In recent years, with the exploration and development of machine learning algorithms in the medical scenario, their potential for application in clinical diagnosis and treatment has been gradually explored. Image-based machine learning algorithms have made a lot of progress in urological cancer-related research, and have been proven to have a positive effect on the diagnosis, treatment and prognosis of urological cancer. Despite the great impact of machine learning algorithms clinically, they are still in the exploratory stage, with many deficiencies and limitations.

Objective: To investigate independent risk factors for lower extremity amputation (LEA) in hospitalized patients with diabetic foot ulcers ( DFUs) . Methods: A multicenter retrospective analysis was conducted on the clinical data of 329 DFUs hospitalized patients with diabetic foot ulcers from four general hospitals across the na⁃tion. A multivariate Logistic regression model was constructed , and prediction analysis was performed using R 4. 2. 1 . The discriminative ability of the model was assessed using receiver operating characteristic curves , while calibration accuracy and clinical applicability were evaluated via calibration curves and decision curve analysis. Results : The study revealed that patients with higher education backgrounds showed lower disease severity (Wagnergrade) (Z = - 4. 331 , P < 0. 05) . A history of amputation , pre⁃existing lower extremity vascular disease , abnormal dorsalis pedis artery pulsation , and a history of coronary heart disease were significantly associated with the severity of DFUs , resulting in higher Wagner scores (P < 0. 05) . In the amputation prognosis analysis , prolonged duration of diabetes and elevated white blood cell count were positively correlated with amputation risk ( both P < 0. 01) .Multivariable regression identified non⁃higher education , low hemoglobin levels , decreased total cholesterol , and abnormally elevated platelet counts as independent risk factors for high Wagner grades ( ≥ grade 3 ) ( all P <0. 05) . The integrated predictive model incorporating these factors demonstrated strong discriminative performance ,with an area under curve of 0. 880 (95% CI: 0. 801 - 0. 960) . The calibration curve slope approached the ideal value , and decision curve analysis confirmed the model ′s clinical net benefit within a threshold probability range of 10% - 65% . Conclusion Lower education level , poor baseline nutritional status , infection , hypercoagulability ,and underlying vascular diseases collectively constitute key factors contributing to elevated amputation risk in DFUs patients. The developed predictive model exhibits high accuracy and may assist clinicians in formulating individual⁃ized intervention strategies.

In recent years, with the exploration and development of machine learning algorithms in the medical scenario, their potential for application in clinical diagnosis and treatment has been gradually explored. Image-based machine learning algorithms have made a lot of progress in urological cancer-related research, and have been proven to have a positive effect on the diagnosis, treatment and prognosis of urological cancer. Despite the great impact of machine learning algorithms clinically, they are still in the exploratory stage, with many deficiencies and limitations.

Metabolic dysfunction-associated fatty liver disease （MAFLD） is a common chronic liver disease in clinical practice， and macrophages are directly involved in the development， progression， and prognosis of MAFLD. Studies have confirmed that glucose metabolic reprogramming in macrophages directly affects immune function， which in turn affects the local inflammatory environment of liver and hepatocyte metabolism. This article reviews the changes in glucose metabolism of macrophages and the corresponding key molecules in the pathogenesis of MAFLD， in order to provide new targets and strategies for the prevention and treatment of MAFLD in the future.

Objective To investigate the causal relationship between gut microbiota and obstruc-tive sleep apnea syndrome(OSA)using a two-sample bidirectional Mendelian randomization(MR)approach.Methods Eligible single nucleotide polymorphisms(SNPs)were selected from genome-wide association study(GWAS)databases as instrumental variables.A bidirectional MR analysis was conducted to evaluate the causal effects between gut microbiota and OSA.Various statistical methods,including the inverse variance weighted(IVW)method,MR-Egger regression,the weighted model method,and the weighted median method,were employed for association assessment.The MR pleiot-ropy residual sum and outlier(MR-PRESSO)test,along with Cochran's Q test and the leave-one-out cross-validation method,were used to assess heterogeneity and pleiotropy.Results According to the IVW method analysis,an increased abundance of the genus Faecalibacterium(sp002397985)(OR=0.847,95％CI,0.719 to 0.997,P=0.046)was associated with a reduced risk of OSA.Conversely,increased abundances of the genera Bacteroides(OR=1.075,95％CI,1.016 to 1.138,P=0.012),Haemophilus(sp001679485)(OR=1.106,95％CI,1.016 to 1.203,P=0.021),Streptococcus(OR=1.168,95％CI,1.036 to 1.316,P=0.011),and Blautia(sp002159835)(OR=1.169,95％CI,1.035 to 1.319,P=0.012)were associated with an elevated risk of OSA.The reverse MR analysis revealed no significant association between the risk of OSA and the abundance of gut microbiota.The results of Cochran's Q test,MR-Egger test,and MR-PRESSO test indicated no het-erogeneity or horizontal pleiotropy(P＞0.05).Conclusion Causal relationships exist between the five genera(Faecalibacterium,Bacteroides,Haemophilus,Streptococcus,and Blautia)and the risk of OSA.

