| 234 | 0 | 58 |
| 下载次数 | 被引频次 | 阅读次数 |
目的 评估人工智能（AI）辅助宫颈液基细胞学（TCT）模型在基层医疗机构真实世界筛查环境中的适应性与局限性，探讨其在不同病变类型、筛查流程及医生接受度等方面的表现，为优化宫颈癌筛查策略提供依据。方法 采用前瞻性对照研究设计，于福建中医药大学附属第二人民医院及管辖社区医院招募宫颈癌筛查女性1 200例，分别进行AI辅助判读、人工阅片及“AI+人工协同”3组判读。以HPV检测和组织病理为参考标准，评估3组在≥CIN2病变识别中的灵敏度、特异度、阴性预测值（NPV）、阅片时间及误判类型。同步开展医生结构化问卷调查与访谈，评估AI系统在使用便利性、判读信任度及操作干扰等方面的主观体验。结果 AI模型在≥CIN2病变识别中的灵敏度为92.8%，特异度为86.5%,NPV为97.6%，可有效预排阴性切片，平均阅片时间为11.5 s。人工组（A组）灵敏度91.2%、特异度89.3%、NPV96.4%、平均阅片时间94.2 s。人机协同组的灵敏度进一步提升至95.3%，假阴性率最低。AI在AGC、混合型病变及稀有细胞类型中仍存在误判倾向。医生调查显示82%认为AI能提高工作效率，78%认可其对低级别病变的预警价值，但仍有56%表示在界限病变中依赖人工复核。结论 AI辅助宫颈细胞学模型在真实基层筛查环境中展现出良好的效率与初筛能力，特别适合大样本快速分流和阴性排除。AI模型适合基层快速分流，复杂病变需人工复核，人机协同模式是优化筛查质量的可行策略。
Abstract：Objective To evaluate the adaptability and limitations of an artificial intelligence(AI)-assisted thin-prep cytology test(TCT) model in real-world screening settings of primary care institutions, and to explore its performance across different lesion types, screening processes, and physician acceptance, aiming to provide evidence for optimizing cervical cancer screening strategies. Methods A prospective controlled study was conducted, enrolling 1,200 women undergoing cervical cancer screening at the Second Affiliated Hospital of Fujian University of Traditional Chinese Medicine and its affiliated community hospitals. Participants were assigned to three interpretation groups: AI-assisted interpretation, manual interpretation, and AI-human collaborative interpretation. Using HPV testing and histopathological examination as reference standards, the sensitivity, specificity, negative predictive value(NPV), interpretation time, and misinterpretation types of the three groups in identifying ≥ CIN2 lesions were assessed. Structured questionnaires and interviews with physicians were conducted to evaluate their subjective experiences regarding system usability, interpretation reliability, and operational interference. Results The AI model demonstrated a sensitivity of 92.8%, specificity of 86.5%, and NPV of 97.6% in identifying ≥ CIN2 lesions. It effectively pre-screened negative slides, with an average interpretation time of 11.5 seconds. The manual interpretation group(Group A) showed a sensitivity of 91.2%, specificity of 89.3%, NPV of 96.4%, and an average interpretation time of 94.2 seconds. The AI-human collaborative group achieved the highest sensitivity(95.3%) and the lowest false-negative rate. However, the AI model exhibited a tendency for misinterpretation in cases of atypical glandular cells(AGC), mixed lesions, and rare cell types. Physician feedback indicated that 82% believed AI improved work efficiency, 78% acknowledged its value in alerting for lowgrade lesions, yet 56% still preferred manual review for borderline cases. Conclusion The AI-assisted cervical cytology model demonstrates excellent efficiency and preliminary screening capability in real-world primary care settings, particularly suitable for rapid triage and negative case exclusion in large-scale screenings. While AI is effective for initial rapid triage in primary care, complex lesions require manual review. The AI-human collaborative approach represents a feasible strategy for improving screening quality.
[1]Singh D, Vignat J, Lorenzoni V, et al. Global estimates of incidence and mortality of cervical cancer in 2020:a baseline analysis of the WHO Global Cervical Cancer Elimination Initiative[J]. Lancet Glob Health, 2023, 11(2):e197-e206. DOI:10. 1016/S2214-109X(23)00211-5.
[2]He WQ, Li C. Recent global burden of cervical cancer incidence and mortality, predictors, and temporal trends[J]. Gynecol Oncol, 2021,163(3):583-592. DOI:10. 1016/j. ygyno. 2021. 07. 027.
[3]舒增怡,梅娴,陈精晶. P16INK4a免疫细胞化学染色联合miRNA、CIN1-3标志物检测在低资源环境下的宫颈癌筛查应用研究[J/OL].诊断病理学杂志, 2025, 1-9[2025-07-04]. http://kns. cnki. net/kcms/detail/11. 3883. R. 20250517. 1623. 010. html
[4]Sachdeva M, Datchoua AM, Yakam VF, et al. Acceptability of artificial intelligence for cervical cancer screening in Dschang, Cameroon:a qualitative study on patient perspectives[J]. Reprod Health, 2024,21(1):92. DOI:10. 1186/s12978-024-01525-5.
