1.Prenatal diagnosis of 22q11.2 microduplication syndrome in a three-generation family: Clinical-genetic characteristics and literature review.
Yifan LIAO ; Yidong WEN ; Xiaoqin DENG ; Cimo WANG ; Zhirong SHANG ; Jinghong YANG ; Jiabing LI
Chinese Journal of Medical Genetics 2026;43(1):57-63
OBJECTIVE:
To explore the genetic etiology for a pregnant woman with a history of multiple adverse pregnancies and assess the phenotype-genotype correlation of 22q11.2 microduplication syndrome in her family.
METHODS:
Amniotic fluid sample was taken from a pregnant woman for whom non-invasive prenatal screening indicated chromosome 22 abnormalities in the fetus. Peripheral blood samples from the woman, her brother and parents were collected for high-throughput low-depth whole genome sequencing (CNV-seq). A pedigree traceability analysis of the results was conducted in conjunction with analysis of clinical manifestation. Relevant literature (from establishment to March 2025) was systematically searched. This study was approved by the Medical Ethics Committee of Mianyang Maternal and Child Health Care Hospital (Ethics No.: Lun Shen [2024]009).
RESULTS:
CNV-seq revealed that the fetus had harbored a 6.02 Mb duplication at 22q11.21q11.23. Karyotyping confirmed it as 46,X?dup(22)(q11.2). Pedigree verification demonstrated that the pregnant woman, her brother and mother had all carried the same duplication. Phenotypic analysis of the affected family members showed classic features of 22q11.2 microduplication syndrome, including hypernasal speech, low nasal bridge, congenital heart disease, and cognitive impairment. A total of 44 cases with full information (including three patients from this pedigree) were included in the analysis. The penetrance of 22q11.2 duplication was approximately 29.5% (13/44), and 52.3% (23/44) of the cases had inherited the variant from a phenotypically normal parent.
CONCLUSION
This study has identified the genetic basis for the woman's recurrent adverse pregnancies and phenotypic abnormalities in her family members. The scoliosis identified in her younger brother has not been previously reported, thereby may enrich the clinical phenotype of this syndrome. For fetuses identified with a 22q11.2 microduplication, detailed fetal imaging is recommended, and genetic counseling should be provided to the couples.
Humans
;
Female
;
Pregnancy
;
Prenatal Diagnosis/methods*
;
Chromosome Duplication/genetics*
;
Male
;
Pedigree
;
DiGeorge Syndrome/diagnosis*
;
Adult
;
Chromosomes, Human, Pair 22/genetics*
;
Abnormalities, Multiple
2.Fourth national survey of traditional Chinese medicine resources and protection of traditional knowledge of medication use among ethnic minorities.
Jiang-Wei DU ; Xiao-Bo ZHANG ; Jian-Zhi CUI ; Shao-Hua YANG ; Hai-Tao LI ; Zhi-Yong LI ; Lu-Qi HUANG
China Journal of Chinese Materia Medica 2025;50(9):2349-2355
Traditional Chinese medicine(TCM) resources are the essential material foundation for the development of TCM. The national survey of TCM resources serves as a periodic summary of these resources, ensuring the continuity, prosperity, and development of TCM in China. Since 1949, four national surveys of TCM resources have been conducted. The fourth survey incorporated an investigation into traditional knowledge related to TCM resources, including the traditional medicinal knowledge of Chinese ethnic minorities, with the goal of systematically exploring, preserving, and inheriting this knowledge. This manuscript provides an overview of the basic findings from the first three national surveys of TCM resources, while also clarifying the concepts, categories, forms, carriers, and acquisition pathways of traditional knowledge related to TCM resources. A preliminary summary of the findings from traditional knowledge investigations reported in current literature is also presented. Based on the fourth survey, this manuscript emphasizes the urgency of developing public medical knowledge through empirically-based investigations, the excavation, and compilation of traditional knowledge. It also outlines the potential for conducting "precise" investigations based on first-hand data obtained from the survey, as well as facilitating the discovery and evaluation of new medicines using traditional knowledge related to ethnic minority medicinal practices. This manuscript is expected to provide valuable insights for promoting the health and industrial development of ethnic minority populations in the post-"survey" phase.
