1.Mechanism of Yiqi Huoxue Therapy Regulating IL-33/ST2/IL-1RAP to Improve Nasal Mucosal Tissue Remodeling and Intervene in Allergic Rhinitis
Huan WANG ; Hongping LUO ; Meiya WANG ; Yuyin LIU ; Chenlin WANG ; Chao LIAO ; Fangqi LIANG ; Peizheng XIONG ; Li TIAN
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(14):298-307
ObjectiveTo explore the mechanism by which Qidan Yifei Tongqiao granules (QDYF) alleviate nasal mucosal remodeling in allergic rhinitis (AR) via the interleukin-33 (IL-33)/growth stimulation expressed gene 2 (ST2)/interleukin-1 receptor accessory protein (IL-1RAP) signaling pathway from the perspective of Qi-replenishing and blood-activating therapy. MethodsFirst, according to the previous network pharmacology results, this study predicted the potential mechanisms of QDYF in treating AR by screening key pathways, components, and targets. Molecular docking was performed via AutoDock and PyMOL 2.5.5. Subsequently, a rat model of ovalbumin (OVA)-induced AR was used for validation through in vivo experiments. Forty-eight rats were assigned into 6 groups: Control, model, low-dose QDYF (QDYF-L, 4.04 g·kg-1), medium-dose QDYF (QDYF-M, 8.08 g·kg-1), high-dose QDYF (QDYF-H, 16.16 g·kg-1), and loratadine (0.9 mg·kg-1). After 14 days of intervention, behavioral scores of the rats were observed. The morphological changes of nasal mucosa tissue were observed by hematoxylin-eosin (HE) staining. Masson staining was used to observe collagen fiber deposition in the nasal mucosal tissue and to calculate the collagen volume fraction (CVF). The expression of E-cadherin (E-cad) in the nasal mucosa tissue was detected by immunofluorescence. The serum levels of helper T cell 2 (Th2) cytokines interleukin-4 (IL-4), interleukin-5 (IL-5), and interleukin-13 (IL-13) as well as helper T cell 1 (Th1) cytokines interleukin-2 (IL-2) and interferon-γ (INF-γ) were quantified by enzyme-linked immunosorbent assay (ELISA). The protein levels of transforming growth factor-beta 1 (TGF-β1), IL-33, ST2, and IL-1RAP in the nasal mucosa tissue were determined by Western blot. ResultsIL-33, ST2, and IL-1RAP had strong binding ability with the main active ingredients—wogonin, 7-methoxy-2-methylisoflavone, formononetin, naringenin, stigmasterol, and beta-sitosterol of QDYF, with the binding energy < -4.25 kcal⋅mol-1(1 cal≈4.184 J). The results of in vivo experiments showed that compared with the control group, the model group exhibited increased behavioral scores (P<0.05), aggravated pathological damage of nasal mucosa, increased collagen fiber deposition and CVF (P<0.05), elevated serum levels of IL-4, IL-5, and IL-13, up-regulated protein levels of TGF-β1, IL-33, ST2, and IL-1RAP in the nasal mucosa (P<0.05), down-regulated expression of E-cad, and declined serum levels of IL-2, IFN-γ, and IFN-γ/IL-4 ratio (P<0.05). Compared with the model group, the QDYF groups and loratadine group showed reduced behavioral scores (P<0.05), alleviated pathological damage of nasal mucosa, reduced collagen fiber deposition and CVF (P<0.05), and up-regulated E-cad expression (P<0.05). Compared with the model group, the QDYF-H group and the loratadine group showed raised levels of INF-γ and IFN-γ/IL-4 ratio (P<0.05), declined serum levels of IL-4, IL-5, and IL-13, and down-regulated protein levels of TGF-β1, IL-33, ST2, and IL-1RAP in the nasal mucosa (P<0.05). In addition, the QDYF-H group exhibited an elevated serum IL-2 level (P<0.05). The QDYF-M group showed down-regulated protein levels of TGF-β1, IL-33 and IL-1RAP in the nasal mucosa (P<0.05). The QDYF-L group demonstrated a down-regulated protein level of ST2 in the nasal mucosa (P<0.05). ConclusionQDYF may regulate the Th1/Th2 balance through the IL-33/ST2/IL-1RAP signaling pathway, thereby ameliorating nasal mucosal tissue remodeling and alleviating AR.
