1.The Disease Burden of Asthma in China, 1990 to 2021 and Projections to 2050: Based on the Global Burden of Disease 2021.
Rui Yi ZHANG ; Miao Miao ZHANG ; Yu Chang ZHOU ; Jia Huan GUO ; Xuan Kai WANG ; Mai Geng ZHOU
Biomedical and Environmental Sciences 2025;38(5):529-538
OBJECTIVE:
Asthma imposes a significant global health burden. This study examines changes in the asthma-related disease burden from 1990 to 2021 and projects future burdens for 2050 under different scenarios.
METHODS:
Using data from the Global Burden of Disease 2021 study, we analyzed asthma incidence, prevalence, mortality, and disability-adjusted life years (DALYs) from 1990 to 2021. We projected the disease burden for 2050 based on current trends and hypothetical scenarios in which all risk factors are controlled. Temporal trends in age-standardized incidence, prevalence, mortality, and DALY rates were explored using Annual Percent Change.
RESULTS:
In 2021, the age-standardized rates for asthma incidence, prevalence, mortality, and DALYs in China were 364.17 per 100,000 (95% uncertainty interval [ UI]: 283.22-494.10), 1,956.49 per 100,000 (95% UI: 1,566.68-2,491.87), 1.47 per 100,000 (95% UI: 1.15-1.79), and 103.76 per 100,000 (95% UI: 72.50-145.46), respectively. A higher disease burden was observed among Chinese men and individuals aged 70 years or older. Compared to the current trend, a combined scenario involving improvements in environmental factors, behavioral and metabolic health, child nutrition, and vaccination resulted in a greater reduction in the disease burden caused by asthma.
CONCLUSION
Addressing modifiable risk factors is essential for further reducing the asthma-related disease burden.
Humans
;
Asthma/mortality*
;
China/epidemiology*
;
Male
;
Female
;
Adult
;
Middle Aged
;
Aged
;
Child
;
Adolescent
;
Global Burden of Disease/trends*
;
Child, Preschool
;
Young Adult
;
Infant
;
Cost of Illness
;
Disability-Adjusted Life Years
;
Prevalence
;
Incidence
;
Infant, Newborn
;
Aged, 80 and over
;
Risk Factors
2.Value of color Doppler ultrasound combined with shear wave elastography in predicting the recurrence risk of breast cancer after operation
Huan WANG ; Jun WANG ; Qiuping WANG ; Jia LI ; Xinxing LIANG
Chinese Journal of Endocrine Surgery 2025;19(5):666-670
Objective:To assess the effectiveness of combining color Doppler ultrasound (CDU) with shear wave elastography (SWE) in forecasting the likelihood of breast cancer (BC) recurrence.Methods:From Jan. 2022 to Jan. 2024, we gathered data on 92 BC patients admitted to Shanxi Maternal and Child Health Hospital and Shanxi Cancer Hospital, focusing on their lesion characteristics. Each patient underwent CDU and SWE examinations pre-surgery and was monitored for a year. Based on BC recurrence, patients were categorized into recurrence and non-recurrence groups. We compared CDU imaging and hemodynamic features of BC between these groups and evaluated SWE elastic modulus values. To assess the agreement between CDU, SWE, and their combined use in predicting BC recurrence and pathological diagnosis, we employed the Kappa test. Additionally, we plotted ROC curves to analyze the predictive power of CDU, SWE, and their combination in assessing BC recurrence risk. Results:Among the 92 BC patients studied, 38 experienced recurrence, while 54 did not. CDU examination revealed that the non-recurrence group exhibited significantly larger tumor maximum diameter, higher peak systolic velocity (PSV), a higher proportion of aspect ratio ≥ 1, irregular margins, calcification, and increased vascular