BackgroundEarly detection of ovarian aging is of huge importance, although no ideal marker or acknowledged evaluation system exists. The purpose of this study was to develop a better prediction model to assess and quantify ovarian reserve using machine learning methods.MethodsThis is a multicenter, nationwide population-based study including a total of 1,020 healthy women. For these healthy women, their ovarian reserve was quantified in the form of ovarian age, which was assumed equal to their chronological age, and least absolute shrinkage and selection operator (LASSO) regression was used to select features to construct models. Seven machine learning methods, namely artificial neural network (ANN), support vector machine (SVM), generalized linear model (GLM), K-nearest neighbors regression (KNN), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were applied to construct prediction models separately. Pearson’s correlation coefficient (PCC), mean absolute error (MAE), and mean squared error (MSE) were used to compare the efficiency and stability of these models.ResultsAnti-Müllerian hormone (AMH) and antral follicle count (AFC) were detected to have the highest absolute PCC values of 0.45 and 0.43 with age and held similar age distribution curves. The LightGBM model was thought to be the most suitable model for ovarian age after ranking analysis, combining PCC, MAE, and MSE values. The LightGBM model obtained PCC values of 0.82, 0.56, and 0.70 for the training set, the test set, and the entire dataset, respectively. The LightGBM method still held the lowest MAE and cross-validated MSE values. Further, in two different age groups (20–35 and >35 years), the LightGBM model also obtained the lowest MAE value of 2.88 for women between the ages of 20 and 35 years and the second lowest MAE value of 5.12 for women over the age of 35 years.ConclusionMachine learning methods combining multi-features were reliable in assessing and quantifying ovarian reserve, and the LightGBM method turned out to be the approach with the best result, especially in the child-bearing age group of 20 to 35 years.

IntroductionInsulin resistance (IR) may play a central role in the pathophysiology of polycystic ovary syndrome (PCOS). Controlled ovarian stimulation (COS) in PCOS women in the setting of assisted reproductive technology (ART) is always a challenge for clinicians. However, it remains unclear whether IR in women with PCOS correlates with reduced ovarian sensitivity to exogenous gonadotropin (Gn). This study aimed to explore the association between homeostasis model assessment of insulin resistance (HOMA-IR) and ovarian sensitivity index (OSI).MethodsIn this retrospective cohort study, we explored the association between Ln HOMA-IR and Ln OSI based on smoothing splines generated by generalized additive model (GAM). Then the correlation between HOMA-IR and OSI was further tested with a multivariable linear regression model and subgroup analysis.Results1508 women with PCOS aged 20-39 years undergoing their first oocyte retrieval cycle were included consecutively between 2018 until 2022. We observed a negative association between Ln HOMA-IR and Ln OSI by using smoothing splines. In multivariable linear regression analysis, the inverse association between Ln HOMA-IR and Ln OSI was still found in PCOS women after adjustment for potential confounders (β = -0.18, 95% CI -0.25, -0.11). Compared with patients with the lowest tertile of HOMA-IR, those who had the highest tertile of HOMA-IR had lower OSI values (β = -0.25, 95% CI -0.36, -0.15).DiscussionOur study provided evidence for the inverse correlation between IR and the ovarian sensitivity during COS in PCOS women. Herein, we proposed new insights for individualized manipulation in PCOS patients with IR undergoing ART.

