Machine learning models predicts risk of proliferative lupus nephritis.

Objective: This study aims to develop and validate machine learning models to predict proliferative lupus nephritis (PLN) occurrence, offering a reliable diagnostic alternative when renal biopsy is not feasible or safe. Methods: This study retrospectively analyzed clinical and laboratory data from patients diagnosed with SLE and renal involvement who underwent renal biopsy at West China Hospital of Sichuan University between 2011 and 2021. We randomly assigned 70% of the patients to a training cohort and the remaining 30% to a test cohort. Various machine learning models were constructed on the training cohort, including generalized linear models (e.g., logistic regression, least absolute shrinkage and selection operator, ridge regression, and elastic net), support vector machines (linear and radial basis kernel functions), and decision tree models (e.g., classical decision tree, conditional inference tree, and random forest). Diagnostic performance was evaluated using ROC curves, calibration curves, and DCA for both cohorts. Furthermore, different machine learning models were compared to identify key and shared features, aiming to screen for potential PLN diagnostic markers. Results: Involving 1312 LN patients, with 780 PLN/NPLN cases analyzed. They were randomly divided into a training group (547 cases) and a testing group (233 cases). we developed nine machine learning models in the training group. Seven models demonstrated excellent discriminatory abilities in the testing cohort, random forest model showed the highest discriminatory ability (AUC: 0.880, 95% confidence interval(CI): 0.835-0.926). Logistic regression had the best calibration, while random forest exhibited the greatest clinical net benefit. By comparing features across various models, we confirmed the efficacy of traditional indicators like anti-dsDNA antibodies, complement levels, serum creatinine, and urinary red and white blood cells in predicting and distinguishing PLN. Additionally, we uncovered the potential value of previously controversial or underutilized indicators such as serum chloride, neutrophil percentage, serum cystatin C, hematocrit, urinary pH, blood routine red blood cells, and immunoglobulin M in predicting PLN. Conclusion: This study provides a comprehensive perspective on incorporating a broader range of biomarkers for diagnosing and predicting PLN. Additionally, it offers an ideal non-invasive diagnostic tool for SLE patients unable to undergo renal biopsy.

Study on the immunomodulatory mechanism of vitamin D in patients with unexplained recurrent spontaneous abortion.

Background: To investigate the mechanism of vitamin D level on the regulation of peripheral blood lymphocyte subsets and serum Th1/Th2 cytokines in patients with unexplained recurrent spontaneous abortion (URSA). Methods: Eighty female patients with URSA attending Sichuan Jinxin Xinan Women's and Children's Hospital from January 2020 to May 2021 were selected as the study group, and 30 age-matched women with a history of healthy deliveries were chosen as the control group, and peripheral blood lymphocyte subpopulations and serum Th1/Th2 cytokines of people with different levels of vitamin D were detected in the study group by flow cytometry, respectively. The results of immune factors before and after supplementation were analyzed in 40 of these patients with low vitamin D levels. The results of lymphoid subpopulations and Th1/Th2 cytokines in 19 patients with normal pregnancy before and after vitamin D supplementation and after normal pregnancy were also analyzed comparatively. Results: (1) Serum 25(OH)D in the study group was lower than in the control group; peripheral blood Th cells, B cells and NK cells in the study group were higher than in the control group; IL-2, TNF-α, IFN-γ and IL-6 in the study group were higher than in the control group, while IL-4 and IL-10 in the study group were lower than in the control group (P < 0.05). (2) Th cells, B cells and NK cells of URSA patients in the vitamin D low level group were higher than those in the vitamin D normal group; serum cytokines IL-2, TNF-α and IFN-γ of patients in the vitamin D low level group were higher than those in the vitamin D normal group (P < 0.05); (3) Th cells, B cells and NK cells in URSA patients after vitamin D supplementation were lower than before vitamin D supplementation; serum cytokines IL-2, TNF-α and IFN-γ after vitamin D supplementation were lower than before vitamin D supplementation, IL-4 and IL-10 after vitamin D supplementation were higher than before vitamin D supplementation (P < 0.05), and there was no significant difference in IL-6 before and after vitamin D supplementation. (4) Th cells, B cells and NK cells in patients with normal pregnancy after vitamin D supplementation and after pregnancy were lower than those before vitamin D supplementation; serum cytokines IL-2, TNF-α and IFN-γ after vitamin D supplementation and after pregnancy were lower than those before vitamin D supplementation, and serum cytokines IL-4 and IL-10 after vitamin D supplementation and after pregnancy were higher than those before vitamin D supplementation, TNF -α, IFN-γ after pregnancy were lower than after vitamin D supplementation (P < 0.05), IL-6 was not significantly different before and after vitamin D supplementation and after pregnancy. Conclusion: Vitamin D deficiency rate was high in URSA patients. Th、B、NK cells and IL-2, TNF-α, IFN-γ, IL-6 cytokines were high, while IL-6 and IL-10 were low in URSA patients. IL-2, TNF-α, IFN-γ cytokines and Th, B, NK cells were increased in vitamin D deficient URSA patients, and Vitamin D deficiency may be an important cause or aggravating factor of immune dysfunction in URSA patients. Vitamin D has an immunomodulatory effect on URSA patients, promoting successful pregnancy by down-regulating peripheral blood Th, B, and NK cells and IL-2, TNF-α, and IFN-γ cytokines, while up-regulating IL-4 and IL-10.

