BACKGROUND: Epidermal growth factor receptor (EGFR) sensitive mutation is one of the effective targets of targeted therapy for non-small cell lung cancer (NSCLC). However, due to the difficulty of obtaining some primary tissues and the economic factors in some underdeveloped areas, some patients cannot undergo traditional genetic testing. The aim of this study is to establish a machine learning (ML) model using non-invasive peripheral blood markers to explore the biomarkers closely related to EGFR mutation status in NSCLC and evaluate their potential prognostic value. METHODS: 2642 lung cancer patients who visited Jiangsu Cancer Hospital from November 2016 to May 2023 were retrospectively enrolled and finally 175 NSCLC patients with complete follow-up data were included in the study. The ML model was constructed based on peripheral blood indicators and divided into training set and test set according to the ratio of 8:2. Unsupervised learning algorithms were used for clustering blood features and mutual information method for feature selection, and an ensemble learning algorithm based on Shapley value was designed to calculate the contribution of each feature to the model prediction result. The receiver operating characteristic (ROC) curve was used to evaluate the predictive ability of the model. RESULTS: Through the feature extraction and contribution analysis of the predictive results of the interpretable ML model based on the Shapley value, the top ten indicators with the highest contribution were: pathological type, phosphorus, eosinophils, monocyte count, activated partial thromboplastin time, potassium, total bilirubin, sodium, eosinophil percentage, and total cholesterol. The area under the curve (AUC) of the model was 0.80. In addition, patients with hyponatremia and squamous cell carcinoma group had a poor prognosis (P<0.05). CONCLUSIONS The interpretable model constructed in this study provides a new approach for the prediction of EGFR mutation status in NSCLC patients, which provides a scientific basis for the diagnosis and treatment of patients who cannot undergo genetic testing.
Humans ; Carcinoma, Non-Small-Cell Lung/diagnosis* ; Machine Learning ; Lung Neoplasms/diagnosis* ; Male ; Female ; Mutation ; Middle Aged ; ErbB Receptors/genetics* ; Prognosis ; Aged ; Retrospective Studies ; Adult ; Biomarkers, Tumor/genetics*

Objective:To investigate the association between estimated cumulative low-density lipoprotein cholesterol (LDL-C) exposure and the severity of coronary artery disease and long-term adverse cardiovascular and cerebrovascular events (MACCE) in patients with acute coronary syndrome (ACS).Methods:The subjects were from the PROMISE study. This study was a prospective cohort study led by Fuwai Hospital, Chinese Academy of Medical Sciences, with participation from eight regional tertiary hospitals as sub-centers, and enrolled 18 701 patients with confirmed coronary heart disease between January 2015 and May 2019. Among them, 8 429 patients with ACS were included in this study. The estimated cumulative LDL-C exposure was calculated by multiplying LDL-C by age. Participants were then divided into four groups based on quartiles. Baseline data and coronary angiography data were collected, and participants were followed for 2 years. The primary endpoint was MACCE, which was composed of all-cause death, cardiac death, myocardial infarction, revascularization, and stroke. Spearman correlation analysis was used to estimate the correlation between cumulative LDL-C exposure and the severity of coronary artery disease. The differences in MACCE among the four groups were compared, and multivariate Cox regression was used to divide the estimated cumulative exposure LDL-C into two groups, three groups, and four groups to analyze its relationship with MACCE.Results:The 8 429 ACS patients included in the study had an age of (60.9±11.4) years, with 1 951(23.1%) females. Spearman correlation analysis revealed that estimated cumulative LDL-C exposure was positively associated with the preoperative SYNTAX score, three-vessel lesions disease, left main disease, and the number of target lesions (correlation coefficients r=0.14, 0.10, 0.04 and 0.03, respectively, with all P<0.05). The 2-year follow-up results indicated that the incidence rates of MACCE, all-cause death, cardiac death, myocardial infarction, and stroke in ACS patients grouped by different levels of estimated cumulative LDL-C exposure were statistically significant (all P<0.05). The results of the Cox multivariate regression analysis showed that when the estimated cumulative LDL-C exposure was treated as a continuous variable and analyzed in two, three, and four groups, with the lowest group as the reference, the risk of MACCE occurrence in the high-value group increased by 21% (95% CI 1.08-1.37, P=0.002), 24% (95% CI 1.07-1.43, P=0.004), and 21% (95% CI 1.02-1.43, P=0.025) respectively. Conclusions:A positive correlation was found between estimated cumulative LDL-C exposure and severity of coronary artery disease. High estimated cumulative LDL-C exposure level is a risk factor for MACCE in ACS patients within 2 years.

