Internal validation of Automated Visual Evaluation (AVE) on smartphone images for cervical cancer screening in a prospective study in Zambia.

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, 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 VIA performance. DESIGN: Prospective study. SETTING: Eight public health facilities in Zambia. PARTICIPANTS: A total of 8204 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 tool for cervical precancerous lesions, AVE identified cases of cervical precancerous and cancerous (CIN2+) lesions with high performance (AUC = 0.91, 95% confidence interval [CI] = 0.89-0.93), which translates to a sensitivity of 85% (95% CI = 81%-90%) and specificity of 86% (95% CI = 84%-88%) based on maximizing the Youden's index. This represents a considerable improvement over naked eye VIA, which as per a meta-analysis by the World Health Organization (WHO) has a sensitivity of 66% and specificity of 87%. For women living with HIV, the AUC of AVE was 0.91 (95% CI = 0.88-0.93), and among those testing positive for high-risk HPV types, the AUC was 0.87 (95% CI = 0.83-0.91). CONCLUSIONS: These results demonstrate the feasibility of utilizing AVE on images captured using a commonly available smartphone by nurses in a screening program, and support our ongoing efforts for moving to more broadly evaluate AVE for its clinical sensitivity, specificity, feasibility, and acceptability across a wider range of settings. Limitations of this study include potential inflation of performance estimates due to verification bias (as biopsies were only obtained from participants with visible aceto-white cervical lesions) and due to this being an internal validation (the test data, while independent from that used to develop the algorithm was drawn from the same study).

Internal Validation of Automated Visual Evaluation (AVE) on Smartphone Images for Cervical Cancer Screening in a Prospective Study in Zambia.

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.

Validation in Zambia of a cervical screening strategy including HPV genotyping and artificial intelligence (AI)-based automated visual evaluation.

BACKGROUND: WHO has recommended HPV testing for cervical screening where it is practical and affordable. If used, it is important to both clarify and implement the clinical management of positive results. We estimated the performance in Lusaka, Zambia of a novel screening/triage approach combining HPV typing with visual assessment assisted by a deep-learning approach called automated visual evaluation (AVE). METHODS: In this well-established cervical cancer screening program nested inside public sector primary care health facilities, experienced nurses examined women with high-quality digital cameras; the magnified illuminated images permit inspection of the surface morphology of the cervix and expert telemedicine quality assurance. Emphasizing sensitive criteria to avoid missing precancer/cancer, ~ 25% of women screen positive, reflecting partly the high HIV prevalence. Visual screen-positive women are treated in the same visit by trained nurses using either ablation (~ 60%) or LLETZ excision, or referred for LLETZ or more extensive surgery as needed. We added research elements (which did not influence clinical care) including collection of HPV specimens for testing and typing with BD Onclarity™ with a five channel output (HPV16, HPV18/45, HPV31/33/52/58, HPV35/39/51/56/59/66/68, human DNA control), and collection of triplicate cervical images with a Samsung Galaxy J8 smartphone camera™ that were analyzed using AVE, an AI-based algorithm pre-trained on a large NCI cervical image archive. The four HPV groups and three AVE classes were crossed to create a 12-level risk scale, ranking participants in order of predicted risk of precancer. We evaluated the risk scale and assessed how well it predicted the observed diagnosis of precancer/cancer. RESULTS: HPV type, AVE classification, and the 12-level risk scale all were strongly associated with degree of histologic outcome. The AVE classification showed good reproducibility between replicates, and added finer predictive accuracy to each HPV type group. Women living with HIV had higher prevalence of precancer/cancer; the HPV-AVE risk categories strongly predicted diagnostic findings in these women as well. CONCLUSIONS: These results support the theoretical efficacy of HPV-AVE-based risk estimation for cervical screening. If HPV testing can be made affordable, cost-effective and point of care, this risk-based approach could be one management option for HPV-positive women.

Addressing the shortage of pathologists in Africa: Creation of a MMed Programme in Pathology in Zambia.