abundance, compared to the recurrence group ( t/ χ2=17.188, 18.491, 6.099, 15.374, 14.526, 19.318, P<0.05). Additionally, the vascular resistance index (RI) was lower in the non-recurrence group ( t=-26.429, P<0.05). SWE results indicated that the recurrence group had higher average (E mean), maximum (E max), and minimum (E min) elastic moduli compared to the non-recurrence group ( t=14.39, 12.34, 8.29, P<0.05). CDU and SWE predictions showed substantial agreement with pathological results, with Kappa values of 0.66 and 0.69, respectively ( P<0.05). The combination of CDU and SWE predictions demonstrated excellent concordance with pathological outcomes ( Kappa=0.91, P<0.05). In terms of predicting BC recurrence risk, CDU and SWE had accuracies of 83.70% and 84.21%, respectively. The ROC curve analysis showed AUC values of 0.830 for CDU, 0.847 for SWE, and 0.955 for their combination. Sensitivity was 0.870 for CDU, 0.852 for SWE, and 0.963 for the combination. Specificity was 0.789 for CDU, 0.842 for SWE, and 0.947 for the combination. Positive predictive values were 78.95% for CDU, 84.21% for SWE, and 94.74% for the combination, while negative predictive values were 87.04% for CDU, 85.19% for SWE, and 96.30% for the combination. The AUC for CDU in predicting post-operative BC recurrence risk was not significantly different from SWE ( χ2=0.04, P>0.05), but the combined prediction AUC was significantly higher than individual predictions ( χ2=8.00, 7.04, P<0.05) . Conclusion:The predictive value of CDU and SWE combined examination for the recurrence risk of BC is better than that of single examination, and it is suggested that the combined examination method should be popularized in clinic.
3.COVID-19-associated Invasive Pulmonary Mucormycosis:A Case Report and Literature Review
Bing-qian YI ; Bo-wen XU ; Xi YU ; Huan-huan BI ; Yu-ting XIAO ; Hong-mei WANG ; Ning CUI ; Jia-xing SUN
Progress in Modern Biomedicine 2025;25(13):2216-2222
Objective:Invasive pulmonary mucormycosis(PM)is a rare but highly lethal opportunistic infection.COVID-19 associated mucormycosis(CAM)is difficult to diagnose,often leading to misdiagnosis or missed diagnosis,and has poor treatment outcomes.This study reports a case of successfully treated CAM and explores optimized diagnostic and therapeutic strategies.Methods:A retrospective analysis of the diagnosis and treatment process in a 50-year-old female patient with COVID-19 associated with diabetic ketoacidosis(DKA)and invasive pulmonary mucormycosis was conducted.Combined with a literature review,the therapeutic efficacy of local bronchoscopic instillation in conjunction with systemic treatment using liposomal Amphotericin B(L-AmB)was specifically evaluated.Results:The patient was rapidly diagnosed with Rhizopus microsporus infection through metagenomic next-generation sequencing(mNGS).She subsequently received antifungal treatment with intravenous L-AmB combined with local bronchoscopic instillation.After treatment,the patient was significantly improved,with imaging studies showing gradual absorption of the lesions.Follow-up at six months revealed no recurrence.A literature review suggests that early diagnosis and multimodal therapy are key to improving survival rates in patients with CAM.Conclusion:mNGS can significantly improve the early diagnosis rate of CAM.The combination of local and systemic treatment with L-AmB is valuable in improving prognosis.Early diagnosis,multimodal antifungal therapy,and individualized management are key to increasing the survival rate of patients with CAM.
