基于机器学习的宫颈高级别鳞状上皮内病变（HSIL）风险分层管理研究

宫颈高等级鳞状上皮内病变（HSIL）经锥切术与阴道镜引导活检（CDB）证实的一致率为64-85%。本研究旨在识别与宫颈HSIL患者锥切术后病理升级或降级相关的风险因素，并基于机器学习预测模型提供风险分层管理。为此，回顾性分析了2019年1月1日至12月31日期间就诊于复旦大学妇产科医院、经CDB诊断为宫颈HSIL并接受锥切术的患者的资料，包括人口学信息、实验室检查、阴道镜描述及病理结果。患者依据锥切术后病理结果分为三组：低级别鳞状上皮内病变（LSIL）或以下（降级组）、HSIL（HSIL组）及宫颈癌（升级组）。采用单变量和多变量分析识别影响病理变化的独立风险因素，建立、评估并用外部测试数据验证了多种机器学习预测模型。共纳入1585例患者，其中65例（4.1%）锥切后升级为宫颈癌，1147例（72.4%）病理仍为HSIL，373例（23.5%）降级至LSIL或以下。多变量分析显示，每增加一岁，病理降级的发生率降低2%，病变面积每增加一单位，下降风险增加1%。在具有细胞学>LSIL（比值比[OR]=0.33；95%置信区间[CI]，0.21-0.52）、人乳头瘤病毒（HPV）感染（OR=0.33；95%CI，0.14-0.81）、HPV 33感染（OR=0.37；95%CI，0.18-0.78）、阴道镜检查中粗大点状血管（OR=0.14；95%CI，0.06-0.32）、宫颈管内HSIL（OR=0.48；95%CI，0.30-0.76）以及HSIL印象（OR=0.02；95%CI，0.01-0.03）的患者，其病理降级的可能性较低。影响锥切术后病理升级为宫颈癌的独立风险因素包括：年龄（OR=1.08；95%CI，1.04-1.12）、HPV 16感染（OR=4.07；95%CI，1.70-9.78）、阴道镜检查中粗大点状血管的存在（OR=2.21；95%CI，1.08-4.50）、非典型血管（OR=6.87；95%CI，2.81-16.83）以及宫颈管内HSIL（OR=2.91；95%CI，1.46-5.77）。六种机器学习模型中，反向传播（BP）神经网络模型在降级、HSIL及升级组表现出最高且最为均匀的预测性能，其曲线下面积（AUC）分别为0.90、0.84和0.69；敏感性分别为0.74、0.84和0.42；特异性分别为0.90、0.71和0.95；准确率分别为0.74、0.84和0.95。在外部测试集中，BP神经网络模型的预测性能优于逻辑回归模型，总体AUC达0.91。因此，本研究开发了基于网络的预测工具。BP神经网络模型具有优异的预测性能，可用于CDB诊断的HSIL患者的风险分层管理。

The concordance rate between conization and colposcopy-directed biopsy (CDB) proven cervical high-grade squamous intraepithelial lesion (HSIL) were 64-85%. We aimed to identify the risk factors associated with pathological upgrading or downgrading after conization in patients with cervical HSIL and to provide risk-stratified management based on a machine learning predictive model. This retrospective study included patients who visited the Obstetrics and Gynecology Hospital of Fudan University from January 1 to December 31, 2019, were diagnosed with cervical HSIL by CDB, and subsequently underwent conization. A wide variety of data were collected from the medical records, including demographic data, laboratory findings, colposcopy descriptions, and pathological results. The patients were categorized into three groups according to their postconization pathological results: low-grade squamous intraepithelial lesion (LSIL) or below (downgrading group), HSIL (HSIL group), and cervical cancer (upgrading group). Univariate and multivariate analyses were performed to identify the independent risk factors for pathological changes in patients with cervical HSIL. Machine learning prediction models were established, evaluated, and subsequently verified using external testing data. In total, 1585 patients were included, of whom 65 (4.1%) were upgraded to cervical cancer after conization, 1147 (72.4%) remained having HSIL, and 373 (23.5%) were downgraded to LSIL or below. Multivariate analysis showed a 2% decrease in the incidence of pathological downgrade for each additional year of age and a 1% increase in lesion size. Patients with cytology > LSIL (odds ratio [OR] = 0.33; 95% confidence interval [CI], 0.21-0.52), human papillomavirus (HPV) infection (OR = 0.33; 95% CI, 0.14-0.81), HPV 33 infection (OR = 0.37; 95% CI, 0.18-0.78), coarse punctate vessels on colposcopy examination (OR = 0.14; 95% CI, 0.06-0.32), HSIL lesions in the endocervical canal (OR = 0.48; 95% CI, 0.30-0.76), and HSIL impression (OR = 0.02; 95% CI, 0.01-0.03) were less likely to experience pathological downgrading after conization than their counterparts. The independent risk factors for pathological upgrading to cervical cancer after conization included the following: age (OR = 1.08; 95% CI, 1.04-1.12), HPV 16 infection (OR = 4.07; 95% CI, 1.70-9.78), the presence of coarse punctate vessels during colposcopy examination (OR = 2.21; 95% CI, 1.08-4.50), atypical vessels (OR = 6.87; 95% CI, 2.81-16.83), and HSIL lesions in the endocervical canal (OR = 2.91; 95% CI, 1.46-5.77). Among the six machine learning prediction models, the back propagation (BP) neural network model demonstrated the highest and most uniform predictive performance in the downgrading, HSIL, and upgrading groups, with areas under the curve (AUCs) of 0.90, 0.84, and 0.69; sensitivities of 0.74, 0.84, and 0.42; specificities of 0.90, 0.71, and 0.95; and accuracies of 0.74, 0.84, and 0.95, respectively. In the external testing set, the BP neural network model showed a higher predictive performance than the logistic regression model, with an overall AUC of 0.91. Therefore, a web-based prediction tool was developed in this study. BP neural network prediction model has excellent predictive performance and can be used for the risk stratification of patients with CDB-diagnosed HSIL.