Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study.

IF 3.1 2区医学 Q3 IMMUNOLOGY

Infectious Agents and Cancer Pub Date : 2024-12-05 DOI:10.1186/s13027-024-00625-z

Dongmei Li, Zhichao Wang, Yan Liu, Meiyuan Zhou, Bo Xia, Lin Zhang, Keming Chen, Yong Zeng

{"title":"Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study.","authors":"Dongmei Li, Zhichao Wang, Yan Liu, Meiyuan Zhou, Bo Xia, Lin Zhang, Keming Chen, Yong Zeng","doi":"10.1186/s13027-024-00625-z","DOIUrl":null,"url":null,"abstract":"Objective: This study aims to analyze factors associated with the missed diagnosis of high-grade squamous intraepithelial lesions (HSIL+) in patients initially diagnosed with low-grade squamous intraepithelial lesions (LSIL) through colposcopic biopsy and to develop a predictive model for assessing the risk of missed HSIL+.Methods: We conducted a retrospective analysis of 505 patients who underwent loop electrical excision procedure (LEEP) following an LSIL diagnosis by colposcopic biopsy. Logistic regression was used to identify demographic and pathological parameters associated with missed diagnoses of HSIL+. Additionally, several machine learning methods were employed to construct and assess the performance of the risk prediction models.Results: The overall rate of missed diagnoses for HSIL+ was 15.2%. Independent risk factors identified were HPV16/18 infection (OR 2.071; 95% CI 1.039-4.127; p = 0.039), TCT ≥ ASC-H (OR 4.147; 95% CI 1.392-12.355; p = 0.011), TZ3 (OR 1.966; 95% CI 1.003-3.853; p = 0.049) and Colposcopic impression G2 (OR 3.627; 95% CI 1.350-9.743; p = 0.011). Among the models tested, the Decision Tree algorithm demonstrated superior performance with an accuracy of 94.7%, sensitivity of 80.0%, specificity of 96.9%, and an area under the curve (AUC) of 0.936 in the validation set.Conclusion: Key independent risk factors for the missed diagnosis of HSIL in patients with LSIL include HPV16/18 infection, TCT ≥ ASC-H, TZ3, and colposcopic impression G2. The Decision Tree model offers a cost-effective, reliable, and clinically valuable tool for accurately predicting the risk of missed diagnosis of HSIL+, facilitating early intervention and management.","PeriodicalId":13568,"journal":{"name":"Infectious Agents and Cancer","volume":"19 1","pages":"61"},"PeriodicalIF":3.1000,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11622471/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Infectious Agents and Cancer","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13027-024-00625-z","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"IMMUNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: This study aims to analyze factors associated with the missed diagnosis of high-grade squamous intraepithelial lesions (HSIL+) in patients initially diagnosed with low-grade squamous intraepithelial lesions (LSIL) through colposcopic biopsy and to develop a predictive model for assessing the risk of missed HSIL+.

Methods: We conducted a retrospective analysis of 505 patients who underwent loop electrical excision procedure (LEEP) following an LSIL diagnosis by colposcopic biopsy. Logistic regression was used to identify demographic and pathological parameters associated with missed diagnoses of HSIL+. Additionally, several machine learning methods were employed to construct and assess the performance of the risk prediction models.

Results: The overall rate of missed diagnoses for HSIL+ was 15.2%. Independent risk factors identified were HPV16/18 infection (OR 2.071; 95% CI 1.039-4.127; p = 0.039), TCT ≥ ASC-H (OR 4.147; 95% CI 1.392-12.355; p = 0.011), TZ3 (OR 1.966; 95% CI 1.003-3.853; p = 0.049) and Colposcopic impression G2 (OR 3.627; 95% CI 1.350-9.743; p = 0.011). Among the models tested, the Decision Tree algorithm demonstrated superior performance with an accuracy of 94.7%, sensitivity of 80.0%, specificity of 96.9%, and an area under the curve (AUC) of 0.936 in the validation set.

Conclusion: Key independent risk factors for the missed diagnosis of HSIL in patients with LSIL include HPV16/18 infection, TCT ≥ ASC-H, TZ3, and colposcopic impression G2. The Decision Tree model offers a cost-effective, reliable, and clinically valuable tool for accurately predicting the risk of missed diagnosis of HSIL+, facilitating early intervention and management.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Infectious Agents and Cancer ONCOLOGY-IMMUNOLOGY

CiteScore

5.80

自引率

2.70%

发文量

期刊介绍： Infectious Agents and Cancer is an open access, peer-reviewed online journal that encompasses all aspects of basic, clinical, epidemiological and translational research providing an insight into the association between chronic infections and cancer. The journal welcomes submissions in the pathogen-related cancer areas and other related topics, in particular: • HPV and anogenital cancers, as well as head and neck cancers; • EBV and Burkitt lymphoma; • HCV/HBV and hepatocellular carcinoma as well as lymphoproliferative diseases; • HHV8 and Kaposi sarcoma; • HTLV and leukemia; • Cancers in Low- and Middle-income countries. The link between infection and cancer has become well established over the past 50 years, and infection-associated cancer contribute up to 16% of cancers in developed countries and 33% in less developed countries. Preventive vaccines have been developed for only two cancer-causing viruses, highlighting both the opportunity to prevent infection-associated cancers by vaccination and the gaps that remain before vaccines can be developed for other cancer-causing agents. These gaps are due to incomplete understanding of the basic biology, natural history, epidemiology of many of the pathogens that cause cancer, the mechanisms they exploit to cause cancer, and how to interrupt progression to cancer in human populations. Early diagnosis or identification of lesions at high risk of progression represent the current most critical research area of the field supported by recent advances in genomics and proteomics technologies.