2.Differences in deltamethrin resistance and kdr gene mutation in Culex tritaeniorhynchus population in and outside the Yellow Sea wetland
Xiao-er ZHANG ; Zhi-ming WU ; Ye TIAN ; Qian CUI ; Yu-qian JI ; Huan WANG ; Shu-juan YANG ; Yi-chao ZHAO ; Yu WANG ; Hua-yu YIN ; Yu DING ; Guo-jin YAN ; Min-sen ZHAO ; Shou-gang ZHANG ; Bing-dong SONG ; Hong-na CHEN ; Jian GAO ; Wei-fang YANG ; Yu-fu ZHANG ; Hui LIU ; Hong-liang CHU
Acta Parasitologica et Medica Entomologica Sinica 2026;33(2):101-107
Objective To gain insights into the biological characteristics of different populations of Culex tritaeniorhynchus within and around the Yellow Sea wetland from the perspective of the occurrence of resistance, we investigated the levels of resistance to deltamethrin and kdr gene mutation in the wetland and its peripheral areas. Methods Specimens were collected from Cx. tritaeniorhynchus populations at two monitoring sites in the Rare Bird National Nature Reserve and Tiaozi Ni Wetland Scenic Area, and also from two populations in Yancheng City and the Liuhe District of Nanjing, and the resistance of these mosquitoes to deltamethrin was determined using the CDC biotest bottle method. For each concentration of deltamethrin assessed, a random subset of exposed specimens was selected for amplification of the kdr gene fragment, followed by Sanger sequencing to identify and analyze resistance-associated mutations. Results The LC50 levels of deltamethrin among mosquitoes from the four populations in Luhe, Yancheng, the Rare Bird National Nature Reserve and the Tiaozi Ni Wetland Scenic Area were 2.048 5, 7.798 2, 3.473 3, and 17.695 5 mg/mL, respectively, with corresponding concentrations of deltamethrin ranging from 0.005 to 5.000,0.050 to 50.000,0.050 to 25.000 and 0.050 to 50.000 mg/mL, respectively. Furthermore, the ranges of the KT50 values were 11.76-107.43, 67.05-216.30,29.77-107.43 and 28.40-329.51 min; the 1-h knockdown rates were 34.58%-99.15%, 9.52%-43.80%, 55.09%-73.01%, and 10.09%-68.07%; and the 24-h mortality rates were 12.15%-67.52%,9.52%-79.56%,13.17%-82.21%, and 11.01%-78.99%, respectively. With respect to kdr gene mutation, we assayed a total of 63,70,59, and 57 mosquitoes for the four populations, for which we detected L1014F mutation frequencies of 14.29%, 35.00%, 20.34%, and 31.58%, respectively, with a majority of these mutations being heterozygous for resistance. In addition, five adult mosquitoes were identified has having synonymous mutations at site 1011[i. e. , AAT(asparagine)mutation to AAC(asparagine)]. Conclusions Our findings revealed the clear resistance of Cx. tritaeniorhynchus to deltamethrin in the Yancheng region of the Yellow Sea wetland, and the resistance phenotype and kdr frequency of Cx. tritaeniorhynchus in the wetland environment were comparable to those of Cx. tritaeniorhynchus in the wetland environment, thereby indicating that the resistance of different populations of Cx. tritaeniorhynchus was homogeneous under the pressure of different insecticide selection within and around the wetland. However, the underlying mechanisms need to be further studied.
