1.Research and application of a new deep learning based strategy for platelet histogram review
Enming ZHANG ; Chao YANG ; Xianchun CHEN ; Yan LIN ; Taixue AN ; Haixia LI ; Yongjian HE ; Zhiwei LIU ; Limei FENG ; Wanying LIN ; Tie XIONG ; Kai QIU ; Ya GAO ; Lizhu HUANG ; Jing HE ; Chunyan WANG ; Dehua SUN ; Bo SITU ; Lei ZHENG
Chinese Journal of Laboratory Medicine 2025;48(9):1201-1206
Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.
2.Research and application of a new deep learning based strategy for platelet histogram review
Enming ZHANG ; Chao YANG ; Xianchun CHEN ; Yan LIN ; Taixue AN ; Haixia LI ; Yongjian HE ; Zhiwei LIU ; Limei FENG ; Wanying LIN ; Tie XIONG ; Kai QIU ; Ya GAO ; Lizhu HUANG ; Jing HE ; Chunyan WANG ; Dehua SUN ; Bo SITU ; Lei ZHENG
Chinese Journal of Laboratory Medicine 2025;48(9):1201-1206
Objective:To develop an artificial intelligence (AI)-based platelet review strategy to identify abnormal platelet histograms with no significant difference between initial impedance platelet count (PLT-I) and PLT-F results.Methods:This study included 5 119 routine blood analysis in Nanfang Hospital of Southern Medical University and its Ganzhou branch from July 2023 and March 2024. Specimens exhibiting abnormal platelet histograms and an initial platelet count >40×10?/L underwent review using the fluorescent platelet count (PLT-F) channel. Consistency of the results was defined as a difference between impedance platelet count (PLT-I) and PLT-F less than ±20% of the PLT-F results. A deep learning model was developed using platelet and red blood cell histogram data from a training set of 3 807 specimens. The model′s diagnostic performance was evaluated on an independent external validation set ( n=805) using receiver operating characteristic (ROC) curve analysis. Changes in the number of reviewed samples and sample turnaround time were analyzed to assess its clinical utility. Results:The deep learning model based on platelet and red blood cell histograms achieved an area under the ROC curve (AUC) of 0.854 in the training set. At a cutoff value of 0.1, the sensitivity was 0.954 and specificity was 0.358. The model could reduce review by 16.80% (190/1 131). In the validation set, the AUC was 0.805, with a sensitivity of 0.955 and specificity of 0.307, corresponding to a reduction of 17.41% (47/270) in reviewed specimens.Conclusion:The platelet review prediction model developed based on deep learning technology can efficiently identify samples with consistent results before and after review, reducing unnecessary reviews and shortening specimen testing time, thereby improving the efficiency of platelet test.
3.Analysis of the epidemic characteristics and treatment outcomes of rifampicin-resistant pulmonary tuberculosis in Yangzhou City from 2012 to 2020
Hui WANG ; Jincheng LI ; Chunhong BO ; Lei WANG ; Qianying ZHAO ; Limei ZHU
Chinese Journal of Preventive Medicine 2024;58(11):1679-1683
Information on patients with rifampicin-resistant pulmonary tuberculosis (RR-PTB) in Yangzhou City from 2012 to 2020 was obtained from the Information System of the Chinese Center for Disease Control and Prevention. The epidemic characteristics of RR-PTB patients were analyzed by using χ2 test. The average annual registered incidence rate of RR-PTB patients in Yangzhou City from 2012 to 2020 was 0.57/100 000, and the difference between the registered incidence rates in each year was statistically significant ( χ2=29.326, P<0.001). The proportion of re-treated patients (64.8%) was higher than that of newly treated patients (35.2%, χ2=50.593, P<0.001). The registered incidence rate in males (0.91/100 000) was higher than that in females (0.24/100 000, χ2=80.566, P<0.001). The age distribution showed that the highest incidence rate was in the age group≥60 years (0.96/100 000) and the lowest was in the age group 0-<45 years (0.31/100 000, χ2=55.853, P<0.001). From 2012 to 2020, Baoying County had the largest number of registered RR-PTB patients (44 cases), and its registered incidence rate (0.64/100 000) was only lower than that of Guangling District (0.98/100 000). The registered incidence rate of RR-PTB patients in Baoying County during 2016—2020 also increased significantly compared to 2012—2015 ( P=0.001). Logistic regression was used to analyze the factors related to the treatment outcome of RR-PTB patients. The results showed that patients aged≥60 years and those classified as the re-treatment were risk factors for successful treatment of RR-PTB patients ( P<0.05). In summary, males, people aged≥60 years, patients classified as the re-treatment, and residents of Baoying County should be the key populations for RR-PTB epidemic prevention and control in Yangzhou City.