Objective:To investigate the expulsion rate of GyneFix postpartum intrauterine device (PPIUD) placed immediately after cesarean section within one year and its influencing factors.Methods:A prospective cohort study was conducted. Women who volunteered to use a GyneFix PPIUD placed immediately after cesarean section (within 10 min after placenta delivery) for postpartum contraception were recruited from September 2017 to November 2020. The relevant information was collected through questionnaires before, during and 24 h after cesarean section. Outpatient follow-up was conducted at 42 d, 3 months, 6 months and 12 months after delivery to obtain information on expulsion of GyneFix PPIUD and unwanted pregnancy. Life table and Cox regression model were used to analyze the cumulative expulsion rate and related influencing factors.Results:A total of 470 subjects were recruited and 461 (98%) subjects were eligible for this study. The cumulative expulsion rate of GyneFix PPIUD within one year after cesarean section was 8.4% (95% CI: 7.0%-9.8%). Multivariate Cox regression analysis showed that women aged >35 years had significantly lower risk of PPIUD expulsion than those aged <25 years ( HR=0.16, 95% CI: 0.04-0.64). The risk of GyneFix PPIUD was not statistically significantly associated with cesarean section history and breastfeeding mode (all P>0.05). Nevertheless, this risk was statistically significant between hospitals. The Pearl index of contraceptive failure of the device was 2.37 (95% CI: 1.09-4.50) per 100 person-years. The rate of contraceptive failure was not associated with maternal age, breastfeeding mode, and history of cesarean delivery (all P>0.05). Conclusion:The one-year cumulative expulsion rate of GyneFix PPIUD placed immediately after cesarean section is 8.4%. Young mothers were at a higher risk of expulsion than their older counterparts. The device users should be counseled regarding the signs of expulsion. In case of expulsion, women should be offered reinsertion or other contraceptive methods. The training of service skills of GyneFix PPIUD should be strengthened in order to mitigate the risk of the device expulsion.

【Objective】 To establish a risk model for predicting spontaneous rupture bleeding of renal angiomyolipoma (RAML) in order to better assess and deal with the risk. 【Methods】 The information of 436 RAML patients diagnosed during Jan.2018 and Dec.2022 was retrospectively analyzed.According to the inclusion and exclusion criteria, 216 patients were included and divided into the rupture bleeding group (n=35) and non-rupture bleeding group (n=181).The factors influencing spontaneous rupture bleeding were identified using univariate and multivariate analysis, and a nomogram was constructed accordingly with R language.The nomogram was evaluated using Calibration curve and area under the receiver operator characteristic curve (AUC). 【Results】 It was found that clinical manifestations, tumor diameter, tumor convexity, tumor blood supply, and tuberous sclerosis complex (TSC) were significantly correlated with rupture bleeding.The Calibration curve fitted well with the nomogram.The AUC was 0.956 (95%CI: 0.856-0.943), indicating that the nomogram had good statistical performance. 【Conclusion】 The model can effectively predict the risk of spontaneous rupture bleeding of renal angiomyolipoma.