4.Value of color Doppler ultrasound combined with shear wave elastography in predicting the recurrence risk of breast cancer after operation
Huan WANG ; Jun WANG ; Qiuping WANG ; Jia LI ; Xinxing LIANG
Chinese Journal of Endocrine Surgery 2025;19(5):666-670
Objective:To assess the effectiveness of combining color Doppler ultrasound (CDU) with shear wave elastography (SWE) in forecasting the likelihood of breast cancer (BC) recurrence.Methods:From Jan. 2022 to Jan. 2024, we gathered data on 92 BC patients admitted to Shanxi Maternal and Child Health Hospital and Shanxi Cancer Hospital, focusing on their lesion characteristics. Each patient underwent CDU and SWE examinations pre-surgery and was monitored for a year. Based on BC recurrence, patients were categorized into recurrence and non-recurrence groups. We compared CDU imaging and hemodynamic features of BC between these groups and evaluated SWE elastic modulus values. To assess the agreement between CDU, SWE, and their combined use in predicting BC recurrence and pathological diagnosis, we employed the Kappa test. Additionally, we plotted ROC curves to analyze the predictive power of CDU, SWE, and their combination in assessing BC recurrence risk. Results:Among the 92 BC patients studied, 38 experienced recurrence, while 54 did not. CDU examination revealed that the non-recurrence group exhibited significantly larger tumor maximum diameter, higher peak systolic velocity (PSV), a higher proportion of aspect ratio ≥ 1, irregular margins, calcification, and increased vascular abundance, compared to the recurrence group ( t/ χ2=17.188, 18.491, 6.099, 15.374, 14.526, 19.318, P<0.05). Additionally, the vascular resistance index (RI) was lower in the non-recurrence group ( t=-26.429, P<0.05). SWE results indicated that the recurrence group had higher average (E mean), maximum (E max), and minimum (E min) elastic moduli compared to the non-recurrence group ( t=14.39, 12.34, 8.29, P<0.05). CDU and SWE predictions showed substantial agreement with pathological results, with Kappa values of 0.66 and 0.69, respectively ( P<0.05). The combination of CDU and SWE predictions demonstrated excellent concordance with pathological outcomes ( Kappa=0.91, P<0.05). In terms of predicting BC recurrence risk, CDU and SWE had accuracies of 83.70% and 84.21%, respectively. The ROC curve analysis showed AUC values of 0.830 for CDU, 0.847 for SWE, and 0.955 for their combination. Sensitivity was 0.870 for CDU, 0.852 for SWE, and 0.963 for the combination. Specificity was 0.789 for CDU, 0.842 for SWE, and 0.947 for the combination. Positive predictive values were 78.95% for CDU, 84.21% for SWE, and 94.74% for the combination, while negative predictive values were 87.04% for CDU, 85.19% for SWE, and 96.30% for the combination. The AUC for CDU in predicting post-operative BC recurrence risk was not significantly different from SWE ( χ2=0.04, P>0.05), but the combined prediction AUC was significantly higher than individual predictions ( χ2=8.00, 7.04, P<0.05) . Conclusion:The predictive value of CDU and SWE combined examination for the recurrence risk of BC is better than that of single examination, and it is suggested that the combined examination method should be popularized in clinic.
5.Analysis of Clinical Characteristics and Drug Sensitivity Spectrum of Pathogenic Bacteria in 1 091 Prepubertal Children with Vulvovaginitis in Xi'an Area from 2019 to 2023
Wei WANG ; Zengguo WANG ; Kai JIA ; Huan QIANG ; Lin WANG
Journal of Modern Laboratory Medicine 2025;40(4):179-182,207
Objective To investigate the clinical characteristics and pathogen resistance of vulvovaginitis among prepubertal children in Xi'an area,so as to provide valuable insights for clinical diagnosis and treatment.Methods A total of 1 019 children(aged<10 years)diagnosed with prepubertal vulvovaginitis in Xi'an Children Hospital from January 2019 to December 2023 were selected as the research objects.The clinical characteristics and drug resistance of pathogenic bacteria were analyzed.Results The number of children with prepubertal vulvovaginitis increased significantly after the end of the COVID-19 pandemic.The positive detection rate in 2023 increased by 13.18%compared to that in 2019,with a significant rise in bacterial vulvitis compared to fungal infection.Common clinical manifestations among diagnosed children included increased secretion and vulvar pruritus.As age increased,the detection rate of pathogenic bacteria also rose,reaching a high positive proportion of 37.29%among children aged 8~<10 years old.Pathogenic bacteria isolated in the laboratory mainly consisted of Haemophilus influenzae(30.72%,313/1 019),Candida albicans(28.46%,290/1 019)and Streptococcus pyogenes(20.61%,210/1 019).Notably,the detection rates of these pathogens exhibited significant variations among children of different age groups(χ2=279.26,382.97,83.48,all P<0.05).Among them,vulvitis in children under 8 years old were mainly caused by respiratory bacterial infections,while those aged 8~<10 tended to be consistent with adults and were mainly caused by candidal vulvitis.The drug sensitivity test results indicated that Haemophilus influenzae exhibited high resistance rates to ampicillin and cefuroxime but good sensitivity to third-generation cephalosporins.Candida albicans showed good sensitivity to common antifungal drugs.Streptococcus pyogenes displayed high sensitivity to penicillin,ampicillin and ceftriaxone but strong resistance(>90%)against erythromycin and clindamycin.Conclusion The positive rate of vulvitis has been increasing among prepubertal children in Xi'an recent years.Pathogenic bacteria are concentrated and sensitive towards common antibiotics.Early submission of clinical samples,rational use of medications and reinforcement on healthy habits guidance are recommended for timely intervention in the development of the disease.
