Hu Liming, Mwanahamuntu Mulindi H, Sahasrabuddhe Vikrant V, Barrett Caroline, Horning Matthew P, Shah Ishan, Laverriere Zohreh, Banik Dipayan, Ji Ye, Shibemba Aaron Lunda, Chisele Samson, Munalula Mukatimui Kalima, Kaunga Friday, Musonda Francis, Malyangu Evans, Hariharan Karen Milch, Parham Groesbeck P
Global Health Labs, Inc, USA.
University Teaching Hospital, Zambia.
medRxiv. 2024 Feb 12:2023.07.19.23292888. doi: 10.1101/2023.07.19.23292888.
Visual inspection with acetic acid (VIA) is a low-cost approach for cervical cancer screening used in most low- and middle-income countries (LMICs) but, similar to other visual tests like histopathology, is subjective and requires sustained training and quality assurance. We developed, trained, and validated an artificial-intelligence-based "Automated Visual Evaluation" (AVE) tool that can be adapted to run on smartphones to assess smartphone-captured images of the cervix and identify precancerous lesions, helping augment performance of VIA.
Prospective study.
Eight public health facilities in Zambia.
8,204 women aged 25-55.
Cervical images captured on commonly used low-cost smartphone models were matched with key clinical information including human immunodeficiency virus (HIV) and human papillomavirus (HPV) status, plus histopathology analysis (where applicable), to develop and train an AVE algorithm and evaluate its performance for use as a primary screen and triage test for women who are HPV positive.
Area under the receiver operating curve (AUC); sensitivity; specificity.
As a general population screening for cervical precancerous lesions, AVE identified cases of cervical precancerous and cancerous (CIN2+) lesions with high performance (AUC = 0.91, 95% confidence interval [CI] = 0.89 to 0.93), which translates to a sensitivity of 85% (95% CI = 81% to 90%) and specificity of 86% (95% CI = 84% to 88%) based on maximizing the Youden's index. This represents a considerable improvement over VIA, which a meta-analysis by the World Health Organization (WHO) estimates to have sensitivity of 66% and specificity of 87%. For women living with HIV, the AUC of AVE was 0.91 (95% CI = 0.88 to 0.93), and among those testing positive for high-risk HPV types, the AUC was 0.87 (95% CI = 0.83 to 0.91).
These results demonstrate the feasibility of utilizing AVE on images captured using a commonly available smartphone by screening nurses and support our transition to clinical evaluation of AVE's sensitivity, specificity, feasibility, and acceptability across a broader range of settings. The performance of the algorithm as reported may be inflated, as biopsies were obtained only from study participants with visible aceto-white cervical lesions, which can lead to verification bias; and the images and data sets used for testing of the model, although "unseen" by the algorithm during training, were acquired from the same set of patients and devices, limiting the study to that of an internal validation of the AVE algorithm.
醋酸肉眼观察法（VIA）是大多数低收入和中等收入国家（LMICs）用于宫颈癌筛查的低成本方法，但与组织病理学等其他视觉检查一样，具有主观性，需要持续培训和质量保证。我们开发、训练并验证了一种基于人工智能的“自动视觉评估”（AVE）工具，该工具可在智能手机上运行，以评估智能手机拍摄的宫颈图像并识别癌前病变，有助于提高VIA的性能。
前瞻性研究。
赞比亚的八家公共卫生机构。
8204名年龄在25 - 55岁的女性。
将常用低成本智能手机型号拍摄的宫颈图像与包括人类免疫缺陷病毒（HIV）和人乳头瘤病毒（HPV）状态等关键临床信息以及（适用时的）组织病理学分析相匹配，以开发和训练AVE算法，并评估其作为HPV阳性女性的初次筛查和分流检测工具的性能。
受试者工作特征曲线下面积（AUC）；敏感性；特异性。
作为宫颈癌前病变的总体人群筛查，AVE在识别宫颈癌前病变和癌性（CIN2 +）病变方面表现出色（AUC = 0.91，95%置信区间[CI] = 0.89至0.93），基于约登指数最大化，这意味着敏感性为85%（95% CI = 81%至90%），特异性为86%（95% CI = 84%至88%）。这比VIA有了显著改善，世界卫生组织（WHO）的一项荟萃分析估计VIA的敏感性为66%，特异性为87%。对于感染HIV的女性，AVE的AUC为0.91（95% CI = 0.88至0.93），在高危HPV类型检测呈阳性的女性中，AUC为0.87（95% CI = 0.83至0.91）。
这些结果证明了筛查护士利用AVE对使用普通智能手机拍摄的图像进行分析的可行性，并支持我们过渡到在更广泛环境中对AVE的敏感性、特异性、可行性和可接受性进行临床评估。报告的算法性能可能被夸大，因为活检仅从宫颈有可见醋酸白病变的研究参与者中获取，这可能导致验证偏倚；并且用于模型测试的图像和数据集，尽管在训练期间算法“未见过”，但来自同一组患者和设备，限制了该研究为AVE算法的内部验证。