Objective:To investigate the effect of pre-pregnancy body mass index (BMI) on the cumulative live birth rate (CLBR) and perinatal outcomes in women with polycystic ovary syndrome (PCOS) undergoing first in vitro fertilization or intracytoplasmic sperm injection (IVF/ICSI).Methods:The clinical data of 1 013 patients with PCOS who received first IVF/ICSI treatment in Reproductive Medicine Center, Henan Provincial People′s Hospital from January 2017 to June 2020 were retrospectively analyzed. According to BMI China standard, they were divided into: normal weight group (18.5≤BMI<24.0 kg/m 2, 388 cases), overweight group (24.0≤BMI<28.0 kg/m 2, 367 cases), obese group (BMI≥28.0 kg/m 2, 258 cases). The effect of BMI on CLBR was analyzed by univariate analysis, multivariate logistic regression analysis and smooth curve fitting. The role of homeostasis model assessment of insulin resistance index (HOMA-IR) in the process of BMI on CLBR was analyzed by mediation analysis. Results:Among three groups, female age, basal level of follicle stimulating hormone, type of infertility and ovulation induction regimens were similar (all P>0.05). The infertility duration, basal testosterone level, HOMA-IR, the ovulation induction time and the total gonadotropin dosage increased with BMI (all P<0.01), anti-Müllerian hormone, basal luteinizing hormone level, the number of retrieved oocytes and available embryos decreased with BMI (all P<0.05). CLBR decreased with BMI increasing [84.08% (301/358) vs 74.26% (251/338) vs 71.88% (161/224); P<0.001]. The incidence of hypertensive disorder in pregnancy was highest in obese group, while premature rupture of membranes rate, premature delivery rate, low birth weight rate and macrosomia birth rate were the lowest in normal weight group. After adjusting for confounding factors, both smooth curve fitting and multiple logistic regression analysis revealed a significant trend: CLBR declined with increasing BMI ( OR=0.93, 95% CI: 0.89-0.97; P=0.002), with a reduction of 41% ( OR=0.59, 95% CI: 0.39-0.91; P=0.020) in overweight group, and a reduction of 48% ( OR=0.52, 95% CI: 0.32-0.83; P=0.010) in obese group. HOMA-IR mediated the effect of BMI on CLBR by 27.5% ( P<0.05). Conclusions:High BMI before IVF/ICSI in PCOS patients negatively impacts CLBR and raises maternal and infant risks during pregnancy and the perinatal period. 27.5% of the effect of BMI on CLBR is mediated by HOMA-IR. Thus, PCOS patients should manage their BMI and enhance insulin sensitivity prior to pregnancy.