6.Construction of a recombinant adenovirus for Mycobacterium tuberculosis c-di-AMP phosphodiesterase expression and induction of humoral immunity
Jia-hao HU ; Huan-huan NING ; Meng-juan DONG ; Yan-zhi LU ; Ting DAI ; Cong-yue ZHANG ; Zi-qing XU ; Shu-yu WANG ; Zheng-yan ZHOU ; Yin-lan BAI
Chinese Journal of Zoonoses 2025;41(4):364-369
A recombinant adenovirus(rAd)for expression of Mycobacterium tuberculosis(M.tb)c-di-AMP phosphodiesterase CnpB was constructed,and its induced humoral immune response was detected.The codon-optimized gene of M.tb CnpB was cloned into the adenoviral plasmid pcADV.The recombinant plasmid pcADV-CnpB was transfected into HEK293T cells,and expression was detected with Western blot.The recombinant plasmid pcADV-CnpB and the backbone plasmid were co-transfected into HEK293T cells to obtain the recombinant adenovirus rAd-CnpB.rAd-CnpB was amplified in HEK293T cells,and the target protein expression of rAd-CnpB was detected with Western blot and immunofluorescence.Mice were immunized with rAd-CnpB intranasally,and their sera and bronchoalveolar lavage fluid(BALF)were collected.ELISA was used to detect levels of antigen-specific antibodies.Restriction enzyme digestion and sequencing indicated that the recombinant plasmid pcADV-CnpB was successfully constructed and led to protein expression in eukaryotic cells.rAd-CnpB was packaged and produced in HEK293T cells.After amplification and purification,rAd-CnpB with a titer of 5.53×1010 PFU/mL was obtained.rAd-CnpB led to CnpB expression in HEK293T cells.Intranasal immunization with rAd-CnpB increased levels of IgG and secretory IgA in BALF and led to high levels of IgG in sera.rAd-CnpB,the recombinant adenovirus for expression of c-di-AMP phosphodiesterase CnpB was successfully constructed,and was found to induce antigen-specific humoral and mucosal immune responses through mucosal immunization.Thus,rAd-CnpB may be used in further research on new TB vaccine strategies.
