Research on establishing gastric cancer lymph node metastasis prediction model based on machine learning and routine laboratory indicators / 实用医学杂志

Objective To establish a prediction model for lymph node metastasis(LNM)of gastric cancer based on routine laboratory indicators using machine learning algorithms.Methods This study collected data of 741 gastric cancer patients at Affiliated Hospital of Nantong University between January 2020 and January 2022 for model training and testing.Additionally,data of 102 gastric cancer patients between January 2023 and October 2023 were collected for model validation.XGBoost algorithm was used to calculate the importance of indicators and filter out a set of important indicators from 66 indicators.Five machine learning algorithms,including K-Nearest Neighbor,Support Vector Machine,Multilayer Perceptron,Random Forest and Adaboost,were constructed and trained for comparative analysis.Furthermore,the stability and accuracy of the model were further validated on the validation set.Results This study selected a set of important indicators composed of 9 routine laboratory indicators and trained the gastric cancer LNM prediction model,named V9.Additionally,through comparative experiments,it was found that the Adaboost algorithm based on the boosting strategy had the best performance,with evaluation metrics such as area under the curve,F1 score,accuracy,sensitivity,and specificity ranging from 0.833 to 0.968.The accuracy of the predictions on the validation set was 94.12%.Conclusion V9 was a gastric cancer LNM prediction model that has auxiliary clinical diagnostic value.It can be used to assess the risk of patients accurately and provide a basis for clinical decision-making.

Analysis of pathogenic bacteria distribution,laboratory indicators and prognosis in patients with bacterial ascites / 中国现代医生

Objective To investigate the clinical features,laboratory indicators and prognosis of patients with bacterial ascites,and to provide evidence for early clinical diagnosis and treatmen.Methods Clinical data of patients diagnosed with cirrhosis ascites from First Teaching Hospital of Tianjin University of Traditional Chinese Medicine from January 2019 to January 2022 were retrospectively analyzed.According to diagnostic criteria,they were divided into bacterial ascites group(n=24),spontaneous bacterial peritonitis group(n=20)and control group(n=26).The clinical features,laboratory indicators and prognosis of three groups were compared.Results Cirrhosis ascites caused by hepatitis B accounted for the highest proportion.The white blood cell count,neutrophil percentage,ascites white blood cell and polymorphonuclear leukocyte count of patients in bacterial ascites group were significantly higher than those in control group(P<0.05).Gram-positive bacteria was the main pathogens causing bacterial ascites,among which staphylococcus accounts for the highest proportion.Ten cases of bacterial ascites with symptoms of infection were treated with ascites culture and anti-infection therapy.The 14 patients without symptoms of infection were given different treatment according to the development of the disease,one patient died,and the other patients improved.Conclusion The number of patients with bacterial ascites was large,and the main pathogenic bacteria was Gram-positive coccus.The combination of clinical symptoms and laboratory indicators is beneficial to the early diagnosis of bacterial ascites and the decision of treatment.

Differences in clinical characteristics and laboratory parameters of primary and recurrent pterygium / 国际眼科杂志(Guoji Yanke Zazhi)

@#Pterygium is a common conjunctival disease which is mainly attributed to chronic ultraviolet light exposure. Previous studies have focused primarily on the clinical characteristics, surgical management and the pathogenesis of pterygium, but the differences between primary pterygium and recurrent pterygium have been less frequently documented. This article reviews the differences in clinical manifestations, histopathological findings, and laboratory parameters between primary pterygium and recurrent pterygium and summarises the latest findings regarding these differences.

O uso de indicadores da fase pré-analítica como ferramenta da gestão laboratorial / The use of indicators in the pre-analytical phase as a laboratory management tool

Introduction: Efficient laboratory services are the basis of modern health systems. Scientific innovations have contributed to substantial improvements in the laboratory environment, but errors still persist. These errors are classified as pre-analytical, analytical and post-analytical, according to the time of occurrence. Objective: To evaluate the frequency of pre-analytical errors in the clinical laboratory service of a military hospital. Methods: A total of 329,582 tests were performed in the clinical laboratory of Hospital Naval Marcílio Dias (HNMD) from August to October 2012, and pre-analytical errors were documented. Results: The most frequent cause of the observed pre-analytical errors was hemolysis (27.54%), followed by samples not received (25.43%) and insufficient sample volume (18.49%). The samples from the Integrated Home Care Service (SIAD) showed the highest frequency of errors (3.38%), followed by those from the inpatient (0.76%) and the outpatient departments (0.21%). Conclusion: Our study demonstrates the importance of managing laboratory pre-analytical quality in order to ensure service excellence...

Introdução: Serviços laboratoriais efetivos são a base dos sistemas de saúde modernos. Inovações científicas têm contribuído para melhorias substanciais no meio laboratorial, mas os erros ainda persistem. Esses erros são classificados como pré-analíticos, analíticos e pós-analíticos, dependendo do momento de sua ocorrência. Objetivo: Avaliar a frequência de erros pré-analíticos ocorridos no serviço de análises clínicas de um hospital militar. Métodos: Um total de 329.582 exames foram realizados no laboratório de análises clínicas do Hospital Naval Marcílio Dias no período de agosto a outubro de 2012, e os erros pré-analíticos documentados. Resultados: Os erros pré-analíticos mais observados foram decorrentes da hemólise (27,54%), seguidos de material não recebido (25,43%) e amostra insuficiente (18,49%). As amostras oriundas do Serviço Integrado de Atendimento Domiciliar (SIAD) foram as que apresentaram a maior frequência de erros (3,38%), seguidas pelo setor de pacientes internos (0,76%) e ambulatoriais (0,21%), respectivamente. Conclusão: Nosso estudo demonstra a importância da gestão da fase pré-analítica na garantia da qualidade laboratorial, de maneira a assegurar um serviço de excelência...

Analysis of application of common laboratory indexes in kidney diseases / 国际检验医学杂志

Objective To investigate the value of laboratory testing in kidney diseases and to assess whether these marks can predict the renal histological lesions for screening the best clinical test combination.Methods The main clinical data,pathological types and laboratory examination indexes in 117 patients with renal biopsy in our hospital from December 2010 to March 2014 were collected and graded according to the WHO renal pathological classification standard and the Katafuchi semi-quantitative score standard classification (Ⅰ,Ⅱ,Ⅲ,Ⅳ).The differences in serum CysC,urine NAG,urine alpha 1-MG,urine mAlb and 24 h urine total protein (24h-UTP)level were compared among the various groups and their relations with the glomerulus was analyzed;the correlation and the statistical significance of each index in different groups was analyzed.Results NAG,alpha 1-MG and CysC had statistical differences between in the grade Ⅳgroup and the gradeⅠ,Ⅱ,Ⅲ groups (P <0.05),24h-UTP and mAlb had significant correlation in reflecting the kidney diseases (r=0.565,P =0.000);NAG and alpha 1-MG also had significant correlation in reflec-ting renal tubular interstitial disease (r=0.509,P =0.000).Conclusion The detection results of various detection indicators when rising to a certain height can be used for judging the progression of the patients clinical and pathological condition,illustrating the serious condition of illness;at the same time according to the correlation among the indexes and the detection efficiency,three indi-cators of Cys C,mAlb,alpha 1 - MG are screened out for conducting the combination detection,the detection efficiency could be greatly improved.