Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Aug 1, 2023
Date Accepted: Sep 9, 2024

The final, peer-reviewed published version of this preprint can be found here:

Performance of a Full-Coverage Cervical Cancer Screening Program Using on an Artificial Intelligence– and Cloud-Based Diagnostic System: Observational Study of an Ultralarge Population

Ji L, Yao Y, Yu D, Chen W, Yin S, Fu Y, Tang S, Yao L

Performance of a Full-Coverage Cervical Cancer Screening Program Using on an Artificial Intelligence– and Cloud-Based Diagnostic System: Observational Study of an Ultralarge Population

J Med Internet Res 2024;26:e51477

DOI: 10.2196/51477

PMID: 39566061

PMCID: 11618014

Performance of a full coverage cervical cancer screening program based on an artificial intelligence + cloud diagnostic system: an observational study of an ultra-large population

  • Lu Ji; 
  • Yifan Yao; 
  • Dandan Yu; 
  • Wen Chen; 
  • Shanshan Yin; 
  • Yun Fu; 
  • Shangfeng Tang; 
  • Lan Yao

ABSTRACT

Background:

Background:

The World Health Organization (WHO) has set a global strategy to eliminate cervical cancer, emphasizing the need for cervical cancer screening coverage to reach 70%. In response, China has developed an action plan to accelerate the elimination of cervical cancer, with Hubei province implementing China's first provincial full coverage screening program utilizing artificial intelligence (AI) + cloud diagnostic system.

Objective:

Objective:

This study aimed to evaluate the performance of AI technology in this full coverage screening program. The evaluation indicators included screening volume in different regions, screening efficiency, diagnostic quality, and program cost.

Methods:

Methods:

Characteristics of 1704,461 cases screened in July 2022 to January 2023 were used to analyze screening volume, regional distribution, and AI screening efficiency. A random sample of 220 cases were used for external diagnostic quality control. Costs of different participating screening institutions were assessed.

Results:

Results:

Approximately 1.7 million individuals were screened, achieving a cumulative coverage of 13.45% in about 6 months. Rural women had the highest participation rate at 67.54%. Full coverage programs could be achieved by AI technology in approximately one year, which was 87.5 times more efficient than manual reading of slides. Compared to real-world screening capacity, AI technology could accomplish full coverage program at least 15 years ahead of schedule. The sample compliance rate was as high as 99.1%, and compliance rates for positive, negative, and pathology biopsy review exceeded 96%. The cost of this program was 49 CNY per person, with the primary screening institution and the third party testing institute receiving 19 CNY and 27 CNY, respectively.

Conclusions:

Conclusions:

AI-assisted diagnosis has proven to be efficient, reliable and low-cost, which could support the implementation of full coverage screening programs, especially in areas with insufficient health resources. AI technology served as a crucial tool for rapidly and effectively increasing screening coverage, which would accelerate the achievement of WHO goals for cervical cancer.


 Citation

Please cite as:

Ji L, Yao Y, Yu D, Chen W, Yin S, Fu Y, Tang S, Yao L

Performance of a Full-Coverage Cervical Cancer Screening Program Using on an Artificial Intelligence– and Cloud-Based Diagnostic System: Observational Study of an Ultralarge Population

J Med Internet Res 2024;26:e51477

DOI: 10.2196/51477

PMID: 39566061

PMCID: 11618014

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.