3.Dual Targeting of TBK1 and JAK-STAT1 Pathways by (-)-epigallocatechin-3-gallate Suppresses Type I Interferon-driven Inflammation
Liang LI ; Qi-Huan SHENG ; Huan LIU ; Wen-Hao YANG ; Jia-Lin SHI ; Ying-Jie SUN ; Rui JING ; Wei-Hua MAI ; Zhi-Min LI ; Xiao-Li XIE
Progress in Biochemistry and Biophysics 2026;53(7):1969-1983
ObjectiveType I interferon (IFN-I) signaling is essential for antiviral innate immunity, yet its sustained or excessive activation contributes to the pathogenesis of several autoimmune diseases and interferonopathies, such as systemic lupus erythematosus and Aicardi-Goutières syndrome. Current strategies targeting this pathway, exemplified by JAK inhibitors, act mainly on downstream signal transduction and provide limited direct control over upstream IFN-I production, while also carrying the risk of broad immunosuppression. Phyllanthus emblica L. has long been used in traditional medicine for inflammatory disorders, but the bioactive constituent responsible for its regulation of IFN-I signaling and the underlying molecular mechanism have not been clearly defined. This study aimed to identify the active anti-inflammatory component of P. emblica and to characterize its mechanism of action on the IFN-I pathway in macrophages. MethodsActive components ofP. emblica and their candidate targets were screened by network pharmacology using the TCMSP and DrugBank databases (oral bioavailability≥30%, drug-likeness≥0.18) and intersected with inflammation-related genes retrieved from public databases. The predicted interaction between EGCG and IFN-I pathway proteins (TBK1, IRF3, STAT1) was evaluated by molecular docking, with BX795 and GSK8612 used as reference TBK1 inhibitors. Mechanistic experiments were performed in THP-1-derived macrophages and primary bone marrow-derived macrophages (BMDM). Upstream signaling was activated by transfection of the nucleic acid analogs poly(I∶C) and poly(dA∶dT) or by lipopolysaccharide (LPS) stimulation, whereas downstream signaling was activated by exogenous IFN-β. An siRNA-mediated TREX1 knockdown model was used to mimic endogenous nucleic acid-driven interferonopathy. Expression of IFN-β1 and interferon-stimulated genes (ISGs) was measured by RT-qPCR, protein phosphorylation by Western blot, and IFN-β secretion by ELISA. Cellular thermal shift assay (CETSA) and drug affinity responsive target stability (DARTS) were used to probe the interactionbetween EGCG and IRF3. ResultsNetwork pharmacology identified (-)-epigallocatechin-3-gallate (EGCG) as a candidate IFN-I-suppressive constituent of P. emblica, with predicted binding to TBK1, IRF3, and STAT1. Molecular docking yielded binding energies of -9.2, -7.2, and -8.2 kcal/mol for TBK1, IRF3, and STAT1, respectively, indicating an affinity for TBK1 comparable to that of the reference inhibitors BX795 (-5.7 kcal/mol) and GSK8612 (-6.4 kcal/mol). EGCG suppressed IFN-β1 and ISG mRNA expression under poly (I∶C), poly (dA∶dT), and LPS stimulation in both THP-1 macrophages and BMDM. At the protein level, EGCG reduced the phosphorylation of TBK1 and IRF3 without affecting the levels of the upstream sensors cGAS and RIG-I, and lowered IFN-β secretion in a concentration-dependent manner. CETSA and DARTS showed that EGCG did not enhance the thermal stability or protease resistance of IRF3, indicating that its effect on IRF3 is indirect. Following IFN-β stimulation, prolonged EGCG treatment reduced STAT1 phosphorylation in a time-dependent manner without an apparent change in IRF9, and partially attenuated ISG transcription; this effect was not monotonicly concentration-dependent, and CXCL10 showed the most consistent suppression. In TREX1-knockdown cells, the elevated mRNA levels of ISG15, ISG56, and CXCL10 were reduced by EGCG. ConclusionEGCG suppresses IFN-I responses by concurrently inhibiting TBK1-IRF3-dependent IFN‑β production and JAK-STAT1-mediated downstream transcription. These in vitro findings provide a mechanistic basis for the anti-inflammatory use of P. emblica in traditional medicine and identify EGCG as a candidate for further evaluation in interferon-driven autoimmune disease models.
4.Potential utility of albumin-bilirubin and body mass index-based logistic model to predict survival outcome in non-small cell lung cancer with liver metastasis treated with immune checkpoint inhibitors.