BackgroundThe optimal first-line immune checkpoint inhibitor (ICI) treatment strategy for metastatic or early triple-negative breast cancer (TNBC) has not yet been determined as a result of various randomized controlled trials (RCTs). The purpose of this study was to compare the efficacy and safety of ICIs in patients with metastatic or early TNBC.MethodsRCTs comparing the efficacy and safety of ICIs in patients with TNBC were included in the studies. Based on PRISMA guidelines, we estimated pooled hazard ratios (HRs) and odds ratios (ORs) using random-effects models of Bayesian network meta-analysis. Primary outcomes were progression-free survival (PFS) and overall survival (OS). Secondary outcomes included pathologic complete response rate (pCR), grade ≥ 3 treatment-related adverse events (trAEs), immune-related adverse events (irAEs), and grade ≥ 3 irAEs.ResultsThe criteria for eligibility were met by a total of eight RCTs involving 4,589 patients with TNBC. When ICIs were used in patients without programmed death-ligand 1 (PD-L1) selection, there was a trend toward improved PFS, OS, and pCR, without significant differences. Pembrolizumab plus chemotherapy is superior to other treatment regimens in terms of survival for TNBC patients based on Bayesian ranking profiles. Subgroup analysis by PD-L1 positive population indicated similar results, and atezolizumab plus chemotherapy provided better survival outcomes. Among grade ≥ 3 trAEs and any grade irAEs, there was no statistically significant difference among different ICI agents. The combination of ICIs with chemotherapy was associated with a higher incidence of grade ≥ 3 irAEs. Based on rank probability, the ICI plus chemotherapy group was more likely to be associated with grade ≥ 3 trAEs, any grade irAEs, and grade ≥ 3 irAEs. Hypothyroidism and hyperthyroidism were the most frequent irAEs in patients receiving ICI.ConclusionsICI regimens had relatively greater efficacy and safety profile. Pembrolizumab plus chemotherapy and atezolizumab plus chemotherapy seem to be superior first-line treatments for intention-to-treat and PD-L1-positive TNBC patients, respectively. It may be useful for making clinical decisions to evaluate the efficacy and safety of different ICIs based on our study.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/, identifier CRD42022354643.

ObjectivesTo analyze clinical characteristics of the diabetic inpatients with foot ulcers and explore the risk factors of lower extremity amputation (LEA) in West China Hospital of Sichuan University.MethodsA retrospective analysis was performed based on the clinical data of the patients with diabetic foot ulcer (DFU) hospitalized in West China Hospital of Sichuan University from January 1, 2012 to December 31, 2020. The DFU patients were divided into three groups: non-amputation, minor amputation, and major amputation groups. The ordinal logistic regression analysis was used to identify the risk factors for LEA.Results992 diabetic patients (622 males and 370 females) with DFU were hospitalized in the Diabetic Foot Care Center of Sichuan University. Among them, 72 (7.3%) (55 minor amputations and 17 major amputations) cases experienced amputation, and 21(2.1%) refused amputation. Excluding the patients who refused amputation, the mean age and duration of diabetes of and HbA1c the 971 patients with DFU, were 65.1 ± 12.3 years old, 11.1 ± 7.6 years, and 8.6 ± 2.3% respectively. The patients in the major amputation group were older and had longer course of diabetes for a longer period of time than those in the non-amputation and minor amputation groups. Compared with the non-amputation patients (55.1%), more patients with amputation (minor amputation (63.5%) and major amputation (88.2%)) suffered from peripheral arterial disease (P=0.019). The amputated patients had statistically lower hemoglobin, serum albumin and ankle brachial index (ABI), but higher white blood cell, platelet counts, fibrinogen and C-reactive protein levels. The patients with amputation had a higher incidence of osteomyelitis (P = 0.006), foot gangrene (P < 0.001), and a history of prior amputations (P < 0.001) than those without amputation. Furthermore, a history of prior amputation (odds ratio 10.194; 95% CI, 2.646-39.279; P=0.001), foot gangrene (odds ratio 6.466; 95% CI, 1.576-26.539; P=0.010) and ABI (odds ratio 0.791; 95% CI, 0.639-0.980; P = 0.032) were significantly associated with LEAs.ConclusionsThe DFU inpatients with amputation were older with long duration of diabetes, poorly glycemic control, malnutrition, PAD, severe foot ulcers with infection. A history of prior amputation, foot gangrene and a low ABI level were the independent predictors of LEA. Multidisciplinary intervention for DFU is essential to avoid amputation of the diabetic patients with foot ulcer.