7.Application of Engineered Exosomes in Tumor-targeted Therapy
Jia-Lu SONG ; Yi-Xin JIN ; Xing-Yu MU ; Yu-Huan JIANG ; Jing WANG
Progress in Biochemistry and Biophysics 2025;52(5):1140-1151
Tumors are the second leading cause of death worldwide. Exosomes are a type of extracellular vesicle secreted from multivesicular bodies, with particle sizes ranging from 40 to 160 nm. They regulate the tumor microenvironment, proliferation, and progression by transporting proteins, nucleic acids, and other biomolecules. Compared with other drug delivery systems, exosomes derived from different cells possess unique cellular tropism, enabling them to selectively target specific tissues and organs. This homing ability allows them to cross biological barriers that are otherwise difficult for conventional drug delivery systems to penetrate. Due to their biocompatibility and unique biological properties, exosomes can serve as drug delivery systems capable of loading various anti-tumor drugs. They can traverse biological barriers, evade immune responses, and specifically target tumor tissues, making them ideal carriers for anti-tumor therapeutics. This article systematically summarizes the methods for exosome isolation, including ultracentrifugation, ultrafiltration, size-exclusion chromatography (SEC), immunoaffinity capture, and microfluidics. However, these methods have certain limitations. A combination of multiple isolation techniques can improve isolation efficiency. For instance, combining ultrafiltration with SEC can achieve both high purity and high yield while reducing processing time. Exosome drug loading methods can be classified into post-loading and pre-loading approaches. Pre-loading is further categorized into active and passive loading. Active loading methods, including electroporation, sonication, extrusion, and freeze-thaw cycles, involve physical or chemical disruption of the exosome membrane to facilitate drug encapsulation. Passive loading relies on drug concentration gradients or hydrophobic interactions between drugs and exosomes for encapsulation. Pre-loading strategies also include genetic engineering and co-incubation methods. Additionally, we review approaches to enhance the targeting, retention, and permeability of exosomes. Genetic engineering and chemical modifications can improve their tumor-targeting capabilities. Magnetic fields can also be employed to promote the accumulation of exosomes at tumor sites. Retention time can be prolonged by inhibiting monocyte-mediated clearance or by combining exosomes with hydrogels. Engineered exosomes can also reshape the tumor microenvironment to enhance permeability. This review further discusses the current applications of exosomes in delivering various anti-tumor drugs. Specifically, exosomes can encapsulate chemotherapeutic agents such as paclitaxel to reduce side effects and increase drug concentration within tumor tissues. For instance, exosomes loaded with doxorubicin can mitigate cardiotoxicity and minimize adverse effects on healthy tissues. Furthermore, exosomes can encapsulate proteins to enhance protein stability and bioavailability or carry immunogenic cell death inducers for tumor vaccines. In addition to these applications, exosomes can deliver nucleic acids such as siRNA and miRNA to regulate gene expression, inhibit tumor proliferation, and suppress invasion. Beyond their therapeutic applications, exosomes also serve as tumor biomarkers for early cancer diagnosis. The detection of exosomal miRNA can improve the sensitivity and specificity of diagnosing prostate and pancreatic cancers. Despite their promising potential as drug delivery systems, challenges remain in the standardization and large-scale production of exosomes. This article explores the future development of engineered exosomes for targeted tumor therapy. Plant-derived exosomes hold potential due to their superior biocompatibility, lower toxicity, and abundant availability. Furthermore, the integration of exosomes with artificial intelligence may offer novel applications in diagnostics, therapeutics, and personalized medicine.
8.Coptidis Rhizoma-Scutellariae Radix alleviates CpG1826-induced cytokine storm secondary lung injury in mice by inhibiting mPTP/NLRP3 pyroptosis pathway.
Qing-Rui ZHONG ; Hong-Kai HUANG ; Yue-Jia LAN ; Huan WANG ; Yong ZENG ; Jia-Si WU
China Journal of Chinese Materia Medica 2025;50(15):4141-4152
This study aims to investigate the therapeutic effects of the Coptidis Rhizoma-Scutellariae Radix on cytokine storm secondary lung injury(CSSLI) induced by CpG1826 in mice, and to elucidate the potential molecular mechanisms by which its major active components, i.e., coptisine and wogonin, alleviate CSSLI by inhibiting the mitochondrial permeability transition pore(mPTP)/nucleotide-binding oligomerization domain-like receptor protein 3(NLRP3) inflammasome pyroptosis pathway. In vivo, a mouse model of CSSLI was established by CpG1826 induction. Pulmonary edema was assessed by lung wet-to-dry weight ratio(W/D), lung injury was evaluated by hematoxylin-eosin(HE) staining, and ultrastructural changes in lung tissue were observed by transmission electron microscopy(TEM). The levels of interleukin(IL)-1β, high mobility group box 1 protein(HMGB1), IL-18, and IL-1α in bronchoalveolar lavage fluid were measured by enzyme-linked immunosorbent assay(ELISA). The results showed that the decoction of the Coptidis Rhizoma-Scutellariae Radix significantly reduced pulmonary edema, alleviated lung injury, and decreased the concentrations of related cytokines in BALF more effectively than either single herb alone, thereby improving CSSLI. In vitro, a CpG1826-induced CSSLI model was established in mouse alveolar macrophage MH-S cells. Calcein-AM quenching was used to screen for the most effective monomer components from the herb pair in inhibiting mPTP opening. Coptisine(5, 10, 20 μmol·L~(-1)) and wogonin(10, 20, 40 μmol·L~(-1)) markedly inhibited mPTP opening, with optimal effects and a clear dose-dependent pattern. These components suppressed mPTP opening, thereby reducing the release of mitochondrial DNA(mtDNA) and the accumulation of reactive oxygen species(ROS), effectively reversing the CpG1826-induced decrease in mitochondrial membrane potential(MMP). Further studies revealed that both coptisine and wogonin inhibited pyroptosis and downregulated the expression of key proteins in the NLRP3/Caspase-1/gasdermin D(GSDMD) pathway. In conclusion, the Coptidis Rhizoma-Scutellariae Radix improves CpG1826-induced CSSLI in mice, and this effect is associated with the inhibition of the mPTP/NLRP3 pyroptosis pathway, providing scientific evidence for its clinical application and further development.