OBJECTIVE To explore the effect mechanism of Eucommia ulmoides on improving postpartum depression in rats. METHODS Pregnant rats were randomly divided into normal group， postpartum depression group， and low-dose and high-dose groups of E. ulmoides （1.34， 2.68 g/kg， calculated by crude drug）， with 10 rats in each group. Except for the normal group， the rats in other groups suffered from fear stress to induce postpartum depression model during pregnancy； at the same time of modeling， the administration groups were given relevant medicine intragastrically， while the normal group and postpartum depression group were given physiological saline intragastrically for 21 days. Postpartum behaviors of rats during the experiment were assessed using the open field test， Morris water maze test and sucrose preference test. Additionally， the levels of corticosterone （CORT） in serum， corticotropin releasing factor （CRF） and urocortin （UCN） in hypothalamus， and adrenocorticotropic hormone （ACTH） in hypophysis were detected； meanwhile， the protein expressions of CRF receptor 1 （CRFR1）， CRFR2， and voltage-dependent anion channel 1 （VDAC1） in hippocampal tissue were measured； the proportions of apoptotic cells and JC-1 high potential cells in hippocampal tissue were determined， and the morphology of hippocampal tissue was observed. RESULTS Compared with postpartum depression group， the high-dose group of E. ulmoides showed improvements in appetite， mental state， and hair color in rats； their body weight had increased； the scores of vertical movement， horizontal movement and self-sorting significantly increased； from the 2ed to 4th day avoidance latency significantly shortened， and the times of crossing the platform and the time of crossing the platform Δ 基金项目国家自然科学基金青年基金项目（No.82204789） significantly increased/prolonged （P＜0.05）； the ratio of glucose and water consumption significantly increased at 20 days of pregnancy and 30 days postpartum （P＜0.05）； the levels of CRF， UCN， ACTH and CORT， phagocytic rate， protein expressions of CRFR2 and VDAC1， and the proportion of apoptosis cells in hippocampal tissue were decreased significantly （P＜0.05）； the proportion of JC-1 high potential cells significantly increased （P＜0.05）， and the phenomenon of edema around neuronal cells was significantly improved. CONCLUSIONS E. ulmoides can improve postpartum depression by inhibiting excessive activation of hypothalamic-pituitary-adrenal axis， decreasing the expression of CRFR2， thereby inhibiting the expression of VDAC1， and decreasing the apoptosis of neuronal cells.

OBJECTIVE To explore the effect mechanism of Eucommia ulmoides on improving postpartum depression in rats. METHODS Pregnant rats were randomly divided into normal group， postpartum depression group， and low-dose and high-dose groups of E. ulmoides （1.34， 2.68 g/kg， calculated by crude drug）， with 10 rats in each group. Except for the normal group， the rats in other groups suffered from fear stress to induce postpartum depression model during pregnancy； at the same time of modeling， the administration groups were given relevant medicine intragastrically， while the normal group and postpartum depression group were given physiological saline intragastrically for 21 days. Postpartum behaviors of rats during the experiment were assessed using the open field test， Morris water maze test and sucrose preference test. Additionally， the levels of corticosterone （CORT） in serum， corticotropin releasing factor （CRF） and urocortin （UCN） in hypothalamus， and adrenocorticotropic hormone （ACTH） in hypophysis were detected； meanwhile， the protein expressions of CRF receptor 1 （CRFR1）， CRFR2， and voltage-dependent anion channel 1 （VDAC1） in hippocampal tissue were measured； the proportions of apoptotic cells and JC-1 high potential cells in hippocampal tissue were determined， and the morphology of hippocampal tissue was observed. RESULTS Compared with postpartum depression group， the high-dose group of E. ulmoides showed improvements in appetite， mental state， and hair color in rats； their body weight had increased； the scores of vertical movement， horizontal movement and self-sorting significantly increased； from the 2ed to 4th day avoidance latency significantly shortened， and the times of crossing the platform and the time of crossing the platform Δ 基金项目国家自然科学基金青年基金项目（No.82204789） significantly increased/prolonged （P＜0.05）； the ratio of glucose and water consumption significantly increased at 20 days of pregnancy and 30 days postpartum （P＜0.05）； the levels of CRF， UCN， ACTH and CORT， phagocytic rate， protein expressions of CRFR2 and VDAC1， and the proportion of apoptosis cells in hippocampal tissue were decreased significantly （P＜0.05）； the proportion of JC-1 high potential cells significantly increased （P＜0.05）， and the phenomenon of edema around neuronal cells was significantly improved. CONCLUSIONS E. ulmoides can improve postpartum depression by inhibiting excessive activation of hypothalamic-pituitary-adrenal axis， decreasing the expression of CRFR2， thereby inhibiting the expression of VDAC1， and decreasing the apoptosis of neuronal cells.

Orchitis is a common male genitourinary disorder that significantly impacts patients' life quality.Current treatment strategies have certain limitations and side effects.Ongoing therapeutic strategies focus on the interactions and regulatory networks among pathways and factors involved in the progression of orchitis.The targeted pharmacological agents include inflammatory pathways (p38MAPK, NF-κB, PI3K/Akt), cytokines (TNF-α, IL-6), and the nitric oxide synthase (NOS) system.However, these studies are currently at the animal research stage, and further clinical investigations are necessary to validate their efficacy and safety before clinical use.This article reviews the preclinical animal studies on new treatment methods of orchitis from the aspects of autoimmunity and exogenous microorganism induction, including ketotifen furmarate, aspirin, L-NAME, activin A, cortisol, melatonin, methane, long non-coding RNA MEG3, Abaloparatide, recombinant type Ⅰ interferon, and so on.