Lianxi SONG ; Qinqin XU ; Ting ZHONG ; Wenhuan GUO ; Shaoding LIN ; Wenjuan JIANG ; Zhan WANG ; Li DENG ; Zhe HUANG ; Haoyue QIN ; Huan YAN ; Xing ZHANG ; Fan TONG ; Ruiguang ZHANG ; Zhaoyi LIU ; Lin ZHANG ; Xiaorong DONG ; Ting LI ; Chao FANG ; Xue CHEN ; Jun DENG ; Jing WANG ; Nong YANG ; Liang ZENG ; Yongchang ZHANG
Chinese Medical Journal 2025;138(4):478-480
5.Processing technology of calcined Magnetitum based on concept of QbD and its XRD characteristic spectra.
De-Wen ZENG ; Jing-Wei ZHOU ; Tian-Xing HE ; Yu-Mei CHEN ; Huan-Huan XU ; Jian FENG ; Yue YANG ; Xin CHEN ; Jia-Liang ZOU ; Lin CHEN ; Hong-Ping CHEN ; Shi-Lin CHEN ; Yuan HU ; You-Ping LIU
China Journal of Chinese Materia Medica 2025;50(9):2391-2403
Guided by the concept of quality by design(QbD), this study optimizes the calcination and quenching process of calcined Magnetitum and establishes the XRD characteristic spectra of calcined Magnetitum, providing a scientific basis for the formulation of quality standards. Based on the processing methods and quality requirements of Magnetitum in the Chinese Pharmacopoeia, the critical process parameters(CPPs) identified were calcination temperature, calcination time, particle size, laying thickness, and the number of vinegar quenching cycles. The critical quality attributes(CQAs) included Fe mass fraction, Fe~(2+) dissolution, and surface color. The weight coefficients were determined by combining Analytic Hierarchy Process(AHP) and the criteria importance though intercrieria correlation(CRITIC) method, and the calcination process was optimized using orthogonal experimentation. Surface color was selected as a CQA, and based on the principle of color value, the surface color of calcined Magnetitum was objectively quantified. The vinegar quenching process was then optimized to determine the best processing conditions. X-ray diffraction(XRD) was used to establish the characteristic spectra of calcined Magnetitum, and methods such as similarity evaluation, cluster analysis, and orthogonal partial least squares-discriminant analysis(OPLS-DA) were used to evaluate the quality of the spectra. The optimized calcined Magnetitum preparation process was found to be calcination at 750 ℃ for 1 h, with a laying thickness of 4 cm, a particle size of 0.4-0.8 cm, and one vinegar quenching cycle(Magnetitum-vinegar ratio 10∶3), which was stable and feasible. The XRD characteristic spectra analysis method, featuring 9 common peaks as fingerprint information, was established. The average correlation coefficient ranged from 0.839 5-0.988 1, and the average angle cosine ranged from 0.914 4 to 0.995 6, indicating good similarity. Cluster analysis results showed that Magnetitum and calcined Magnetitum could be grouped together, with similar compositions. OPLS-DA discriminant analysis identified three key characteristic peaks, with Fe_2O_3 being the distinguishing component between the two. The final optimized processing method is stable and feasible, and the XRD characteristic spectra of calcined Magnetitum was initially established, providing a reference for subsequent quality control and the formulation of quality standards for calcined Magnetitum.
