Search

BackgroundVery few efforts have been undertaken to scale-up low-cost approaches to cervical cancer prevention in low-resource countries.MethodsIn a public sector cervical cancer prevention program in Zambia, nurses provided visual-inspection with acetic acid (VIA) and cryotherapy in clinics co-housed with HIV/AIDS programs, and referred women with complex lesions for histopathologic evaluation. Low-cost technological adaptations were deployed for improving VIA detection, facilitating expert physician opinion, and ensuring quality assurance. Key process and outcome indicators were derived by analyzing electronic medical records to evaluate program expansion efforts.FindingsBetween 2006-2013, screening services were expanded from 2 to 12 clinics in Lusaka, the most-populous province in Zambia, through which 102,942 women were screened. The majority (71.7%) were in the target age-range of 25–49 years; 28% were HIV-positive. Out of 101,867 with evaluable data, 20,419 (20%) were VIA positive, of whom 11,508 (56.4%) were treated with cryotherapy, and 8,911 (43.6%) were referred for histopathologic evaluation. Most women (87%, 86,301 of 98,961 evaluable) received same-day services (including 5% undergoing same-visit cryotherapy and 82% screening VIA-negative). The proportion of women with cervical intraepithelial neoplasia grade 2 and worse (CIN2+) among those referred for histopathologic evaluation was 44.1% (1,735/3,938 with histopathology results). Detection rates for CIN2+ and invasive cervical cancer were 17 and 7 per 1,000 women screened, respectively. Women with HIV were more likely to screen positive, to be referred for histopathologic evaluation, and to have cervical precancer and cancer than HIV-negative women.InterpretationWe creatively disrupted the 'no screening' status quo prevailing in Zambia and addressed the heavy burden of cervical disease among previously unscreened women by establishing and scaling-up public-sector screening and treatment services at a population level. Key determinants for successful expansion included leveraging HIV/AIDS program investments, and context-specific information technology applications for quality assurance and filling human resource gaps.

Objectives: 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., Design: Prospective study., Setting: Eight public health facilities in Zambia., Participants: 8,204 women aged 25-55., Interventions: 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., Main Outcome Measures: Area under the receiver operating curve (AUC); sensitivity; specificity., Results: 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)., Conclusions: 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.