Objective:To investigate the effect of pre-pregnancy body mass index (BMI) on the cumulative live birth rate (CLBR) and perinatal outcomes in women with polycystic ovary syndrome (PCOS) undergoing first in vitro fertilization or intracytoplasmic sperm injection (IVF/ICSI).Methods:The clinical data of 1 013 patients with PCOS who received first IVF/ICSI treatment in Reproductive Medicine Center, Henan Provincial People′s Hospital from January 2017 to June 2020 were retrospectively analyzed. According to BMI China standard, they were divided into: normal weight group (18.5≤BMI<24.0 kg/m 2, 388 cases), overweight group (24.0≤BMI<28.0 kg/m 2, 367 cases), obese group (BMI≥28.0 kg/m 2, 258 cases). The effect of BMI on CLBR was analyzed by univariate analysis, multivariate logistic regression analysis and smooth curve fitting. The role of homeostasis model assessment of insulin resistance index (HOMA-IR) in the process of BMI on CLBR was analyzed by mediation analysis. Results:Among three groups, female age, basal level of follicle stimulating hormone, type of infertility and ovulation induction regimens were similar (all P>0.05). The infertility duration, basal testosterone level, HOMA-IR, the ovulation induction time and the total gonadotropin dosage increased with BMI (all P<0.01), anti-Müllerian hormone, basal luteinizing hormone level, the number of retrieved oocytes and available embryos decreased with BMI (all P<0.05). CLBR decreased with BMI increasing [84.08% (301/358) vs 74.26% (251/338) vs 71.88% (161/224); P<0.001]. The incidence of hypertensive disorder in pregnancy was highest in obese group, while premature rupture of membranes rate, premature delivery rate, low birth weight rate and macrosomia birth rate were the lowest in normal weight group. After adjusting for confounding factors, both smooth curve fitting and multiple logistic regression analysis revealed a significant trend: CLBR declined with increasing BMI ( OR=0.93, 95% CI: 0.89-0.97; P=0.002), with a reduction of 41% ( OR=0.59, 95% CI: 0.39-0.91; P=0.020) in overweight group, and a reduction of 48% ( OR=0.52, 95% CI: 0.32-0.83; P=0.010) in obese group. HOMA-IR mediated the effect of BMI on CLBR by 27.5% ( P<0.05). Conclusions:High BMI before IVF/ICSI in PCOS patients negatively impacts CLBR and raises maternal and infant risks during pregnancy and the perinatal period. 27.5% of the effect of BMI on CLBR is mediated by HOMA-IR. Thus, PCOS patients should manage their BMI and enhance insulin sensitivity prior to pregnancy.

Objective:To investigate the association between estimated cumulative low-density lipoprotein cholesterol (LDL-C) exposure and the severity of coronary artery disease and long-term adverse cardiovascular and cerebrovascular events (MACCE) in patients with acute coronary syndrome (ACS).Methods:The subjects were from the PROMISE study. This study was a prospective cohort study led by Fuwai Hospital, Chinese Academy of Medical Sciences, with participation from eight regional tertiary hospitals as sub-centers, and enrolled 18 701 patients with confirmed coronary heart disease between January 2015 and May 2019. Among them, 8 429 patients with ACS were included in this study. The estimated cumulative LDL-C exposure was calculated by multiplying LDL-C by age. Participants were then divided into four groups based on quartiles. Baseline data and coronary angiography data were collected, and participants were followed for 2 years. The primary endpoint was MACCE, which was composed of all-cause death, cardiac death, myocardial infarction, revascularization, and stroke. Spearman correlation analysis was used to estimate the correlation between cumulative LDL-C exposure and the severity of coronary artery disease. The differences in MACCE among the four groups were compared, and multivariate Cox regression was used to divide the estimated cumulative exposure LDL-C into two groups, three groups, and four groups to analyze its relationship with MACCE.Results:The 8 429 ACS patients included in the study had an age of (60.9±11.4) years, with 1 951(23.1%) females. Spearman correlation analysis revealed that estimated cumulative LDL-C exposure was positively associated with the preoperative SYNTAX score, three-vessel lesions disease, left main disease, and the number of target lesions (correlation coefficients r=0.14, 0.10, 0.04 and 0.03, respectively, with all P<0.05). The 2-year follow-up results indicated that the incidence rates of MACCE, all-cause death, cardiac death, myocardial infarction, and stroke in ACS patients grouped by different levels of estimated cumulative LDL-C exposure were statistically significant (all P<0.05). The results of the Cox multivariate regression analysis showed that when the estimated cumulative LDL-C exposure was treated as a continuous variable and analyzed in two, three, and four groups, with the lowest group as the reference, the risk of MACCE occurrence in the high-value group increased by 21% (95% CI 1.08-1.37, P=0.002), 24% (95% CI 1.07-1.43, P=0.004), and 21% (95% CI 1.02-1.43, P=0.025) respectively. Conclusions:A positive correlation was found between estimated cumulative LDL-C exposure and severity of coronary artery disease. High estimated cumulative LDL-C exposure level is a risk factor for MACCE in ACS patients within 2 years.