Humans
;
Medicine, Chinese Traditional
;
China/ethnology*
;
Minority Groups
;
Ethnicity
;
Drugs, Chinese Herbal/therapeutic use*
;
Health Knowledge, Attitudes, Practice/ethnology*
;
Surveys and Questionnaires
3.Advances in mechanotransduction signaling pathways in distraction osteogenesis.
Jinghong YANG ; Lujun JIANG ; Zi WANG ; Zhong LI ; Yanshi LIU
Chinese Journal of Reparative and Reconstructive Surgery 2025;39(7):912-918
OBJECTIVE:
To review the role and research progress of mechanotransduction signaling pathway in distraction osteogenesis, so as to provide theoretical basis and reference for clinical treatment.
METHODS:
The role and research progress of mechanotransduction signaling pathway in distraction osteogenesis were summarized by extensive review of relevant literature at home and abroad.
RESULTS:
The mechanotransduction signaling pathway plays a central role of "sensation-transformation-execution" in distraction osteogenesis, and activates a series of molecular mechanisms to promote the regeneration and remodeling of bone tissue by integrating external mechanical signals. Mechanical stimuli are converted into mechanotransduction signals through the perception of integrins, Piezo1 ion channels and bone cell networks. Activate downstream molecules are transduce through signal pathways such as Wnt/β-catenin, transforming growth factor β/bone morphogenetic protein-Smad, mitogen-activated protein kinase, protein kinase Hippo-Yes-associated protein/transcriptional coactivator with PDZ-binding motif, and phosphatidylinositol 3-kinase/ protein kinase B, so as to achieve the effects of promoting osteoblasts proliferation, accelerating endochondral ossification, regulating bone resorption and the like, thereby promoting the regeneration of new bone in the distraction area. The study of mechanotransduction signaling pathways in distraction osteogenesis is expected to optimize the mechanical parameters of distraction osteogenesis and provide targeted intervention strategies for accelerating new bone regeneration and mineralization in the distraction zone. However, the specific mechanism of mechanotransduction signaling pathway in distraction osteogenesis remains to be further elucidated, and artificial intelligence and multi-omics analysis may be the future development direction of mechanotransduction signaling pathway.
CONCLUSION
In distraction osteogenesis, mechanotransduction signal transduction is the core mechanism of bone regeneration in the distraction zone, which regulates cell behavior and tissue regeneration by converting mechanical stimulation into biochemical signals.
Mechanotransduction, Cellular/physiology*
;
Osteogenesis, Distraction/methods*
;
Humans
;
Signal Transduction
;
Bone Regeneration
;
Animals
;
Osteoblasts/metabolism*
;
Osteogenesis
;
Transforming Growth Factor beta/metabolism*
;
Ion Channels/metabolism*
;
Integrins/metabolism*
;
beta Catenin/metabolism*
;
Bone Morphogenetic Proteins/metabolism*
;
Smad Proteins/metabolism*
4.Photodynamic enhancement of PROTAC prodrug activation in hypoxic tumors.
Zhongliang FU ; Chunrong YANG ; Yuchen YANG ; Meichen PAN ; Hongwei HOU ; Jinghong LI
Acta Pharmaceutica Sinica B 2025;15(9):4945-4960
Proteolysis-targeting chimeras (PROTACs) have emerged as a promising therapeutic strategy for targeted protein degradation. However, the clinical application of PROTACs may be hindered by off-target toxicity resulting from non-tissue-specific protein degradation and ingenious prodrug strategies may open new avenues to addressing this concern. Herein, we propose a light-induced positive feedback strategy to use photodynamic therapy (PDT) to improve the activation efficiency of PROTAC prodrugs, monitor PROTAC release, and combine PROTAC to induce tumor cell apoptosis. In the hypoxic tumor microenvironment, the azo bond in AZO-PRO selectively cleaves, triggering the release of the potent protein degrader PRO and the multifunctional photosensitizer. Once activated, the fluoresce signal of the photosensitizer dramatically recovers, allowing monitoring of prodrug activation. Additionally, upon irradicating the tumor site using near-infrared (NIR) laser, PDT exacerbates tumor hypoxia, further promoting AZO-PRO activation. Our work introduces a novel approach to efficiently track and activate PROTAC prodrugs, enhance their antitumor efficacy, and mitigate off-target systemic toxicity.