X-Ray Diffraction/methods*
;
Drugs, Chinese Herbal/chemistry*
;
Quality Control
;
Particle Size
6.Clinical features of recompensation in autoimmune hepatitis-related decompensated cirrhosis and related predictive factors
Xiaolong LU ; Lin HAN ; Huan XIE ; Lilong YAN ; Xuemei MA ; Dongyan LIU ; Xun LI ; Qingsheng LIANG ; Zhengsheng ZOU ; Caizhe GU ; Ying SUN
Journal of Clinical Hepatology 2025;41(9):1808-1817
ObjectiveTo investigate the clinical features and outcomes of recompensation in patients with autoimmune hepatitis (AIH)-related decompensated cirrhosis, to identify independent predictive factors, and to construct a nomogram prediction model for the probability of recompensation. MethodsA retrospective cohort study was conducted among the adult patients with AIH-related decompensated cirrhosis who were admitted to The Fifth Medical Center of PLA General Hospital from January 2015 to August 2023 (n=211). The primary endpoint was achievement of recompensation, and the secondary endpoint was liver-related death or liver transplantation. According to the outcome of the patients at the end of the follow-up, the patients were divided into the recompensation group (n=16) and the persistent decompensation group(n=150).The independent-samples t test was used for comparison of normally distributed continuous data with homogeneity of variance, and the Mann-Whitney U rank sum test was used for comparison of non-normally distributed continuous data with heterogeneity of variance; the chi-square test or the Fisher’s exact test was used for comparison of categorical data between groups; the Kaplan-Meier method was used for survival analysis; the Cox proportional-hazards regression model was used to identify independent predictive factors, and a nomogram model was constructed and validated. ResultsA total of 211 patients were enrolled, with a median age of 55.0 years and a median follow-up time of 44.0 months, and female patients accounted for 87.2%. Among the 211 patients, 61 (with a cumulative proportion of 35.5%) achieved recompensation. Compared with the persistent decompensation group, the recompensation group had significantly higher white blood cell count, platelet count (PLT), total bilirubin (TBil), alanine aminotransferase (ALT), aspartate aminotransferase (AST), total bile acid, prothrombin time, international normalized ratio (INR), SMA positive rate, Model for End-Stage Liver Disease (MELD) score, Child-Pugh score, and rate of use of glucocorticoids (all P0.05), as well as significantly lower age at baseline, number of complications, and death/liver transplantation rate (all P0.05). At 3 and 12 months after treatment, the recompensation group had continuous improvements in AST, TBil, INR, IgG, MELD score, and Child-Pugh score, which were significantly lower than the values in the persistent decompensation group (all P0.05), alongside with continuous increases in PLT and albumin, which were significantly higher than the values in the persistent decompensation group (P0.05). The multivariate Cox regression analysis showed that baseline ALT (hazard ratio [HR]=1.067, 95% confidence interval [CI]: 1.010 — 1.127, P=0.021), IgG (HR=0.463,95%CI:0.258 — 0.833, P=0.010), SMA positivity (HR=3.122,95%CI:1.768 — 5.515, P0.001), and glucocorticoid therapy (HR=20.651,95%CI:8.744 — 48.770, P0.001) were independent predictive factors for recompensation, and the nomogram model based on these predictive factors showed excellent predictive performance (C-index=0.87,95%CI:0.84 — 0.90). ConclusionAchieving recompensation significantly improves clinical outcomes in patients with AIH-related decompensated cirrhosis. Baseline SMA positivity, a high level of ALT, a low level of IgG, and corticosteroid therapy are independent predictive factors for recompensation. The predictive model constructed based on these factors can provide a basis for decision-making in individualized clinical management.
7.Associations of Genetic Risk and Physical Activity with Incident Chronic Obstructive Pulmonary Disease: A Large Prospective Cohort Study.
Jin YANG ; Xiao Lin WANG ; Wen Fang ZHONG ; Jian GAO ; Huan CHEN ; Pei Liang CHEN ; Qing Mei HUANG ; Yi Xin ZHANG ; Fang Fei YOU ; Chuan LI ; Wei Qi SONG ; Dong SHEN ; Jiao Jiao REN ; Dan LIU ; Zhi Hao LI ; Chen MAO
Biomedical and Environmental Sciences 2025;38(10):1194-1204
OBJECTIVE:
To investigate the relationship between physical activity and genetic risk and their combined effects on the risk of developing chronic obstructive pulmonary disease.
METHODS:
This prospective cohort study included 318,085 biobank participants from the UK. Physical activity was assessed using the short form of the International Physical Activity Questionnaire. The participants were stratified into low-, intermediate-, and high-genetic-risk groups based on their polygenic risk scores. Multivariate Cox regression models and multiplicative interaction analyses were used.
