Development and Clinical Validation of Visual Inspection With Acetic Acid Application-Artificial Intelligence Tool Using Cervical Images in Screen-and-Treat Visual Screening for Cervical Cancer in South India: A Pilot Study

Sep 21, 2026

Exploratory interventional research addresses the high cervical cancer burden in India and the WHO screen-and-treat goal of treating 90% of women with cervical lesions. The study targets overtreatment caused by the subjective nature of visual inspection with acetic acid (VIA), by developing a deep-learning VIA-AI tool that triages VIA-positive women using cervical images. It evaluates how accurately the tool identifies VIA-screen–positive areas and guides nurse decisions on treatment eligibility in a pilot screen-and-treat program.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Purpose

Methods

Results

Conclusion

Context

Key objective

Knowledge generated

Relevance

Original Reports | Cancer Prevention and Control Development and Clinical Validation of Visual Inspection With Acetic Acid Application-Artiﬁcial Intelligence Tool Using Cervical Images in Screen-and-Treat Visual Screening for Cervical Cancer in South India: A Pilot Study Usha Rani Poli, MBBS, DNB, DGO1 ; Anirudh G. Gudlavalleti, MA, BDS1 ; Jaya Bharadwaj Y, BS2 ; Hira B. Pant, MA, PGDBDM1 ; Varun Agiwal, PhD, MA3 ; and G.V.S. Murthy, MD, MBBS, MSc1 DOI [https://doi.org/10.1200/GO.24.00146](https://doi.org/10.1200/GO.24.00146) | ABSTRACT | | | --- | --- | | PURPOSE | The burden of cervical cancer in India is enormous, with more than 60,000 deaths being reported in 2020 . The key intervention in the WHO’s global strategy for the elimination of cervical cancer is to aim for the treatment and care of 90% of women diagnosed with cervical lesions. The current screen-andtreat approach as an option for resource-limited health care systems where screening of the cervix with visual inspection with acetic acid application (VIA) is followed by immediate ablative treatment by nurses in the case of a positive test. This approach often results in overtreatment, owing to the subjective nature of the test. Unnecessary treatments can be diminished with the use of emerging computer-assisted visual evaluation technology, using artiﬁcial intelligence (AI) tool to triage VIA-positive women. The aim of this study was (1) to develop a VIA-AI tool using cervical images to identify and categorize the VIA-screen–positive areas for eligibility and suitability for ablative treatment, and (2) to understand the efﬁcacy of the VIA-AI tool in guiding the nurses to decide on treatment eligibility in the screen-and-treat cervical screening program. | | METHODS | This was an exploratory, interventional study. The VIA-AI tool was developed using deep-learning AI from the image bank collected in our previously conducted screening programs. This VIA-AI tool was then pilot-tested in an ongoing nurse-led VIA screening program. | | RESULTS | A comparative assessment of the cervical features performed in all women using the VIA-AI tool showed clinical accuracy of 76% . The perceived challenge rate for false positives was 20% . | | CONCLUSION | This novel cervical image–based VIA-AI algorithm showed promising results in real-life settings, and could help minimize overtreatment in single-visit VIA screening and treatment programs in resource-constrained situations. | ACCOMPANYING CONTENT Appendix Accepted October 1, 2024 Published December 12, 2024 JCO Global Oncol 10:e2400146 © 2024 by American Society of Clinical Oncology Creative Commons Attribution Non-Commercial No Derivatives 4.0 License INTRODUCTION Cervical cancer is the fourth most common cancer among women worldwide, with 570,000 new cases and 311,000 deaths by 2020 .1 Nearly 90% of these deaths occur in lowincome and middle-income countries. Disparities in the distribution of incidence and mortality rates are due to inadequate access to health services. The cervical cancer burden in India is enormous, with more than 60,000 deaths in 2020, and is a major cause of the lack of organized cervical cancer screening. The key intervention in the WHO’s global strategy for the elimination of cervical cancer is to aim for the treatment and care of 90% of women diagnosed with cervical lesions. The recommended screen-and-treat approach option is for a resourcelimited health care system where screening of the cervix by visual inspection with acetic acid application (VIA) is followed by immediate ablative treatment by nurses.2 A health worker performing VIA rates the cervical appearance as normal or abnormal, paying particular attention to possible invasive cancers. If the appearance is abnormal, and after excluding invasive cancer, based on the size and position the visible precancerous lesion, it permits the cervical epithelium to be ablated by freezing or heating. [ascopubs.org/journal/go](as

FAQs

What problem does the study try to solve in cervical cancer screen-and-treat programs?

The study focuses on overtreatment that can result from the subjective nature of VIA. It aims to reduce unnecessary ablative treatments by using an AI tool to triage VIA-positive women.

How was the VIA-AI tool developed and tested?

The VIA-AI tool was developed using deep-learning from a cervical image bank collected in prior screening programs. It was then pilot-tested within an ongoing nurse-led VIA screening program.

What were the reported performance outcomes of the VIA-AI tool?

The tool achieved clinical accuracy of 76% in comparative assessment across women, with a perceived false-positive challenge rate of 20%.

Sep 21, 2026

Upload by Theodora