases of CD and 8 from 3 cases of UC)in test group were used as test set.Diseased tubes of CD,UC and no abnormality tubes were labeled.Then 5 sub-models,including YOLO-V5n,YOLO-V5s,YOLO-V5m,YOLO-V5l and YOLO-V5x were constructed and trained with modified YOLO-V5,and their efficacy were verified in test set.Precision(Pr),recall(Rc)and mean average precision(mAP)were used to evaluate the efficacy of each sub-model for identifying IBD lesions displayed on CTE.Results The complexity of the above 5 sub-models increased successively.YOLO-V5l and YOLO-V5x sub-model had better diagnostic efficacy,the overall Pr,Rc,mAP_0.5 and mAP_0.5.0.95 of the former for identifying IBD lesions in training and validation sets was 0.97,0.93,0.96 and 0.91,while of the latter was 0.97,0.95,0.96 and 0.92,respectively.In test set,the efficacy of YOLO-V5n sub-model for identifying IBD lesions was low,with mAP_0.5∶0.95 of 0.66 and AUC of 0.82,whereas mAP_0.5∶0.95 of YOLO-V5x sub-model for identifying CD was as high as 0.92,and of YOLO-V5l sub-model for identifying UC was as high as 0.91.Conclusion YOLO-V5l and YOLO-V5x sub-models based on modified YOLO-V5 could effectively identify IBD lesions displayed on CTE.

Objective:To investigate the value of a deep learning method based on MobileNet in classification of bedside chest radiograph and improvement of the work efficiency.Methods:A total of 6, 320 bedside chest radiographs from January 2017 to December 2022 in the Second Peoples′ Hospital of Changzhou were retrospectively collected. The included cases were divided into normal group (885 images), pneumonia group (1 927 images), pleural effusion group (373 images), and pneumonia with pleural effusion group (3 135 images). Three hundred and fifty images were selected as a validation set, while the remaining images were divided into a train set (4 775 images) and a test set (1 195 images) using simple randomization, by 8∶2 ratio. Two lightweight convolutional neural network models (MobileNetV1 and MobileNetV2) were used to construct a bedside chest radiograph classification model, based on which two fine-tuning strategies were designed. Four models were generated namely MobileNetV1_False (V1_False), MobileNetV1_True (V1_True), MobileNetV2_False (V2_False) and MobileNetV2_True (V2_True). In the first stage, a binary classification model was established to divide the images into normal and lesion groups; then a four-class classification model was established in the second stage, with which the images were divided into four groups: normal, pneumonia, pleural effusion and pneumonia with pleural effusion. Metrics for model performance evaluation including accuracy (Ac), precision (Pr), recall rate (Rc), F1 score (F1) and area under the receiver operating characteristic curve (AUC) were calculated.Results:In both the first and second stages, V1_True and V2_True had higher Ac, Pr, Rc, and F1 than V1_False and V2_False in both the training set and validation set; and the V1_True model outperformed the other three models in classification. The classification Ac of the V1_True model in the validation set was higher than that of radiologists in the first stage [95.71% (335/350) vs. 90.29% (316/350)] and in the second stage [93.43% (327/350) vs. 87.14% (305/350)]. The recognition time of V1_True model′s in the validation set of 350 bedside chest radiographs was significantly less than that of the radiologists (mean: 17 s vs. 300 min).Conclusions:V1_True is an optimal MobileNet model for classifying bedside chest radiographs. The application of this model in clinical practice may help to accurately identify the information of lung lesions from bedside chest radiographs in time, and may improve the work efficiency in the radiology department.

Chemically defined medium is widely used for culturing mouse embryonic stem cells (mESCs), in which N2B27 works as a substitution for serum, and GSK3β and MEK inhibitors (2i) help to promote ground-state pluripotency. However, recent studies suggested that MEKi might cause irreversible defects that compromise the developmental potential of mESCs. Here, we demonstrated the deficient bone morphogenetic protein (BMP) signal in the chemically defined condition is one of the main causes for the impaired pluripotency. Mechanistically, activating the BMP signal pathway by BMP4 could safeguard the chromosomal integrity and proliferation capacity of mESCs through regulating downstream targets Ube2s and Chmp4b. More importantly, BMP4 promotes a distinct in vivo developmental potential and a long-term pluripotency preservation. Besides, the pluripotent improvements driven by BMP4 are superior to those by attenuating MEK suppression. Taken together, our study shows appropriate activation of BMP signal is essential for regulating functional pluripotency and reveals that BMP4 should be applied in the serum-free culture system.
Animals ; Bone Morphogenetic Protein 4/metabolism* ; Cell Differentiation ; Chromosomal Instability ; Endosomal Sorting Complexes Required for Transport ; Mice ; Mitogen-Activated Protein Kinase Kinases/metabolism* ; Mouse Embryonic Stem Cells/cytology* ; Pluripotent Stem Cells/cytology* ; Signal Transduction ; Ubiquitin-Conjugating Enzymes