RESULTS:
During a median follow-up period of 13 years, 9,209 participants were diagnosed with chronic obstructive pulmonary disease. For low genetic risk, compared to low physical activity, the hazard ratios ( HRs) for moderate and high physical activity were 0.853 (95% confidence interval [ CI]: 0.748-0.972) and 0.831 (95% CI: 0.727-0.950), respectively. For intermediate genetic risk, the HRs were 0.829 (95% CI: 0.758-0.905) and 0.835 (95% CI: 0.764-0.914), respectively. For participants with high genetic risk, the HRs were 0.809 (95% CI: 0.746-0.877) and 0.818 (95% CI: 0.754-0.888), respectively. A significant interaction was observed between genetic risk and physical activity.
CONCLUSION
Moderate or high levels of physical activity were associated with a lower risk of developing chronic obstructive pulmonary disease across all genetic risk groups, highlighting the need to tailor activity interventions for genetically susceptible individuals.
Humans
;
Pulmonary Disease, Chronic Obstructive/epidemiology*
;
Exercise
;
Male
;
Female
;
Middle Aged
;
Prospective Studies
;
Aged
;
Genetic Predisposition to Disease
;
Risk Factors
;
United Kingdom/epidemiology*
;
Incidence
;
Adult
8.POLYMORPHISM OF THE INTERNAL TRANSCRIBED SPACER SEQUENCES OF EUSTRONGYLIDES SPP.IN MONOPTERUS ALBUS
Ri-Hua YANG ; Huan-Fu TIAN ; Lin-Sen ZOU ; Song-Bai WANG ; De-Liang LI ; Wei LIU
Acta Parasitologica et Medica Entomologica Sinica 2025;32(1):60-64
Objective The aim of the study is to reveal the polymorphisms of Eustrongylides spp.in Monopterus albus.Methods A total of five Eustrongylides spp.collected from five M.albus in the Yongzhou area were sampled to amplify ribosomal ITS sequence by PCR in vitro,then sequenced after extracting the DNA templates of Eustrongylides.The phylogenetic tree based on the ITS sequence was also constructed to explore the evolutionary history of Eustrongylides.Results The length of the ITS sequence of the five Eustrongylides spp.is approximately 933 bp,and the genetic differences between the isolates are 0.00%-0.90%and the genetic inheritance differences with other nematodes are 15.5%-18.20%,maintaining a certain genetic distance from other families.Conclusions The ITS sequence of Eustrongylides spp.in M.albus will be used as a genetic marker for the molecular identification of Eustrongylides spp.and will provide a basis for the prevention and control of Eustrongylides spp.in the future.
9.Comparison of setup errors between two postural fixation methods in radiotherapy for breast cancer
Fukui HUAN ; Yu ZHAO ; Chao LIU ; Gengqiang ZHU ; Ruiao ZHAO ; Yongtai ZHENG ; Yandong GE ; Bao WAN ; Bin LIANG
Chongqing Medicine 2025;54(4):921-925
Objective To compare the positioning errors and the motion of acromioclavicular joint in breast cancer patients with integrated cervicothoracic thermoplastic membrane and breast bracket fixation,and to provide reference for accurate irradiation of upper and lower clavicular region.Methods Sixty-three pa-tients with breast cancer who were treated in the radiotherapy center of the hospital from November 1,2021 to August 9,2023 were selected as the study objects,and were divided into the integrated cervicothoracic thermo-plastic membrane group(n=32)and breast bracket group(n=31)according to different positioning meth-ods.The translation errors of left and right direction(X),head and foot direction(Y)and ventral and dorsal direction(Z)and the rotation errors of sagittal plane(Rx),cross section(Ry)and coronal plane(Rz)of the two groups were analyzed,and the movement amplitude and three-dimensional displacement of acromioclavic-ular joint were measured respectively.Results Compared with the breast bracket group,X translation errors[(0.18±0.14)cm vs.(0.15±0.12)cm]and Z translation errors[(0.19±0.14)cm vs.(0.16±0.14)cm]of the cervicothoracic thermoplastic memberane group were greater,Z translation error[(0.21±0.17)cm vs.(0.22±0.21)cm]and Rx rotation error of cervical and sternoclavicular joints[(0.93±0.87)° vs.(1.08±0.92)°]were smaller,Rz rotation error[(1.00±0.94)° vs.(0.95±0.86)°]was greater,and the motion ΔX of acromioclavicular joint[(0.18±0.15)cm vs.(0.25±0.21)cm]was smaller,the difference was statistically significant(P<0.05).Conclusion Integrated cervicothoracic thermoplastic membrane can be used as a solu-tion for prophylactic irradiation of breast cancer in the upper and lower clavicular region and for radiation leak-age in the presence of metastasis.