4.Analysis of the epidemic characteristics and treatment outcomes of rifampicin-resistant pulmonary tuberculosis in Yangzhou City from 2012 to 2020
Hui WANG ; Jincheng LI ; Chunhong BO ; Lei WANG ; Qianying ZHAO ; Limei ZHU
Chinese Journal of Preventive Medicine 2024;58(11):1679-1683
Information on patients with rifampicin-resistant pulmonary tuberculosis (RR-PTB) in Yangzhou City from 2012 to 2020 was obtained from the Information System of the Chinese Center for Disease Control and Prevention. The epidemic characteristics of RR-PTB patients were analyzed by using χ2 test. The average annual registered incidence rate of RR-PTB patients in Yangzhou City from 2012 to 2020 was 0.57/100 000, and the difference between the registered incidence rates in each year was statistically significant ( χ2=29.326, P<0.001). The proportion of re-treated patients (64.8%) was higher than that of newly treated patients (35.2%, χ2=50.593, P<0.001). The registered incidence rate in males (0.91/100 000) was higher than that in females (0.24/100 000, χ2=80.566, P<0.001). The age distribution showed that the highest incidence rate was in the age group≥60 years (0.96/100 000) and the lowest was in the age group 0-<45 years (0.31/100 000, χ2=55.853, P<0.001). From 2012 to 2020, Baoying County had the largest number of registered RR-PTB patients (44 cases), and its registered incidence rate (0.64/100 000) was only lower than that of Guangling District (0.98/100 000). The registered incidence rate of RR-PTB patients in Baoying County during 2016—2020 also increased significantly compared to 2012—2015 ( P=0.001). Logistic regression was used to analyze the factors related to the treatment outcome of RR-PTB patients. The results showed that patients aged≥60 years and those classified as the re-treatment were risk factors for successful treatment of RR-PTB patients ( P<0.05). In summary, males, people aged≥60 years, patients classified as the re-treatment, and residents of Baoying County should be the key populations for RR-PTB epidemic prevention and control in Yangzhou City.
5.Study on the status quo and correlation between body image and stigma of drug-resistant tuberculosis patients treated with Clofazimine
Fanghui XIE ; Limei LEI ; Rong YAO ; Xia ZHAO ; Bin WAN ; Meng MENG
Chinese Journal of Practical Nursing 2023;39(7):486-491
Objective:To investigate the current situation of body image and stigma of drug-resistant tuberculosis patients treated with Clofazimine, and analyze the correlation between them.Methods:A cross-sectional study was conducted using convenience sampling method to investigate 150 patients with drug-resistant tuberculosis treated with Clofazimine in tuberculosis ward of Chengdu Public Health Clinical Medical Center from October 2020 to October 2021. The general questionnaire, Body Image Scale (BIS) and Tuberculosis Related Stigma Scale were used to conduct a questionnaire survey.Results:A total of 130 questionnaires were effectively collected. The body image score of 130 patients with drug-resistant tuberculosis treated with Clofazimine was (20.51 ± 6.80) points; the score of stigma was (17.78 ± 6.92) points. There was a positive correlation between the total score of disease shame and the total score of body image ( r=0.544, P<0.05). Conclusions:Patients with drug-resistant tuberculosis treated with Clofazimine have body image disorder and stigma, and the two are positively correlated. Caregivers should carry out psychological assessment and intervention at an early stage to improve the patient′s mental health level.