BACKGROUND: With approximately one pathologist for one million people compared to ratios of approximately 1 to 25 000 in the United States and United Kingdom, there is a severe shortage of pathologists in much of Africa. The situation is particularly severe in Zambia, where, in 2009, the ratio was 1 to 1.4 million. OBJECTIVE: To address this, a postgraduate Master of Medicine (MMed) training programme was launched in Lusaka in 2011. METHODS: The process and most significant challenges and lessons learned were documented, as they may be of value to other countries facing similar challenges. RESULTS: Since 2011, four Zambian pathologists have graduated, doubling the number of indigenous pathologists in the country. Currently 10 students are in training. The most significant problem was issues arising from the split responsibilities of the Ministries of Health and of Education and the most important lesson learned was the crucial need for broad local ownership and commitment. CONCLUSION: Successfully addressing the shortage of local pathologists by creating country-specific, postgraduate MMed training programmes, even in situations of restricted resources, is feasible. However, having access to and support from the shared resources, expertise and knowledge of a regional College of Pathologists would be a major advantage.

Evidence of EBV infection in lymphomas diagnosed in Lusaka, Zambia.

INTRODUCTION: Epstein-Barr virus (EBV) is a ubiquitous virus that infects more than 90% of the world's population, and is implicated in lymphoma pathogenesis. However, in Zambia during the diagnosis of these lymphomas, the association of the virus with the lymphomas is not established. Since most patients with lymphomas have poor prognosis, the identification of the virus within the lymphoma lesion will allow for more targeted therapy. The aim of this study was to provide evidence of the presence of the EBV in lymphomas diagnosed at the University Teaching Hospital (UTH) in Lusaka, Zambia. METHODS: One hundred and fifty archival formalin-fixed paraffin embedded suspected lymphoma tissues stored over a 4-year period in the Histopathology Laboratory at the UTH in Lusaka, Zambia, were analysed. Histological methods were used to identify the lymphomas, and the virus was detected using Polymerase Chain Reaction (PCR). Subtyping of the virus was achieved through DNA sequencing of the EBNA-2 region of the viral genome. Chi square or fisher's exact test was used to evaluate the association between EBV status, type of lymphoma and gender. RESULTS: The majority of the lymphomas identified were non-Hodgkin's lymphoma (NHL) (80%) followed by Hodgkin's lymphoma (HL) (20%). EBV was detected in 51.8% of the cases, 54.5% of which were associated with NHL cases, while 40.9% associated with HL cases. The predominant subtype of the virus in both types of lymphomas was subtype 1. One of the lymphoma cases harboured both subtype 1 and 2 of the virus. CONCLUSION: This study showed that EBV is closely associated with lymphomas. Therefore, providing evidence of the presence of the virus in lymphoma tissues will aid in targeted therapy. To our knowledge this is the first time such data has been generated in Zambia.

Efficacy of Cyto-Chex blood preservative for delayed manual CD4 testing using Dynal T4 Quant CD4 test among HIV-infected persons in Zambia.

BACKGROUND: Manual CD4 tests such as Dynal T4 Quant (Dynabeads, Dynal Biotech, Oslo, Norway) are less expensive alternatives to flow cytometry in resource-limited countries. Whereas blood preservatives have proven useful for stabilizing blood samples to allow delayed CD4 testing by flow cytometry, they have not been verified for manual tests. A method for preservation of blood prior to manual CD4 testing is needed for long-distance transport or sample batching. METHODS: Blood from HIV-positive Zambian military beneficiaries was mixed (1:1) with Cyto-Chex (Streck Laboratories, La Vista, NE) blood preservative, and the blood was stored at refrigerated, ambient, and incubator (37 degrees C) temperatures prior to Dynabeads CD4 testing at 0, 3, 6, and 9 days after collection. Baseline flow cytometry and Dynabeads testing without preservative were performed for comparison. RESULTS: Twenty-seven patient samples were analyzed. Dynabeads vs. flow cytometry had a correlation coefficient (r) of 0.84. There was excellent correlation (r = 0.96) between baseline Dynabeads testing and Cyto-Chex-preserved samples. Refrigerated samples showed strong correlation with baseline Dynabeads (r = 0.93-0.95) on days 3, 6, and 9 without decline in CD4 count (P = 0.73). Samples stored at ambient temperature yielded inferior results (r = 0.76-0.81), with a significant decline in CD4 count by day 3 (P < 0.001). The incubator arm had especially poor correlation (r = 0.30-0.49). CONCLUSIONS: Addition of Cyto-Chex to peripheral blood (1:1) adequately preserves refrigerated blood samples for up to 9 days for subsequent testing with Dynabeads CD4 test. Cyto-Chex, however, cannot be recommended for delayed Dynabeads CD4 testing with storage at 37 degrees C or ambient temperatures in tropical areas similar to the site of this study.