Animals
;
Mice
;
Drugs, Chinese Herbal/administration & dosage*
;
Pyroptosis/drug effects*
;
NLR Family, Pyrin Domain-Containing 3 Protein/immunology*
;
Male
;
Lung Injury/immunology*
;
Cytokines/immunology*
;
Scutellaria baicalensis/chemistry*
;
Oligodeoxyribonucleotides/adverse effects*
;
Mice, Inbred C57BL
;
Coptis chinensis
9.Effectiveness of Xuanshen Yishen Decoction on Intensive Blood Pressure Control: Emulation of a Randomized Target Trial Using Real-World Data.
Xiao-Jie WANG ; Yuan-Long HU ; Jia-Ming HUAN ; Shi-Bing LIANG ; Lai-Yun XIN ; Feng JIANG ; Zhen HUA ; Zhen-Yuan WANG ; Ling-Hui KONG ; Qi-Biao WU ; Yun-Lun LI
Chinese journal of integrative medicine 2025;31(8):677-684
OBJECTIVE:
To investigate the effectiveness of Xuanshen Yishen Decoction (XYD) in the treatment of hypertension.
METHODS:
Hospital electronic medical records from 2019-2023 were utilized to emulate a randomized pragmatic clinical trial. Hypertensive participants were eligible if they were aged ⩾40 years with baseline systolic blood pressure (BP) ⩾140 mm Hg. Patients treated with XYD plus antihypertensive regimen were assigned to the treatment group, whereas those who followed only antihypertensive regimen were assigned to the control group. The primary outcome assessed was the attainment rate of intensive BP control at discharge, with the secondary outcome focusing on the 6-month all-cause readmission rate.
RESULTS:
The study included 3,302 patients, comprising 2,943 individuals in the control group and 359 in the treatment group. Compared with the control group, a higher proportion in the treatment group achieved the target BP for intensive BP control [8.09% vs. 17.5%; odds ratio (OR)=2.29, 95% confidence interval (CI)=1.68 to 3.13; P<0.001], particularly in individuals with high homocysteine levels (OR=3.13; 95% CI=1.72 to 5.71; P<0.001; P for interaction=0.041). Furthermore, the 6-month all-cause readmission rate in the treatment group was lower than in the control group (hazard ratio=0.58; 95% CI=0.36 to 0.91; P=0.019), and the robustness of the results was confirmed by sensitivity analyse.
CONCLUSIONS
XYD could be a complementary therapy for intensive BP control. Our study offers real-world evidence and guides the choice of complementary and alternative therapies. (Registration No. ChiCTR2400086589).
Adult
;
Aged
;
Female
;
Humans
;
Male
;
Middle Aged
;
Antihypertensive Agents/pharmacology*
;
Blood Pressure/drug effects*
;
Drugs, Chinese Herbal/pharmacology*
;
Hypertension/physiopathology*
;
Patient Readmission
;
Treatment Outcome
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