6.Survey on the first-aid capability of primary general practitioners in southern Zhejiang province
Ruonan HOU ; Sonam DEKYI ; Xiaoming ZHOU ; Wei ZHOU ; Limei LEI ; Minwu ZHANG ; Xiyi XU ; Jie WENG ; Liping WU ; Zhiyi WANG ; Daqing CHEN
Chinese Journal of General Practitioners 2021;20(1):67-72
Objective:To survey the first-aid ability of general practitioners (GPs) and the emergency service capacity of primary health institutions in southern Zhejiang province.Methods:The questionnaire of first-aid ability of GPs in primary care institution was developed on the basis of the Delphi method during August to October 2018. The questionnaire was employed in a survey on the first-aid ability among 480 GPs from 169 community health service centers of three regions in southern Zhejiang province. The survey covered basic information and first-aid skills and emergency response ability of GPs, and the emergency facilities of primary health institutions.Results:A total of 480 questionnaires were distributed and 447 were retrieved with an recovery rate of 93. 1%(447/480). Among the 447 responders, 55.9% (250/447) were males, 70.9% (317/447) had bachelor′s degree or above, and 60.2% (269/447) had middle and senior professional titles. There were 99.6% (445/447), 86.6% (387/447), 76.1% (340/447) and 69.8% (312/447) responders considered cardiopulmonary resuscitation(CPR), electrical defibrillation, respiratory balloon and endotracheal intubation as important first-aid skills, and corresponding mastery rates were 84.3% (377/447), 32.0% (143/447), 55.2% (247/447) and 12.9% (58/447), respectively. The 92.4% (413/447) responders thought that the rescue ability of common emergency and critical illness was the most important, while only 32.4% (145/447) responders mastered it. Least responders [41.4%(185/447)] thought that ability of using bedside ultrasound was important, and the corresponding mastery rate was only 3.8%(17/447); 77.4%(346/447) of general practitioners believed that CPR machines was important, while the available rate of CPR machines in primary health care institutions was only 16.0%(27/169).Conclusion:The GPs in southern Zhejiang province have a good grasp of cardiopulmonary resuscitation skills, but have a low mastery rate of first-aid skills such as electrical defibrillation, tracheal intubation, and emergency rescue capabilities, which are quite different from their perceived importance evaluation.
7.Construction and practice of remote intervention program for clinical nurses' neck, shoulder and low back pain based on Omaha system
Weige SUN ; Zhantao JIAO ; Ying HE ; Limei TANG ; Haijiao ZHANG ; Xiuwu LI ; Lei SHI ; Suzhai TIAN
Chinese Journal of Modern Nursing 2021;27(32):4380-4385
Objective:To construct an Omaha system-based remote intervention program for clinical nurses' neck, shoulder and low back pain and evaluate its effect.Methods:From July to October 2020, 94 nurses with neck, shoulder and low back pain in a Class Ⅲ hospital were randomly selected by ward. Using the envelope method, nurses were randomly divided into the intervention group and the control group, with 47 cases in each group, among them, the intervention group dropped 1 and the remaining 46 persons, the control group dropped 4 and the remaining 43 persons. The intervention group conducted a remote intervention program (using Omaha system as the theoretical framework, and using literature review, semi-structured interviews and expert consultation to construct a remote intervention program for clinical nurses' neck, shoulder and low back pain) . The control group used conventional guidance. The General Information Questionnaire, Exercise Compliance Questionnaire, Knowledge-Behavior-Symptoms (K-B-S) and Visual Analog Scale (VAS) were used to evaluate the intervention effect.Results:The exercise compliance of nurses in the intervention group was 78.26% (36/46) and that in the control group was 39.53% (17/43) , the difference was statistically significant ( P<0.01) . After 6 weeks of intervention, the nurses' cognitive and behavior scores in the intervention group were higher than those in the control group, and the difference was statistically significant ( P<0.05) . There was no statistically significant difference in the symptom score between the two groups ( P>0.05) . The VAS score and frequency of neck, shoulder and low back pain were lower than those of the control group, and the difference was statistically significant ( P<0.05) . Conclusions:Based on Omaha system, the remote intervention program for the clinical nurses' neck, shoulder and low back pain is safe, scientific and theoretical. It can improve cognition and behavior of neck, shoulder and low back pain nurses, reduce the intensity and frequency of pain, and the nurses have good compliance.
