Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 28;4(1):e289.
doi: 10.1002/deo2.289. eCollection 2024 Apr.

Cost-effectiveness analysis of the artificial intelligence diagnosis support system for early gastric cancers

Shion Yonazu  1   2 , Tsuyoshi Ozawa  2   3 , Tamiji Nakanishi  2 , Kentaro Ochiai  2   4 , Junichi Shibata  2   3 , Hiroyuki Osawa  5 , Toshiaki Hirasawa  6 , Yusuke Kato  2 , Hisao Tajiri  7 , Tomohiro Tada  2   3   4
Affiliations

Cost-effectiveness analysis of the artificial intelligence diagnosis support system for early gastric cancers

Shion Yonazu et al. DEN Open. .

Abstract

Objectives: The introduction of artificial intelligence into the medical field has improved the diagnostic capabilities of physicians. However, few studies have analyzed the economic impact of employing artificial intelligence technologies in the clinical environment. This study evaluated the cost-effectiveness of a computer-assisted diagnosis (CADx) system designed to support clinicians in differentiating early gastric cancers from non-cancerous lesions in Japan, where the universal health insurance system was introduced.

Methods: The target population to be used for the CADx was estimated as those with moderate to severe gastritis caused by Helicobacter pylori infection. Decision trees with Markov models were built to analyze the cumulative cost-effectiveness of using CADx relative to the pre-artificial intelligence status quo, a condition reconstructed from data in published reports. After conducting a base-case analysis, we performed sensitivity analyses by modifying several parameters. The primary outcome was the incremental cost-effectiveness ratio.

Results: Compared with the status quo as represented in the base-case analysis, the incremental cost-effectiveness ratio of CADx in the Japanese market was forecasted to be 11,093 USD per quality-adjusted life year. The sensitivity analyses demonstrated that the expected incremental cost-effectiveness ratios were within the willingness-to-pay threshold of 50,000 USD per quality-adjusted life year when the cost of the CAD was less than 104 USD.

Conclusions: Using CADx for EGCs may decrease their misdiagnosis, contributing to improved cost-effectiveness in Japan.

Keywords: artificial intelligence; computer‐aided diagnosis; cost‐effectiveness; early gastric cancer; medical cost.

PubMed Disclaimer

Conflict of interest statement

Tomohiro Tada and Yusuke Kato are the CEO and the CTO of AI Medical Service Inc., respectively. Tsuyoshi Ozawa, Junichi Shibata, and Kentaro Ochiai are consulting members of AI Medical Service Inc. Hisao Tajiri received an advisory fee from AI Medical Service Inc., and lecture fees from Olympus Medical Co. and Fujifilm Medical Co. Hiroyuki Osawa and Hisao Tajiri received an advisory fee from AI Medical Service Inc. Shion Yonazu and Toshiaki Hirasawa have no conflict of interest.

Figures

FIGURE 1
FIGURE 1
The quality‐adjusted life years (QALYs) and medical costs for the present and the computer‐assisted diagnosis (CADx)‐use cases. For the false negative cases, the Markov model was applied to simulate the QALY and medical costs.
FIGURE 2
FIGURE 2
The probabilities of progression and morbidity of gastric cancer in each stage.
FIGURE 3
FIGURE 3
A tornado diagram representing the results of the one‐way sensitivity analysis.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Sung H, Ferlay J, Siegel RL et al. Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2021; 71: 209–49. - PubMed
    1. Hamashima C, Shibuya D, Yamazaki H et al. The Japanese guidelines for gastric cancer screening. Jpn J Clin Oncol 2008; 38: 259–67. - PubMed
    1. Jun JK, Choi KS, Lee HY et al. Effectiveness of the Korean national cancer screening program in reducing gastric cancer mortality. Gastroenterology 2017; 152: 1319–28.e7. - PubMed
    1. Shah SC, Canakis A, Peek RM, Jr , Saumoy M. Endoscopy for gastric cancer screening is cost effective for Asian Americans in the United States. Clin Gastroenterol Hepatol 2020; 18: 3026–39. - PMC - PubMed
    1. Yoshimizu S, Hirasawa T, Horiuchi Y et al. Differences in upper gastrointestinal neoplasm detection rates based on inspection time and esophagogastroduodenoscopy training. Endosc Int Open 2018; 6: E1190–7. - PMC - PubMed