[5]Yang Q, Xie M, Yuan M, et al. Application of artificial intelligence in cervical cancer screening:Enhancing accuracy and reducing misdiagnosis[J]. J Clin Nurs, 2025, 34(2):673-674. DOI:10. 1111/jocn. 15928.
[6]Ouh YT, Kim TJ, Ju W, et al. Development and validation of artificial intelligence-based analysis software to support screening system of cervical intraepithelial neoplasia[J]. Sci Rep, 2024, 14(1):1957.DOI:10. 1038/s41598-023-41285-7.
[7]Lindquist S, Kj?r SK, Frederiksen K, et al. Comparative analysis of HPV testing versus cytology in Danish cervical cancer screening:Insights from a large-scale implementation study[J]. Gynecol Oncol,2024, 191:45-55. DOI:10. 1016/j. ygyno. 2023. 10. 001.
[8]杨伟康,张燕,易利模,等.宫颈液基细胞学计算机辅助分析在宫颈癌筛查应用中的意义[J],广东医学, 2025, 46(4):495-501. DOI:10. 3969/j. issn. 1006-7498. 2025. 04. 018.
[9]梁乐.人工智能辅助宫颈癌液基细胞学筛查系统落地实践体会[J].诊断病理学杂志, 2025, 32(1):78-82. DOI:10. 3969/j. issn.1006-384X. 2025. 01. 017.
[10]吕京澴,樊祥山,沈勤,等.人工智能辅助宫颈液基细胞学诊断可行性的多中心研究[J].中华病理学杂志, 2021, 50(4):353-357.DOI:10. 3760/cma. j. cn112151-20210101-00021.
[11]Bai X, Wei J, Starr D, et al. Assessment of efficacy and accuracy of cervical cytology screening with artificial intelligence assistive system[J], Mod Pathol, 2024, 37(6):100486. DOI:10. 1038/s41379-024-01234-7.
[12]Holmstr?m O, Linder N, Kaingu H, et al. Point-of-care digital cytology with artificial intelligence for cervical cancer screening in a resource-limited setting[J]. JAMA Netw Open, 2021, 4(3):e211740.DOI:10. 1001/jamanetworkopen. 2021. 1740.
[13]Bao H, Bi H, Zhang X, et al. Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer:A multicenter, clinical-based, observational study[J]. Gynecol Oncol,2020, 159(1):171-178. DOI:10. 1016/j. ygyno. 2020. 06. 367.
[14]Ikeda K, Sakabe N, Maruyama S, et al. Relationship between liquid-based cytology preservative solutions and artificial intelligence:Liquid-based cytology specimen cell detection using YOLOv5 deep convolutional neural network[J]. Acta Cytol, 2022, 66(6):542-550.DOI:10. 1159/000525460.
[15]Yang Y, Xian D, Yu L, et al. Integration of AI-assisted in digital cervical cytology training:A comparative study[J]. Cytopathology, 2025,36(2):156-164. DOI:10. 1111/cyt. 12371.
[16]Aitken CA, Jansen EEL, Siebers AG, et al. Risk of gynecologic cancer after atypical glandular cells found on cervical cytology:A population-based cohort study[J]. Cancer Epidemiol Biomarkers Prev,2021, 30(4):743-750. DOI:10. 1158/1055-9965. EPI-20-1371.
[17]Gerhard R, Colmenarez CR, Selle C, et al. Digital cytology combined with artificial intelligence compared to conventional microscopy for anal cytology:A preliminary study[J]. Cytopathology, 2025, 36(3):250-258. DOI:10. 1111/cyt. 12376.
[18]Lyu JH, Fan XS, Shen Q, et al. Feasibility multi-center study of artificial intelligence assistance in cervical fluid-based cytology diagnosis[J]. Zhonghua Bing Li Xue Za Zhi, 2021, 50(4):353-357. DOI:10.3760/cma. j. cn112151-20210324-00210.
[19]So KA, Jang EB, Shim SH, et al. Diagnostic accuracy of artificial intelligence vs. oncologist interpretation in digital cervicography for abnormal cervical cytology[J]. J Clin Med, 2025, 14(5):1763. DOI:10. 3390/jcm14051763.
[20]Atteia G, Alabdulhafith M, Abdallah HA, et al. Deep learning-based decision support system for cervical cancer identification in liquid-based cytology pap smears[J]. Technol Health Care, 2025,9287329251330081. DOI:10. 3233/THC-220416.
基本信息:
中图分类号:R737.33;TP18
引用信息:
[1]余孙兴,许振国,江峰.人工智能辅助宫颈细胞学AI模型在真实世界基层筛查中的适应性与局限性分析[J].诊断病理学杂志,2025,32(12):1550-1554.
基金信息:
福建省科学技术厅引导性项目（编号：2023Y0030）
2025-08-12
2025
2025-11-26
2025
1
2025-10-29
2025-10-29
2025-10-29