Retinal pigment epithelium(RPE)has essential functions,such as nourishing and sup-porting the neural retina,and is of vital importance in the pathogenesis of age-related retinal degen-eration.However,the exact molecular changes of RPE during aging remain poorly understood.Here,we isolated human primary RPE(hRPE)cells from 18 eye donors distributed over a wide age range(10-67 years old).A quantitative proteomic analysis was performed to analyze changes in their intracellular and secreted proteins.Age-group related subtypes and age-associated proteins were revealed and potential age-associated mechanisms were validated in ARPE-19 and hRPE cells.The results of proteomic data analysis and verifications suggest that RNF123-and RNF149-related protein ubiquitination plays an important role in protecting hRPE cells from oxidative damage dur-ing aging.In older hRPE cells,apoptotic signaling-related pathways were up-regulated,and endo-plasmic reticulum organization was down-regulated both in the intracellular and secreted proteomes.Our work paints a detailed molecular picture of hRPE cells during the aging process and provides new insights into the molecular characteristics of RPE during aging and under other related clinical retinal conditions.

Objective To evaluate the effect of dexmedetomidine on nerve regeneration following cerebral ischemia-reperfusion (Ⅰ/R) in mice and the role of transforming growth factor-beta 1 (TGF-β1) in brain tissues.Methods Sixty healthy SPF male C57BL/6J mice,weighing 23-25 g,aged 8-10 weeks,were divided into 5 groups (n =12 each) using a random number table method:sham operation group (group Sham),Ⅰ/R group,dexmedetomidine group (group D),dexmedetomidine plus IgG1 isotype control monoclonal antibody group (group DI) and dexmedetomidine plus TGF-β1 neutralizing monoclonal antibody group (group DA).Cerebral Ⅰ/R was induced by occlusion of the middle cerebral artery followed by reperfusion.Dexmedetomidine 50 μg/kg was intraperitoneally injected every 24 h for 14 days starting from 14 days of reperfusion in group D.TGF-β1 neutralizing monoclonal antibody 20 μg and IgG1 isotype control monoclonal antibody 20 μg were intraperitoneally injected at 30 min prior to dexmedetomidine injection in group DA and group DI,respectively.5-bromodeoxyuridine (BrdU) 100 mg/kg was intraperitoneally injected and injected again at an 8-h interval on 27 days of reperfusion.Forced swimming test (FST),sucrose consumption test (SCT) and open field test (OFT) were performed at 16 h after the second administration of BrdU.After the end of behavior testing,the number of Ki67,BrdU and BrdU/DCX positive cells in the subventricular zone on ischemic side was measured by immunohistochemistry,and the expression of TGF-β1 protein and mRNA in brain tissues in ischemic area was detected using Western blot and real-time polymerase chain reaction,respectively.Results Compared with group Sham,the time spent floating in FST was significantly prolonged,the percent of time spent in the central region in OFT and sucrose solution intake in SCT were decreased,the number of Ki67,BrdU and BrdU/DCX positive cells in the subventricular zone was increased,and the expression of TGF-β1 protein and mRNA was up-regulated in group Ⅰ/R (P＜0.05 or 0.01).Compared with group Ⅰ/R,the time spent floating in FST was significantly shortened,the percent of time spent in the central region in OFT and sucrose solution intake in SCT were increased,the number of Ki67,BrdU and BrdU/DCX positive cells in the subventricular zone was increased,and the expression of TGF-β1 protein and mRNA was up-regulated in group D (P＜0.05 or 0.01).Compared with group D,the time spent floating in FST was significantly prolonged,the percent of time spent in the central region in OFT and sucrose solution intake in SCT were decreased,the number of Ki67,BrdU and BrdU/DCX positive cells in the subventricular zone was decreased in group DA (P ＜ 0.05),and no significant change was found in the parameters mentioned above in group DI (P＞0.05).Conclusion Dexmedetomidine can relieve depression and anxiety following cerebral Ⅰ/R,thus promotes nerve regeneration and the mechanism is related to up-regulating the expression of TGF-β1 in brain tissues of mice.

Objective To explore the effect of information system management combined with PDCA on negative emotion and quality of life in patients with Parkinson's disease.Methods Totally of 232 patients with Parkinson's disease who were hospitalized in Affiliated Hospital of Ji'ning Medical University from July 2014 to June 2016 were selected and divided into observation group and control group according to the random number table, with 116 cases in each group. The control group was given routine mental health education, while the observation group was treated with the combination of PDCA and nursing intervention on the basis of routine nursing. The scores of depression, cognitive function and quality of life were measured and evaluated at three months after admission.Results At the time of admission, scores of depression showed no significant difference between two groups (t=0.965,P=0.102); after the intervention, the score of depression in the observation group was significantly lower than that in the control group, and the difference was statistically significant (t=3.359, P=0.001). Before the intervention, the score of cognitive assessment scale showed no significant difference between two groups (t=1.254,P=0.068); after the intervention, cognitive function score in the observation group was significantly higher than that in the control group, and the difference was statistically significant (t=4.021, P<0.001). The scores of physiological function, psychological function, social function, environmental adaptability and total quality of life in the observation group were improved significantly higher than those in the control group, and the differences were statistically significant (t=5.274, 4.667, 4.277, 4.148, 3.957;P<0.01).Conclusions Information system management combined with PDCA mode nursing intervention can improve the negative emotions and the quality of life of patients with Parkinson's disease.

