DIAGNOSTIC ACCURACY OF AI-POWERED DIGITAL COLPOSCOPY FOR CERVICAL CANCER SCREENING AND DETECTION: A SYSTEMATIC REVIEW AND META-ANALYSIS...

Author(s)

Pudi N. Seshu, Sr., PhD1, Kavita Kachroo, MBA, MHA2, Jitendra Sharma, MHA, Ph.D2.
1Scientist-D, Kalam Institute of Health Technology ( KIHT), Visakhapatnam, India, 2Kalam Institute of Health Technology ( KIHT), Visakhapatnam, India.
OBJECTIVES: This study assesses the diagnostic accuracy of AI-powered digital colposcopy in terms of sensitivity and specificity for detecting cervical intraepithelial neoplasia (CIN) and cervical cancer. It compares the diagnostic performance of a portable AI-colposcope with digital spectral imaging, conventional colposcopy, and visual inspection with acetic acid (VIA).
METHODS: A comprehensive search was performed at various electronic databases using PubMed, Web of Science, Google Scholar, and Cochrane. A PRISMA method is used to curate and collocate the studies. Quantitative data were pooled into statistical meta-analyses using the Cochrane Review Manager (RevMan) for diagnostic accuracy.
RESULTS: A total of 3598 articles were obtained and after evaluation, 110 articles were accepted and met the criteria for systematic review and meta-analysis. Therefore, The AI colposcope demonstrates the highest sensitivity at 0.90 (95% CI: 0.90-0.90), and specificity is moderate at 0.63 (95% CI: 0.62-0.63), Conventional colposcopy shows lower sensitivity at 0.71 (95% CI: 0.70-0.72) and moderate specificity at 0.68 (95% CI: 0.67-0.68), DSI offers a more balanced profile, with sensitivity of 0.80 (95% CI: 0.79-0.80) and specificity of 0.69 (95% CI: 0.68-0.69), performing better than conventional colposcopy but not surpassing AI in sensitivity. In contrast, VIA demonstrates relatively lower sensitivity at 0.77 (95% CI: 0.73-0.81) but the highest specificity at 0.83 (95% CI: 0.82-0.85)
CONCLUSIONS: AI-Powered digital colposcopy is an effective and innovative diagnostic tool for the detection of cervical cancer and precancerous lesions. Technology offers high sensitivity and specificity, reduces variability in interpretation, and enhances the overall accuracy of colposcopic evaluation.

Conference/Value in Health Info

2026-09, ISPOR Asia Pacific 2026, Bangkok, Thailand

Value in Health, Volume 55, Issue S1

Code

HTA35

Topic

Health Technology Assessment

Topic Subcategory

Systems & Structure

Disease

SDC: Oncology, SDC: Reproductive & Sexual Health, STA: Personalized & Precision Medicine

Your browser is out-of-date

ISPOR recommends that you update your browser for more security, speed and the best experience on ispor.org. Update my browser now

×