Objective:To investigate the impact of the progesterone concentration on human chorionic gonadotropin (hCG) trigger day in fresh cycles versus thawed transfer cycles (the freeze-all strategy) with an antagonist protocol, and to compare the differences in clinical outcomes.Methods:This retrospective cohort study included a total of 2 165 cycles conducted at Henan Provincial People′s Hospital with cleavage-stage embryo (at least one top-quality) transfer between January 2017 and December 2023, with serum progesterone levels on hCG trigger day all≤6.34 nmol/L (i.e. 2 ng/ml). Multivariate logsitic regression analysis and curve fitting were performed based on different serum progesterone levels on hCG trigger day [≤3.17 nmol/L (i.e. 1 ng/ml) or 1-2 ng/ml].Results:Multivariate regression analysis, by using cycle type (either fresh or frozen-thawed cycle) as the exposure variable, showed that the clinical pregnancy rate (≤1 ng/ml: OR=0.93, 95% CI: 0.75-1.14; 1-2 ng/ml: OR=1.05, 95% CI: 0.58-1.87) and live birth rate (≤1 ng/ml: OR=0.90, 95% CI: 0.71-1.13; 1-2 ng/ml: OR=1.53, 95% CI: 0.79-3.00) had no statistically significant differences in group of progesterone concentration ≤1 ng/ml or in group of 1-2 ng/ml. Using serum progesterone levels on hCG trigger day as a continuous variable for curve fitting analysis, the clinical pregnancy rate in fresh or thawed cycles showed no significant changes with increasing progesterone levels. Conclusions:In the antagonist protocol with cleavage-stage embryo transfer (at least one top-quality), when the serum progesterone level on hCG day is ≤2 ng/ml, there are no significant differences in clinical outcomes between thawed cycles and fresh cycles, including clinical pregnancy rate and live birth rate. Transferred in fresh cycles or choosing the freeze-all strategy could be selected based on the actual situation of the patients.

Objective:To explore the effect of different salt intake levels on clinical outcomes after the first embryo transfer in women undergoing assisted reproductive technology.Methods:This was a retrospective cohort study. A total of 163 patients with the first in vitro fertilization/intracytoplasmic sperm injection and embryo transfer from January 2021 to July 2021 in Reproductive Medical Center, Henan Provincial People's Hospital were recruited. The spot urine method was used to estimate the 24 h salt intake of patients, and all patients were divided into three groups based on their 25th and 75th percentiles: low-salt group (≤9.21 g, n=41), medium-salt group (9.22-13.31 g, n=81), and high-salt group (≥13.32 g, n=41). Baseline data and clinical outcomes were analyzed and compared among the three groups. Results:The rate of MII oocyte [72.7% (410/564)], and the rate of high-quality embryos [42.1% (109/259)] in the high-salt group were lower than those in the low-salt group [82.5% (461/559), P<0.05; 52.4% (154/294), P<0.05], the differences among the three groups were statistically significant ( P<0.001, P=0.048). The rate of normal cleavage [99.1% (568/573)] in the medium-salt group was higher than that in the low-salt group [96.1% (294/306), P<0.05], and the difference among the three groups was statistically significant ( P=0.003). After adjusting for potential confounding factors by using multivariate logistic regression, the clinical pregnancy rate ( OR=0.520, 95% CI: 0.221-1.221, P=0.133), the early miscarriage rate ( OR=1.226, 95% CI: 0.219-6.851, P=0.817), and the live birth rate ( OR=0.730, 95% CI: 0.323-1.647, P=0.448) in the medium-salt group, the clinical pregnancy rate ( OR=0.659, 95% CI: 0.246-1.762, P=0.406), the early miscarriage rate ( OR=1.080, 95% CI: 0.162-7.180, P=0.937), and the live birth rate ( OR=1.012, 95% CI: 0.396-2.588, P=0.980) in the high-salt group were comparable with the low-salt group (all P>0.05). Conclusion:High level of salt intake does not affect the clinical pregnancy outcomes of infertile women in their first transplantation cycle. However, it has an adverse effect on oocyte maturation, normal cleavage, and high-quality embryo formation.