10.Pregnancy probability prediction models based on 5 machine learning algorithms and comparison of their performance
Chao REN ; Huan YANG ; Niya ZHOU ; Qing CHEN ; Wenzheng ZHOU ; Tong WANG ; Xi LING ; Lei SUN ; Peng ZOU ; Zhuoyue LIANG ; Lin AO ; Jinyi LIU ; Jia CAO
Journal of Army Medical University 2025;47(12):1376-1387
Objective To construct 5 machine-learning models and compare their performance in predicting the associations between pre-pregnancy socio-psycho-behavioral exposures of both spouses and preconception outcomes.Methods Based on Chongqing Preconception Reproductive Health and Birth Outcome Cohort of volunteers recruited from Chongqing Health Center for Women and Children during January 2019 and March 2022,5 447 couples were recruited and surveyed through interviewer-interview for the demographic and social-psychological-behavioral data of both spouses(221 variables).According to the inclusion and exclusion criteria,4 097 couples were finally included,and randomly assigned into a training set(n=2 867 spouses)and a validation set(n=1 230 spouses)at a ratio of 7∶3.Feature analysis and collinear screening were applied to select the potential exposure factors.In consideration of difficulty to carry out semen parameters analysis in primary healthcare institutions,feature Set 1 including sperm parameters and feature Set 2 excluding semen parameters were constructed by including or excluding sperm quality simultaneously in the training set and the validation set.Five algorithms,that is,Logistic Regression,Naive Bayes,Random Forest,Gradient Boosting Machine,and Support Vector Machine,were used to construct preconception outcome prediction models,and the parameters of each model were optimized using random search combined with grid search.The predictive performance of each model was compared using precision,recall,F1 score,area under the receiver operating characteristic curve(AUC),and calibration curve.The optimal model was then selected by comparing the changes in the predictive ability of the questionnaire data for fertility outcomes with or without semen parameters.Results There were 24 variables screened out in feature Set 1,and 16 variables in feature Set 2.In feature Set 1,the gradient boosting machine performed better,with a relatively higher AUC value(0.651)and better F1 score(0.61).The logistic regression model performed stably(AUC value=0.647)and was suitable as the reference model.The random forest(AUC value=0.641),Naive Bayes(AUC value=0.641),and support vector machine(AUC value=0.634)performed second-best.By utilizing the gradient boosting machine,comparable results were found between the predictions from feature sets with or without semen parameters,as in feature Set 1,the AUC value of its validation set was 0.651(95%CI:0.629~0.681),the prediction accuracy was 0.63,the recall rate was 0.65,and the average precision value F1 was 0.61;and in feature Set 2,the AUC value of its validation set was 0.649(95%CI:0.624~0.663),and both the calibration curves were close to the ideal curve.The prediction results indicated that in feature Set 1,the features highly negatively correlated with preconception outcomes were female age,male age,and no pregnancy within 1 year without contraception,while the features highly positively correlated with preconception outcomes were female pregnancy history,total sperm vitality,and use of contraceptive measures before enrollment.Conclusion Among the 5 machine-learning algorithms performed in this cohort data,the gradient boosting machine shows slightly better performance.There are 24 factors being associated with preconception outcomes in both spouses,and the performance of the simplified model excluding semen parameters is not significantly declined.It is feasible to use machine-learning methods to predict human preconception outcomes through social-psychological-behavioral questionnaires.


Result Analysis
Print
Save
E-mail