[Semen quality of infertile men carrying hepatitis B virus].

OBJECTIVE: To study the semen parameters of infertile men carrying hepatitis B virus (HBV) and the influence of HBV infection on semen quality. METHODS: We collected the semen samples from 782 infertility males aged 25－35 years old. According to the results of serological examinations, we divided the patients into groups A (HBsAg, HBeAb and HBcAb positive, n = 286), B (HBsAg, HBeAg and HBcAb positive, n = 230) and C (non-HBV control, n = 266), and comparatively analyzed the routine semen parameters, sperm acrosin activity, sperm DNA fragmentation index (DFI) and high DNA stainability (HDS) among the three groups of patients. RESULTS: Compared with the patients of groups B and C, those of group A showed markedly decreased sperm concentration (ï¼»88.20 ± 82.62ï¼½ and ï¼»89.29 ± 53.80ï¼½ vs ï¼»71.49 ± 60.03ï¼½ ×106/ml, P<0.05), progressively motile sperm (PMS) (ï¼»34.88 ± 15.60ï¼½% and ï¼»37.82 ± 13.63ï¼½% vs ï¼»30.70 ± 14.79ï¼½%, P<0.05), sperm motility (ï¼»45.77 ± 16.58ï¼½% and ï¼»48.16 ± 14.03ï¼½% vs ï¼»42.67 ± 17.23ï¼½%, P<0.05), sperm viability (ï¼»82.55 ± 7.55ï¼½% and ï¼»85.26 ± 6.39ï¼½% vs ï¼»81.07 ± 10.19ï¼½%, P>0.05) and morphologically normal sperm (MNS) (ï¼»6.93 ± 4.45ï¼½% and ï¼»7.27 ± 4.43ï¼½% vs ï¼»5.72 ± 3.47ï¼½%, P<0.05), with sperm concentration, PMS, sperm motility, sperm viability and MNS remarkably lower in group B than in C. Sperm acrosin activity was significantly reduced in group A in comparison with groups B and C (ï¼»57.07 ± 26.38ï¼½ vs ï¼»63.03 ± 28.75ï¼½ and ï¼»78.00 ± 33.49ï¼½ µIU/106, P<0.01), remarkably lower in group B than in C (P<0.01). The sperm DFI and HDS, however, were markedly higher in group A than in B (ï¼»14.79 ± 9.46ï¼½% vs ï¼»12.95 ± 7.29ï¼½% and ï¼»11.60 ± 5.98ï¼½%, P<0.05; ï¼»9.62 ± 6.20ï¼½% vs ï¼»8.43 ± 4.72ï¼½% and ï¼»8.41 ± 4.59ï¼½%, P<0.05), and both higher in group B than in C. CONCLUSIONS: Semen quality is lower in infertile men carrying HBV and therefore HBV infection is one of the causes of male infertility.