5.Epidemiological characteristics of surgical site infection outbreaks at home and abroad
Lanping SHI ; Mengru LI ; Ping ZHOU ; Jianyun CHEN ; Jinghong YU ; Yuhua GAO ; Yang LI
Chinese Journal of Nosocomiology 2025;35(20):3063-3067
OBJECTIVE To analyze the characteristics of global surgical site infection(SSI)outbreaks and provide references for targeted prevention and control measures.METHODS SSI outbreak events from Jan.1,1990 to Dec.31,2023 were searched from Wanfang Med,CNKI,VIP and PubMed.Data on department distribution dur-ing the outbreak,duration,investigation methods,main causes,transmission modes,pathogen composition and outbreak outcomes were summarized for analysis.RESULTS A total of 111 SSI outbreaks in 20 countries were identi-fied,involving 1 382 patients and 24 deaths.The source of the outbreak was identified in 78 cases,mainly involving med-ical personnel in 27 cases(34.62%),hospital equipment in 19 cases(24.36%),environmental factors in 11 cases(14.10%),workflow factors in 10 cases(12.82%),hospital water factors in 7 cases(8.97%)and disinfectant fac-tors in 4 cases(5.13%).The duration of SSI outbreaks abroad was 5.00(1.50,12.00)months,longer than that in China[1.00(1.00,2.00)month](P<0.05).In China,the outbreaks mainly occurred in neurosurgery,cardiac surger-y,orthopedics,obstetrics and general surgery,while at abroad,they mainly occurred in cardiac surgery,orthopedics,and involved multiple surgical departments.Environmental hygiene methods were adopted in up to 90.63%of cases in China.Compared with China,analytical epidemiological methods and molecular epidemiological methods were more com-monly used abroad.Targeted measures and strengthened basic measures were implemented for different outbreak sources to terminate the SSI outbreaks.Pulsed-field gel electrophoresis(34 times)was a widely used molecular typing method in outbreak investigations.CONCLUSIONS Based on the analysis of SSI outbreak characteristics and risk factors,it is neces-sary to strengthen medical personnel training and monitoring of special pathogens.At the same time,the epidemiologi-cal investigation capabilities of infection control professionals should be strengthened.