ObjectiveTo explore the relationship between folic acid supplementation and the recovery rate of gestational diabetes mellitus (GDM) in women with methylenetetrahydrofolate (MTHFR) 677 TT genotypes in mid-late pregnancy.Methods9, 096 pregnant women were recruited with their MTHFR gene genotyped. 5,111 women underwent a 75-g oral glucose tolerance test (OGTT) and 2,097 were confirmed with GDM. The association between MTHFR genotypes and GDM risk was estimated using logistic and log-binomial regression, with age and parity set as the covariates to control their confounding effects. Further assessment of GDM risk on glucose levels was done using the ANCOVA model. As an open-label intervention study, 53 GDM patients with TT genotype were prescribed 800μg/day of folic acid as the high-dose group, while 201 GDM patients were given 400μg/day as the standard-dose group at their 24-28 weeks of pregnancy. A rate ratio (RR) of GDM recovery was estimated at each available time point for both groups. The time-to-GDM persistence events were analyzed with the Kaplan-Meier method and Cox-regression model. The trend of glucose levels over time was estimated using the linear model.ResultsMTHFR 677 TT genotype has no significant association with the glucose levels and GDM risk, with an adjusted OR of 1.105 (95% CI 0.853, 1.431; p=0.452) and an adjusted PR of 1.050 (95% CI 0.906, 1.216; p=0.518) compared to the wildtype CC group. Patients in the high-dose group (n=38; 15 drop-outs; 40.69 days (95% CI 33.22, 48.15)) recovered from GDM approximately 27 days faster than those in the standard-dose group (n=133; 68 drop-outs; 68.09 days (95% CI 63.08, 73.11)). Concomitantly, the RR of GDM recovery rose and reached 1.247 (95% CI 1.026, 1.515) at 100 days of treatment with the standard-dose group as reference.ConclusionHigh-dose folic acid supplement intake in mid-late pregnancy is associated with faster GDM relief in patients with MTHFR 677 TT genotype compared to the standard dose, which would be served as a novel and low-cost alternative therapy for the treatment of GDM.

ObjectivePatients with pancreatic cancer (PC) have a poor prognosis. Radiotherapy (RT) is a standard palliative treatment in clinical practice, and there is no effective clinical prediction model to predict the prognosis of PC patients receiving radiotherapy. This study aimed to analyze PC’s clinical characteristics, find the factors affecting PC patients’ prognosis, and construct a visual Nomogram to predict overall survival (OS).MethodsSEER*Stat software was used to collect clinical data from the Surveillance, Epidemiology, and End Results (SEER) database of 3570 patients treated with RT. At the same time, the relevant clinical data of 115 patients were collected from the Affiliated Cancer Hospital of Zhengzhou University. The SEER database data were randomly divided into the training and internal validation cohorts in a 7:3 ratio, with all patients at The Affiliated Cancer Hospital of Zhengzhou University as the external validation cohort. The lasso regression was used to screen the relevant variables. All non-zero variables were included in the multivariate analysis. Multivariate Cox proportional risk regression analysis was used to determine the independent prognostic factors. The Kaplan-Meier(K-M) method was used to plot the survival curves for different treatments (surgery, RT, chemotherapy, and combination therapy) and calculate the median OS. The Nomogram was constructed to predict the survival rates at 1, 3, and 5 years, and the time-dependent receiver operating characteristic curves (ROC) were plotted with the calculated curves. Calculate the area under the curve (AUC), the Bootstrap method was used to plot the calibration curve, and the clinical efficacy of the prediction model was evaluated using decision curve analysis (DCA).ResultsThe median OS was 25.0, 18.0, 11.0, and 4.0 months in the surgery combined with chemoradiotherapy (SCRT), surgery combined with radiotherapy, chemoradiotherapy (CRT), and RT alone cohorts, respectively. Multivariate Cox regression analysis showed that age, N stage, M stage, chemotherapy, surgery, lymph node surgery, and Grade were independent prognostic factors for patients. Nomogram models were constructed to predict patients’ OS. 1-, 3-, and 5-year Time-dependent ROC curves were plotted, and AUC values were calculated. The results suggested that the AUCs were 0.77, 0.79, and 0.79 for the training cohort, 0.79, 0.82, and 0.81 for the internal validation cohort, and 0.73, 0.93, and 0.88 for the external validation cohort. The calibration curves Show that the model prediction probability is in high agreement with the actual observation probability, and the DCA curve shows a high net return.ConclusionSCRT significantly improves the OS of PC patients. We developed and validated a Nomogram to predict the OS of PC patients receiving RT.