Objective To explore the application of CARE kV technique in the adult chest CT and the value of reducing radiation dose.Methods Sixty-nine patients were divided into two groups by random number generators:group A(39 cases) and group B(30 cases).Group A was examined by using CARE kV technique and group B was examined at routine 120 kV.CT dose index(CTDIvol),dose length product (DLP) and effective dose (E) were compared between the two groups,and analyzed the correlation between tube voltage selection and patient body mass index (BMI) of group A was analyzed.Results The average CTDIvol [(11.00 ± 3.89) mGy],DLP[(294.05 ± 91.17) mGy·cm] and E[(4.12 ± 1.28) mSv] of group A were lower than those of group B (16.64 ± 1.20) mGy,[(475.99 ± 41.16) mGy · cm],[(6.66 ±0.58) mSv].With statistically significant difference (t =-7.653,-10.151,-10.150,P ＜ 0.05).Compared with routine 120 kV technique (group B),the CARE kV technique (group A) could reduce the total radiation dose about 38.14％.Compared obese patients(BMI≥28 kg/m2) with non-obese patients in group A and B,the mean E of non-obese patients was lower than that of obese patients in group A,which reduced the total E about 31.74％ (t =4.322,P ＜0.05),while E in group B was no significant different between non-obese patients and obese patients.Conclusions In adult chest CT,CARE kV technique can select optimum scanning voltage automatically according to the patients with different BMI and anatomical regions,which can reduce the overall radiation dose while maintaining image quality.

Objective To determine the optimum dose of dexmedetomidine through evaluating the effects of different doses of dexmedetomidine combined with propofol and remifentanil for anesthesia during laparotomy in patients with mild liver dysfunction.Methods Sixty ASA physical status Ⅱ patients of both sexes,aged 18-60 yr,with body mass index 20-26kg/m2,Child-Pugh grade A,undergoing radical resection for stomach or colon cancer,were randomly assigned into 3 groups (n=20 each):propofol and remifentanil group (group Ⅰ),low-dose dexmedetomidine combined with propofol and remifentanil group (group Ⅱ) and high-dose dexmedetomidine combined with propofol and remifentanil group (group Ⅲ).In Ⅱ and Ⅲ groups,dexmedetomidine was infused at a rate of 0.2 μg·kg-1 · h-1 and 0.4 μg·kg 1 · h-1,respectively,until 30 min before the end of surgery after a loading dose of dexmedetomidine 0.4 μg/kg and 0.8 μg/kg,respectively,was infused at 10 min before induction of anesthesia.The patients were mechanically ventilated after tracheal intubation.Anesthesia was maintained with target-controlled infusion of propofol (target plasma concentration 2-4 μg/ml),iv infusion of remifentanil 0.2 μμg·kg-1 · h-1 and intermittent iv boluses of rocuronium 0.15 mg/kg.BIS value was maintained at 40-60.Before dexmedetomidine infusion (T0),at 2 min before intubation (T1),at 1 min after intubation (T2),immediatay after zskin incision (T3),and at 30 min of surgery (T4),arterial blood samples were taken for measurement of concentrations of plasma norepinephrine (NE) and epinephrine (E).The emergence time,adverse cardiovascular events,and the development of nausea and vomiting and restlessness during recovery from anesthesia were recorded.Results Compared with group Ⅰ,the plasma concentration of propofol was significantly decreased,and the incidence of tachycardia and restlessness during recovery from anesthesia were significantly decreased in Ⅱ and Ⅲ groups,and the incidence of bradycardia during operation was significantly increased,and the incidence of hypertension during recovery from anesthesia was significantly decreased,and the emergence time was prolonged in group Ⅲ (P ＜ 0.05).Compared with group Ⅱ,the plasma concentration of propofol was significantly decreased,the incidence of bradycardia during operation was increased,and the emergence time was prolonged in group Ⅲ (P ＜0.05).The plasma NE and E concentrations were significantly higher at T2.3 in group Ⅰ,and were lower at T1-4 in Ⅰ and Ⅲ groups than those at T0 (P ＜ 0.05).Conclusion 0.4 μg/kg injected before induction of anesthesia followed by infusion at 0.2 μg·kg-1 · h-1 is the recommended optimum method for application of dexmedetomidine when combined with propofol and remifentanil for anesthesia during laparotomy in patients with mild liver dysfunction.