6.Oxoglutarate dehydrogenase-L regulates mitochondrial metabolism reprogramming of renal tubular epithelial cells to alleviate renal fibrosis
Yingxian YANG ; Yinghui HUANG ; Jinghong ZHAO
Journal of Army Medical University 2025;47(11):1145-1154
Objective To investigate the role and underlying mechanisms of oxoglutarate dehydrogenase-L(OGDHL)in renal fibrosis.Methods Twelve male wild-type C57BL/6J mice(8 weeks old,weighting about 25 g)were randomly divided into control group and model group(n=6).A mouse model of renal fibrosis was established by unilateral ureteral obstruction(UUO).HE staining,immunofluorescence assay,and immunohistochemical and Masson staining were applied to assess the extent of renal fibrosis.Human kidney-2 proximal tubule cell line(HK-2)were randomly divided into blank plasmid group(Vector),OGDHL overexpression group(OGDHL OE),blank plasmid+TGF-β1 treatment group(TGF-β1+Vector),TGF-β1 treatment and OGDHL overexpression group(TGF-β1+OGDHL OE).Transmission electron microscopy(TEM)was employed to observe mitochondrial morphology.RT-qPCR,Western blotting and immunofluorescence assay were used to detect the expression levels of OGDHL and mitochondrial metabolism-related genes.Adenosine triphosphate(ATP)level,oxygen consumption rate(OCR),extracellular acidification rate(ECAR)and other mitochondrial metabolism-related indicators were detected with corresponding reagent kits and Agilent Seahorse.Results UUO operation resulted in obvious thinning of the renal cortex,significant hydronephrosis.HE staining revealed that tubular atrophy accompanied by dilated tubular lumens in the kidneys.Immunofluorescence,immunohistochemical and Masson staining showed obvious renal fibrosis after UUO operation.In the mouse model of renal fibrosis,the expression of OGDHL was decreased by 82.9%at mRNA level(P<0.001)and 81.9%at protein level(P<0.001),the production of mitochondrial ATP was reduced by 0.970±0.151 μmol/L(P<0.01),and notable damaged mitochondrial structure was observed,with maximum breathing capacity decreased by 25.260±1.920 pmol/min(P<0.001),expression levels of fatty acid oxidation-related genes were declined by 50.2%(P<0.05),while glycolysis was enhanced,with the genes related to glycolysis increased by 2.5 times when compared with those in the control group(P<0.05).After OGDHL overexpression,mitochondrial morphological damage was significantly improved,ATP production was increased by 0.980±0.090 μmol/L(P<0.05),with significantly alleviated energy metabolism disorder and renal fibrosis(P<0.05).Conclusion OGDHL regulates mitochondrial metabolic reprogramming of renal tubular epithelial cells to alleviate fibrosis,suggesting that OGDHL may be a new therapeutic target for renal fibrosis.
7.Analyses on the knockdown resistance gene mutations in Aedes aegypti in Jinghong City of Yunnan Province
Zhengshan CHENG ; Li CHEN ; Yang GAO ; Jing HE ; Jianhong ZOU ; Litao TAN ; Binghui WANG ; Jinyong JIANG
Shanghai Journal of Preventive Medicine 2025;37(12):1034-1038
ObjectiveTo analyze the temporal trend of knockdown resistance (kdr) gene mutations highly correlated with pyrethroid resistance in field populations of Aedes aegypti in Jinghong City of Yunnan Province, and to provide a scientific basis for formulating rational insecticide use strategies. MethodsAdult mosquito samples of Aedes aegypti from 2016 to 2023 and larvae mosquito samples from July 2022 to June 2023 were collected in Jinghong City of Yunnan Province. Allele specific PCR (AS-PCR) was used to measure kdr mutations at amino acid positions 989, 1016 and 1534 of the voltage-gated sodium ion channel (VGSC) gene. Data such as mutation rate and mutation allele frequency were calculated, SPSS software was used to perform trend chi square tests on mutation rate and mutation allele frequency with year and month, as well as comparison of mutation allele frequencies and genotype distributions between the dry and rainy seasons, thereby delineating the temporal trend of kdr gene mutations. ResultsAmong the 173 samples collected from 2016 to 2023, the mutation rates of S989P and V1016G were 100.00% for each year, while the mutation rate of F1534C ranged from 62.50% to 100.00%. The mutation rate and mutation allele frequency of F1534C were increased over the years (χ2=22.079, P<0.001; χ2=42.971, P<0.001). Concurrently, the proportion of the PPGGCC genotype was increased annually (χ2=60.790, P<0.001). Among the 288 samples collected from July 2022 to June 2023, the monthly mutation rates for S989P, V1016G, and F1534C were consistently 100.00%. There was only one type of mutation present, namely S989P+V1016G+F1534C. In the combinations of the three genotypes, the SPGGCC genotype accounted for 1.39% (4/288), the PPGGFC accounted for 2.78% (8/288), and the PPGGCC had the highest proportion at 95.83% (276/288). After tesiting the samples collected in August 2023, the mutation rates of 989, 1016 and 1534 sites of VGSC in females, males, and larvae of the same generation were all 100.00%. ConclusionSince 2016, the gene mutations at S989P and V1016G loci in the VGSC gene of wild Aedes aegypti in Jinghong City have remained consistently at 100.00%, while the mutation rate and mutant allele frequency of F1534C have increased year by year during the testing period. By 2023, the mutation rates at three loci in the VGSC gene of Aedes aegypti in Jinghong City had all reached 100.00%, and neither changes in insect developmental stage nor gender differences during transmission exerted a detectable impact on the mutation rates. In the control of Aedes aegypti in Jinghong City, the use of pyrethroid insecticides should be stopped or reduced, and regular monitoring of kdr genes should be carried out to promptly detect new mutations.