8. Study on urine metabolomics of left-behind children with vitamin D deficiency under 1 year old in Zunyi area based on nuclear magnetic resonance
Li LEI ; Yu CHENG ; Yanan SONG ; Yunfeng XIANG ; Hongjiao JIN ; Huiling SONG ; Enjin GOU ; Qing LI ; Xuqin WANG ; Limei LUO ; Yong LIN ; Bo HUANG
Chinese Journal of Applied Clinical Pediatrics 2019;34(20):1565-1569
Objective:
To explore the characteristic changes in urinary metabolites in left-behind children with vitamin D deficiency under 1 year old in Zunyi area by metabolomic nuclear magnetic resonance (NMR) in order to provide new biomarkers for early diagnosis of vitamin D deficiency.
Methods:
From January to August 2018, blood tests and urine collection were carried out on the left-behind children under 1 year old in Fenggang county, Bozhou district and Zheng′an county under Zunyi city by stratified sampling.Forty children diagnosed as a vitamin D deficiency were selected as a vitamin D deficiency group, and 40 children with normal urine test were selected as a healthy control group.For urine sampling, SIMCA-P+ software was applied to analyze the integral value of hydrogen spectrogram by principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) was used to distinguish the difference in urine metabolites between two groups of the left-behind children.Orthogonal partial least squares discriminant analysis (OPLS-DA) was used to screen different metabolites.
Results:
The serum level of 25-hydroxy vitamin D[25-(OH)D][(32.0±3.6) nmol/L ] in the healthy control group was higher than that in the vitamin D deficiency group[(15.8±2.3) nmol/L], and the difference was statistically significant (
9.Effects of modified Siwutang aqueous extract on mobilization and plantation of bone marrow cells in mice after acute myocardial infarction
Yuying WANG ; Ying WE ; Jianghong LEI ; Limei YU
The Journal of Practical Medicine 2017;33(7):1083-1086
Objective To investigate the effects of Modified Siwutang aqueous extract (mSWT) on bone marrow cell mobilization and plantation in mice after acute myocardial infarction (AMI).Methods The AMI model was established by ligating the left anterior descending artery in Kunming mice.Bone marrow cells were marked by injection of DAPI into the cavitas medullaris of shin bones.Mice were administered with mSWT 60 mg/kg by intragastric administration once a day after surgery.After haematoxylin-eosin and immunofluorescent staining,the plantation of bone marrow cells in AMI area and microvessel density were detected by histopathological assay.The EPCs proportion of peripheral blood was measured by flow cytometry.Results Compared with model mice,infarct size obviously was decreased after mSWT 60 mg/kg treatment,with EPCs ratio increased significantly.Inflammatory cell infiltration of myocardium was much less.Myocardium cellular degeneration and necrosis,fibrosis were reduced,which survival cardiac muscle tissue was increased.DAPI positive cells of plantation and survive were found in AMI region of mSWT group.The number of positive cells were increased in mSWT group than that of model group.There were lot of microvessels of vWF positive expresseion in mSWT than model group.Conclusion:mSWT significantly improved histopathology of AMI mice.The mechanism may be involved in moved bone marrow cells,homed to AMI area and promote angiogenesis.

Result Analysis
Print
Save
E-mail