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

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 as...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongmei Li, Zhichao Wang, Yan Liu, Meiyuan Zhou, Bo Xia, Lin Zhang, Keming Chen, Yong Zeng
Format: Article
Language:English
Published: BMC 2024-12-01
Series:Infectious Agents and Cancer
Subjects:
Online Access:https://doi.org/10.1186/s13027-024-00625-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846137250046279680
author Dongmei Li
Zhichao Wang
Yan Liu
Meiyuan Zhou
Bo Xia
Lin Zhang
Keming Chen
Yong Zeng
author_facet Dongmei Li
Zhichao Wang
Yan Liu
Meiyuan Zhou
Bo Xia
Lin Zhang
Keming Chen
Yong Zeng
author_sort Dongmei Li
collection DOAJ
description 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.
format Article
id doaj-art-0a56fa12307144bd8b35f2d069610f7d
institution Kabale University
issn 1750-9378
language English
publishDate 2024-12-01
publisher BMC
record_format Article
series Infectious Agents and Cancer
spelling doaj-art-0a56fa12307144bd8b35f2d069610f7d2024-12-08T12:19:10ZengBMCInfectious Agents and Cancer1750-93782024-12-0119111210.1186/s13027-024-00625-zAssessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based studyDongmei Li0Zhichao Wang1Yan Liu2Meiyuan Zhou3Bo Xia4Lin Zhang5Keming Chen6Yong Zeng7Department of Obstetrics and Gynecology, The First Affiliated Hospital of Yangtze UniversityOncology Department, The First Affiliated Hospital of Yangtze UniversityNeurology Intensive Care Unit, The First Affiliated Hospital of Yangtze UniversityPathology Department, The First Affiliated Hospital of Yangtze UniversityPathology Department, The First Affiliated Hospital of Yangtze UniversityDepartment of Obstetrics and Gynecology, The First Affiliated Hospital of Yangtze UniversityDepartment of Obstetrics and Gynecology, The First Affiliated Hospital of Yangtze UniversityDepartment of Obstetrics and Gynecology, The First Affiliated Hospital of Yangtze UniversityAbstract 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.https://doi.org/10.1186/s13027-024-00625-zLSILHSILMissed diagnosisPredictive modelMachine learningColposcopic biopsy
spellingShingle Dongmei Li
Zhichao Wang
Yan Liu
Meiyuan Zhou
Bo Xia
Lin Zhang
Keming Chen
Yong Zeng
Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
Infectious Agents and Cancer
LSIL
HSIL
Missed diagnosis
Predictive model
Machine learning
Colposcopic biopsy
title Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
title_full Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
title_fullStr Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
title_full_unstemmed Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
title_short Assessing the risk of high-grade squamous intraepithelial lesions (HSIL+) in women with LSIL biopsies: a machine learning-based study
title_sort assessing the risk of high grade squamous intraepithelial lesions hsil in women with lsil biopsies a machine learning based study
topic LSIL
HSIL
Missed diagnosis
Predictive model
Machine learning
Colposcopic biopsy
url https://doi.org/10.1186/s13027-024-00625-z
work_keys_str_mv AT dongmeili assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT zhichaowang assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT yanliu assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT meiyuanzhou assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT boxia assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT linzhang assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT kemingchen assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy
AT yongzeng assessingtheriskofhighgradesquamousintraepitheliallesionshsilinwomenwithlsilbiopsiesamachinelearningbasedstudy