8.Construction and preliminary validation of machine learning predictive models for cervical cancer screening based on human DNA methylation
Yuan YANG ; Hang ZHOU ; Yakun WANG ; Yu DAI ; Ruoji PI ; Hua ZHANG ; Ziyue HUANG ; Ting WU ; Jinghong YANG ; Wen CHEN
Chinese Journal of Oncology 2025;47(2):193-200
Objective:Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions.Methods:Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis.Results:In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P>0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P<0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P<0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion:Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.
9.Epidemiological characteristics of surgical site infection outbreaks at home and abroad
Lanping SHI ; Mengru LI ; Ping ZHOU ; Jianyun CHEN ; Jinghong YU ; Yuhua GAO ; Yang LI
Chinese Journal of Nosocomiology 2025;35(20):3063-3067
OBJECTIVE To analyze the characteristics of global surgical site infection(SSI)outbreaks and provide references for targeted prevention and control measures.METHODS SSI outbreak events from Jan.1,1990 to Dec.31,2023 were searched from Wanfang Med,CNKI,VIP and PubMed.Data on department distribution dur-ing the outbreak,duration,investigation methods,main causes,transmission modes,pathogen composition and outbreak outcomes were summarized for analysis.RESULTS A total of 111 SSI outbreaks in 20 countries were identi-fied,involving 1 382 patients and 24 deaths.The source of the outbreak was identified in 78 cases,mainly involving med-ical personnel in 27 cases(34.62%),hospital equipment in 19 cases(24.36%),environmental factors in 11 cases(14.10%),workflow factors in 10 cases(12.82%),hospital water factors in 7 cases(8.97%)and disinfectant fac-tors in 4 cases(5.13%).The duration of SSI outbreaks abroad was 5.00(1.50,12.00)months,longer than that in China[1.00(1.00,2.00)month](P<0.05).In China,the outbreaks mainly occurred in neurosurgery,cardiac surger-y,orthopedics,obstetrics and general surgery,while at abroad,they mainly occurred in cardiac surgery,orthopedics,and involved multiple surgical departments.Environmental hygiene methods were adopted in up to 90.63%of cases in China.Compared with China,analytical epidemiological methods and molecular epidemiological methods were more com-monly used abroad.Targeted measures and strengthened basic measures were implemented for different outbreak sources to terminate the SSI outbreaks.Pulsed-field gel electrophoresis(34 times)was a widely used molecular typing method in outbreak investigations.CONCLUSIONS Based on the analysis of SSI outbreak characteristics and risk factors,it is neces-sary to strengthen medical personnel training and monitoring of special pathogens.At the same time,the epidemiologi-cal investigation capabilities of infection control professionals should be strengthened.
10.Construction and preliminary validation of machine learning predictive models for cervical cancer screening based on human DNA methylation
Yuan YANG ; Hang ZHOU ; Yakun WANG ; Yu DAI ; Ruoji PI ; Hua ZHANG ; Ziyue HUANG ; Ting WU ; Jinghong YANG ; Wen CHEN
Chinese Journal of Oncology 2025;47(2):193-200
Objective:Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions.Methods:Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis.Results:In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P>0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P<0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P<0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion:Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.

Result Analysis
Print
Save
E-mail