Objective:To investigate the impact of hyperuricemia on the live birth rate per transfer cycle and the cumulative live birth rate per oocyte retrieval cycle in patients with polycystic ovary syndrome (PCOS) undergoing in vitro fertilization and embryo transfer (IVF-ET). Methods:A retrospective cohort study was conducted on data from 3 959 PCOS patients who received IVF-ET treatment at the Reproductive Centers of Henan Provincial People's Hospital and Jiangxi Provincial Maternal and Child Health Hospital between January 2016 and December 2021. The patients were divided into hyperuricemia group (>357 μmol/L, n=1 126) and normal uric acid group (≤357 μmol/L, n=2 833) based on their uric acid levels. Baseline data, clinical and laboratory indicators were compared between the two groups. Univariate and multivariate regression analyses were performed on factors influencing clinical outcomes. Multivariate logistic regression analysis was used to compare the live birth rate per transfer cycle and the cumulative live birth rate per oocyte retrieval cycle between the two groups, clarifying the impact of hyperuricemia on clinical outcomes in PCOS patients. Results:There were no significant differences between the two groups in terms of age, duration of infertility, baseline testosterone level, type of infertility, and the rate of unusable embryos (all P>0.05). Body mass index [BMI, (25.15±3.75) kg/m 2], fasting blood glucose [(4.99±0.80) mmol/L] and fasting insulin levels [17.19 (11.78, 25.30) mU/L] in hyperuricemia group were higher than those in normal uric acid group [(23.60±3.64) kg/m 2, P<0.001; (4.88±0.81) mmol/L, P<0.001;12.40 (8.59, 17.86) mU/L, P<0.001], while their baseline luteinizing hormone [7.62 (4.68, 11.18) U/L] and anti-Müllerian hormone [7.62 (5.34, 10.73) μg/L] levels were lower than those in normal uric acid group [7.88 (4.98, 11.91) U/L, P=0.024; 7.95 (5.49, 11.73) μg/L, P<0.001], with statistically significant differences. Multivariate logistic regression analysis indicated that female BMI, endometrial thickness on human chorionic gonadotropin (hCG) injection day, and the number of transferable embryos were factors influencing the live birth rate per transfer cycle ( OR=1.02, 95% CI: 1.00-1.04, P=0.044; OR=0.95, 95% CI: 0.92-0.97, P<0.001; OR=0.97, 95% CI: 0.95-0.99, P=0.006). Fasting blood glucose, endometrial thickness on hCG injection day, and the number of transferable embryos were factors influencing the cumulative live birth rate per oocyte retrieval cycle ( OR=1.14, 95% CI: 1.01-1.29, P=0.036; OR=0.92, 95% CI: 0.87-0.97, P=0.002; OR=0.70, 95% CI: 0.66-0.75, P<0.001). Compared with the normal uric acid group, the hyperuricemia group in PCOS patients had not a statistically signifcant decrease in the live birth rate per transfer cycle and the cumulative live birth rate per oocyte retrieval cycle ( OR=0.93, 95% CI: 0.72-1.19, P=0.548; OR=1.18, 95% CI: 0.87-1.60, P=0.300). Conclusion:Hyperuricemia does not affect the live birth rate per transfer cycle or the cumulative live birth rate per oocyte retrieval cycle in PCOS patients undergoing IVF-ET.

Objective:To explore the effect of different salt intake levels on clinical outcomes after the first embryo transfer in women undergoing assisted reproductive technology.Methods:This was a retrospective cohort study. A total of 163 patients with the first in vitro fertilization/intracytoplasmic sperm injection and embryo transfer from January 2021 to July 2021 in Reproductive Medical Center, Henan Provincial People's Hospital were recruited. The spot urine method was used to estimate the 24 h salt intake of patients, and all patients were divided into three groups based on their 25th and 75th percentiles: low-salt group (≤9.21 g, n=41), medium-salt group (9.22-13.31 g, n=81), and high-salt group (≥13.32 g, n=41). Baseline data and clinical outcomes were analyzed and compared among the three groups. Results:The rate of MII oocyte [72.7% (410/564)], and the rate of high-quality embryos [42.1% (109/259)] in the high-salt group were lower than those in the low-salt group [82.5% (461/559), P<0.05; 52.4% (154/294), P<0.05], the differences among the three groups were statistically significant ( P<0.001, P=0.048). The rate of normal cleavage [99.1% (568/573)] in the medium-salt group was higher than that in the low-salt group [96.1% (294/306), P<0.05], and the difference among the three groups was statistically significant ( P=0.003). After adjusting for potential confounding factors by using multivariate logistic regression, the clinical pregnancy rate ( OR=0.520, 95% CI: 0.221-1.221, P=0.133), the early miscarriage rate ( OR=1.226, 95% CI: 0.219-6.851, P=0.817), and the live birth rate ( OR=0.730, 95% CI: 0.323-1.647, P=0.448) in the medium-salt group, the clinical pregnancy rate ( OR=0.659, 95% CI: 0.246-1.762, P=0.406), the early miscarriage rate ( OR=1.080, 95% CI: 0.162-7.180, P=0.937), and the live birth rate ( OR=1.012, 95% CI: 0.396-2.588, P=0.980) in the high-salt group were comparable with the low-salt group (all P>0.05). Conclusion:High level of salt intake does not affect the clinical pregnancy outcomes of infertile women in their first transplantation cycle. However, it has an adverse effect on oocyte maturation, normal cleavage, and high-quality embryo formation.

