Endoscopy · 2026
Cost-effectiveness and environmental impact of artificial intelligence-assisted colonoscopy with the resect-and-discard strategy: a microsimulation study.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Hernandez Lyndon V, Wallace Michael B, von Renteln Daniel, Sherman Jodi, Bhutani Manoop S, Guda Nalini M, Espinosa Wendell, Klyve Dominic, Manahan Theo, Pohl Heiko
Аннотация
BACKGROUND: Artificial intelligence (AI)-assisted colonoscopy reduces costs in colorectal cancer screening, but its incremental value relative to non-AI resect-and-discard strategies for diminutive polyps (≤5 mm) remains unclear. We aimed to compare the clinical, economic, and environmental outcomes of resect-and-discard strategies both with and without AI assistance with the standard of care (SoC).
METHODS: In our Markov model simulating 6 million individuals aged ≥45 years undergoing screening colonoscopy, four strategies were evaluated: SoC; non-AI resect and discard (nonAI-RD); computer-aided detection (CADe)-assisted resect and discard (CADe-RD); and combined CADe and computer-aided diagnosis (CADx)-assisted resect and discard (CADe+CADx-RD). The primary outcome was total quality-adjusted life years (QALYs), with secondary outcomes including cost and carbon dioxide (CO2) emissions.
RESULTS: NonAI-RD achieved the lowest total cost ($36.6 billion) and carbon emissions (0.90 million kgCO2while yielding the highest QALYs (51.37 million), although differences in QALYs across strategies were small (<0.01%). CADe-RD and CADe+CADx-RD remained cost-saving relative to SoC ($36.9 billion and $37.4 billion vs. $37.8 billion, respectively), but were associated with higher costs than nonAI-RD. CADe modestly increased adenoma detection without improving QALYs, while the addition of CADx increased costs and emissions and resulted in slightly lower QALYs. Sensitivity analysis showed that CADe+CADx-RD matched or exceeded the QALYs for CADe-RD only within a limited region of high diagnostic performance. At currently reported CADx performance levels, CADe+CADx-RD yielded lower QALYs and higher costs than CADe-RD. CADe+CADx-RD achieved noninferiority in QALYs relative to CADe-RD only within a limited region of high diagnostic performance.
CONCLUSIONS: In our nondeterministic model, nonAI-RD provided the optimal balance of clinical benefit, cost savings, and lower environmental impact.
METHODS: In our Markov model simulating 6 million individuals aged ≥45 years undergoing screening colonoscopy, four strategies were evaluated: SoC; non-AI resect and discard (nonAI-RD); computer-aided detection (CADe)-assisted resect and discard (CADe-RD); and combined CADe and computer-aided diagnosis (CADx)-assisted resect and discard (CADe+CADx-RD). The primary outcome was total quality-adjusted life years (QALYs), with secondary outcomes including cost and carbon dioxide (CO2) emissions.
RESULTS: NonAI-RD achieved the lowest total cost ($36.6 billion) and carbon emissions (0.90 million kgCO2while yielding the highest QALYs (51.37 million), although differences in QALYs across strategies were small (<0.01%). CADe-RD and CADe+CADx-RD remained cost-saving relative to SoC ($36.9 billion and $37.4 billion vs. $37.8 billion, respectively), but were associated with higher costs than nonAI-RD. CADe modestly increased adenoma detection without improving QALYs, while the addition of CADx increased costs and emissions and resulted in slightly lower QALYs. Sensitivity analysis showed that CADe+CADx-RD matched or exceeded the QALYs for CADe-RD only within a limited region of high diagnostic performance. At currently reported CADx performance levels, CADe+CADx-RD yielded lower QALYs and higher costs than CADe-RD. CADe+CADx-RD achieved noninferiority in QALYs relative to CADe-RD only within a limited region of high diagnostic performance.
CONCLUSIONS: In our nondeterministic model, nonAI-RD provided the optimal balance of clinical benefit, cost savings, and lower environmental impact.