Objective Based on 25 indicators including immune factors, cell count classification, and smear results of the knee joint fluid, machine learning models were established to distinguish between osteoarthritis (OA) and rheumatoid arthritis (RA). Methods 100 OA and 40 RA patients scheduled for total knee arthroplasty were enrolled respectively. Each patient's knee joint fluid was collected preoperatively. Nucleated cells were counted and classified. The expression levels of immune factors, including tumor necrosis factor alpha (TNF-α), interleukin-1 beta (IL-1β), IL-6, IL-8, IL-15, matrix metalloproteinase 3 (MMP3), MMP9, MMP13, rheumatoid factor (RF), serum amyloid A (SAA), C-reactive protein (CRP), and others were measured. Smears and microscopic classification of all the immune factors were performed. Independent influencing factors for OA or RA were identified using univariate binary logistic regression, Lasso regression, and multivariate binary logistic regression. Based on the independent influencing factors, three machine learning models were constructed which are logistic regression, random forest, and support vector machine. Receiver operating characteristic curve (ROC), calibration curve and decision curve analysis (DCA) were used to evaluate and compare the models. Results A total of 5 indicators in the knee joint fluid were screened out to distinguish OA and RA, which were IL-1β(odds ratio(OR)=10.512, 95× confidence interval (95×CI) was 1.048-105.42, P=0.045), IL-6 (OR=1.007, 95×CI was 1.001-1.014, P=0.022), MMP9 (OR=3.202, 95×CI was 1.235-8.305, P=0.017), MMP13 (OR=1.002, 95× CI was 1-1.004, P=0.049), and RF (OR=1.091, 95×CI was 1.01-1.179, P=0.026). According to the results of ROC, calibration curve and DCA, the accuracy (0.979), sensitivity (0.98) and area under the curve (AUC, 0.996, 95×CI was 0.991-1) of the random forest model were the highest. It has good validity and feasibility, and its distinguishing ability is better than the other two models. Conclusion The machine learning model based on immune factors in the knee joint fluid holds significant value in distinguishing OA and RA. It provides an important reference for the clinical early differential diagnosis, prevention and treatment of OA and RA.
Humans ; Arthritis, Rheumatoid/metabolism* ; Machine Learning ; Male ; Female ; Middle Aged ; Aged ; Synovial Fluid/immunology* ; Osteoarthritis, Knee/metabolism* ; Knee Joint/metabolism* ; ROC Curve ; Diagnosis, Differential

OBJECTIVE To establish the quality standard of Kuipingning gastric floating tablets. METHODS Kuipingning gastric floating tablets were prepared and investigated in terms of property ，weight difference and friability. Crydalis yanhusuo was identified qualitatively by thin layer chromatography （TLC）method. High performance liquid chromatography method was used to determine the content of total anthraquinones in Rheum palmatum ，and set the content limit of total anthraquinones. The floating performance and release degree of the preparation were investigated ，and the release kinetic process was fitted. RESULTS Kuipingning gastric floating tablets prepared in this study were gray white to gray tablets with slight smell and bitter taste ；the weight difference and friability were all in line with relevant regulations ；the established TLC method possessed strong specificity and could accurately identify C. yanhusuo . The average content of total anthraquinones in R. palmatum was 17.95 mg/tablet，and its content limit would not be less than 14.36 mg/tablet. The initial floating time of the preparation was no more than 10 s，and the holding time was more than 8 h. The release kinetics process accorded with the Retger-Peppas release model. CONCLUSIONS The method established in this study shows good reliability ，stability and feasibility ，and can effectively control the quality of Kuipingning gastric floating tablets.

Objective To establish reference ranges of venous blood cell parameters in Lanzhou area ,through investigating 1 880 cases of healthy people .Methods Retrospective analysis method was adopted ,and changes of 26 venous blood cell parameters were observed by using Sysmex XE‐5000 automatic hematology analyzer .Results Some parameters ,including platelet(PLT) and hemo‐globin(Hb) ,were close to normal distribution ,while most of parameters were skewed distribution .In the 6 parameters of white blood cells ,except for percentage of lymphocyte and neutrophi ,the 95% CI of the rest of parameters had statistically significant differences between male and female(P<0 .05) .In the 8 parameters of red blood cell ,except for mean corpuscular haemoglobin con‐centration (MCHC) and standard deviation of red blood cell volume distribution width (RDWSD) ,the 95% CI of the rest of parame‐ters had statistically significant differences between male and female (P<0 .05) .The 95% CI of PLT related parameters and per‐centage of juvenile cells had no statistically significant differences between male and female (P>0 .05) .In some parameters ,there were significant differences between 95% CI observed in this study and reference ranges currently used .Conclusion There are sig‐nificant differences between 95% CI of these parameters and original reference ranges ,so the original reference ranges are lack of ac‐curacy and applicability ,which indicates that it is necessary to scientificlly and rationally establish reference ranges of blood cell in region .