Objective:To investigate the impact of hyperuricemia on the live birth rate per transfer cycle and the cumulative live birth rate per oocyte retrieval cycle in patients with polycystic ovary syndrome (PCOS) undergoing in vitro fertilization and embryo transfer (IVF-ET). Methods:A retrospective cohort study was conducted on data from 3 959 PCOS patients who received IVF-ET treatment at the Reproductive Centers of Henan Provincial People's Hospital and Jiangxi Provincial Maternal and Child Health Hospital between January 2016 and December 2021. The patients were divided into hyperuricemia group (>357 μmol/L, n=1 126) and normal uric acid group (≤357 μmol/L, n=2 833) based on their uric acid levels. Baseline data, clinical and laboratory indicators were compared between the two groups. Univariate and multivariate regression analyses were performed on factors influencing clinical outcomes. Multivariate logistic regression analysis was used to compare the live birth rate per transfer cycle and the cumulative live birth rate per oocyte retrieval cycle between the two groups, clarifying the impact of hyperuricemia on clinical outcomes in PCOS patients. Results:There were no significant differences between the two groups in terms of age, duration of infertility, baseline testosterone level, type of infertility, and the rate of unusable embryos (all P>0.05). Body mass index [BMI, (25.15±3.75) kg/m 2], fasting blood glucose [(4.99±0.80) mmol/L] and fasting insulin levels [17.19 (11.78, 25.30) mU/L] in hyperuricemia group were higher than those in normal uric acid group [(23.60±3.64) kg/m 2, P<0.001; (4.88±0.81) mmol/L, P<0.001;12.40 (8.59, 17.86) mU/L, P<0.001], while their baseline luteinizing hormone [7.62 (4.68, 11.18) U/L] and anti-Müllerian hormone [7.62 (5.34, 10.73) μg/L] levels were lower than those in normal uric acid group [7.88 (4.98, 11.91) U/L, P=0.024; 7.95 (5.49, 11.73) μg/L, P<0.001], with statistically significant differences. Multivariate logistic regression analysis indicated that female BMI, endometrial thickness on human chorionic gonadotropin (hCG) injection day, and the number of transferable embryos were factors influencing the live birth rate per transfer cycle ( OR=1.02, 95% CI: 1.00-1.04, P=0.044; OR=0.95, 95% CI: 0.92-0.97, P<0.001; OR=0.97, 95% CI: 0.95-0.99, P=0.006). Fasting blood glucose, endometrial thickness on hCG injection day, and the number of transferable embryos were factors influencing the cumulative live birth rate per oocyte retrieval cycle ( OR=1.14, 95% CI: 1.01-1.29, P=0.036; OR=0.92, 95% CI: 0.87-0.97, P=0.002; OR=0.70, 95% CI: 0.66-0.75, P<0.001). Compared with the normal uric acid group, the hyperuricemia group in PCOS patients had not a statistically signifcant decrease in the live birth rate per transfer cycle and the cumulative live birth rate per oocyte retrieval cycle ( OR=0.93, 95% CI: 0.72-1.19, P=0.548; OR=1.18, 95% CI: 0.87-1.60, P=0.300). Conclusion:Hyperuricemia does not affect the live birth rate per transfer cycle or the cumulative live birth rate per oocyte retrieval cycle in PCOS patients undergoing IVF-ET.