Triaging mammography with artificial intelligence: an implementation study.

IF 3 3区医学 Q2 ONCOLOGY Breast Cancer Research and Treatment Pub Date : 2025-05-01 Epub Date: 2025-01-29 DOI:10.1007/s10549-025-07616-7

Sarah M Friedewald, Marcin Sieniek, Sunny Jansen, Fereshteh Mahvar, Timo Kohlberger, David Schacht, Sonya Bhole, Dipti Gupta, Shruthi Prabhakara, Scott Mayer McKinney, Stacey Caron, David Melnick, Mozziyar Etemadi, Samantha Winter, Thidanun Saensuksopa, Alejandra Maciel, Luca Speroni, Martha Sevenich, Arnav Agharwal, Rubin Zhang, Gavin Duggan, Shiro Kadowaki, Atilla P Kiraly, Jie Yang, Basil Mustafa, Yossi Matias, Greg S Corrado, Daniel Tse, Krish Eswaran, Shravya Shetty

{"title":"Triaging mammography with artificial intelligence: an implementation study.","authors":"Sarah M Friedewald, Marcin Sieniek, Sunny Jansen, Fereshteh Mahvar, Timo Kohlberger, David Schacht, Sonya Bhole, Dipti Gupta, Shruthi Prabhakara, Scott Mayer McKinney, Stacey Caron, David Melnick, Mozziyar Etemadi, Samantha Winter, Thidanun Saensuksopa, Alejandra Maciel, Luca Speroni, Martha Sevenich, Arnav Agharwal, Rubin Zhang, Gavin Duggan, Shiro Kadowaki, Atilla P Kiraly, Jie Yang, Basil Mustafa, Yossi Matias, Greg S Corrado, Daniel Tse, Krish Eswaran, Shravya Shetty","doi":"10.1007/s10549-025-07616-7","DOIUrl":null,"url":null,"abstract":"Purpose: Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis.Methods: In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022. The experimental group used an AI system to prioritize a subset of cases for same-visit radiologist evaluation, and same-visit diagnostic workup if necessary. The control group followed the standard of care. The primary operational endpoints were time to additional imaging (TA) and time to biopsy diagnosis (TB).Results: The final cohort included 463 experimental and 392 control participants. The one-sided Mann-Whitney U test was employed for analysis of TA and TB. In the control group, the TA was 25.6 days [95% CI 22.0-29.9] and TB was 55.9 days [95% CI 45.5-69.6]. In comparison, the experimental group's mean TA was reduced by 25% (6.4 fewer days [one-sided 95% CI > 0.3], p<0.001) and mean TB was reduced by 30% (16.8 fewer days; 95% CI > 5.1], p=0.003). The time reduction was more pronounced for AI-prioritized participants in the experimental group. All participants eventually diagnosed with breast cancer were prioritized by the AI.Conclusions: Implementing AI prioritization can accelerate care timelines for patients requiring additional workup, while maintaining the efficiency of delayed interpretation for most participants. Reducing diagnostic delays could contribute to improved patient adherence, decreased anxiety and addressing disparities in access to timely care.","PeriodicalId":9133,"journal":{"name":"Breast Cancer Research and Treatment","volume":" ","pages":"1-10"},"PeriodicalIF":3.0000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11953103/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Breast Cancer Research and Treatment","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10549-025-07616-7","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/29 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis.

Methods: In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022. The experimental group used an AI system to prioritize a subset of cases for same-visit radiologist evaluation, and same-visit diagnostic workup if necessary. The control group followed the standard of care. The primary operational endpoints were time to additional imaging (T_A) and time to biopsy diagnosis (T_B).

Results: The final cohort included 463 experimental and 392 control participants. The one-sided Mann-Whitney U test was employed for analysis of T_A and T_B. In the control group, the T_A was 25.6 days [95% CI 22.0-29.9] and T_B was 55.9 days [95% CI 45.5-69.6]. In comparison, the experimental group's mean T_A was reduced by 25% (6.4 fewer days [one-sided 95% CI > 0.3], p<0.001) and mean T_B was reduced by 30% (16.8 fewer days; 95% CI > 5.1], p=0.003). The time reduction was more pronounced for AI-prioritized participants in the experimental group. All participants eventually diagnosed with breast cancer were prioritized by the AI.

Conclusions: Implementing AI prioritization can accelerate care timelines for patients requiring additional workup, while maintaining the efficiency of delayed interpretation for most participants. Reducing diagnostic delays could contribute to improved patient adherence, decreased anxiety and addressing disparities in access to timely care.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

用人工智能对乳房x光检查进行分类：一项实施研究。

目的：许多乳腺中心无法在筛查乳房x光检查时提供即时结果，导致患者护理延迟。实施人工智能（AI）可以识别可能患有乳腺癌的患者，并加快诊断成像和活检诊断的时间。方法：在这项前瞻性随机、非盲、对照实施研究中，我们在2021年3月至2022年5月期间招募了1000名筛查参与者。实验组使用人工智能系统优先考虑一些病例，供同访放射科医生评估，并在必要时进行同访诊断检查。对照组遵循护理标准。主要手术终点为额外成像时间（TA）和活检诊断时间（TB）。结果：最终队列包括463名实验参与者和392名对照参与者。采用单侧Mann-Whitney U检验对TA和TB进行分析。对照组TA为25.6天[95% CI 22.0 ~ 29.9]， TB为55.9天[95% CI 45.5 ~ 69.6]。相比之下，实验组的平均TA减少了25%(6.4天[单侧95% CI > 0.3])， pB减少了30%(16.8天；95% CI [[5.1], p=0.003])。在实验组中，优先考虑人工智能的参与者减少的时间更为明显。所有最终被诊断为乳腺癌的参与者都被人工智能优先考虑。结论：实施人工智能优先级可以加快需要额外检查的患者的护理时间，同时保持大多数参与者延迟口译的效率。减少诊断延误可有助于提高患者的依从性，减少焦虑，并解决在获得及时护理方面的差距。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Breast Cancer Research and Treatment 医学-肿瘤学

CiteScore

6.80

自引率

2.60%

发文量

342

审稿时长

1 months

期刊介绍： Breast Cancer Research and Treatment provides the surgeon, radiotherapist, medical oncologist, endocrinologist, epidemiologist, immunologist or cell biologist investigating problems in breast cancer a single forum for communication. The journal creates a "market place" for breast cancer topics which cuts across all the usual lines of disciplines, providing a site for presenting pertinent investigations, and for discussing critical questions relevant to the entire field. It seeks to develop a new focus and new perspectives for all those concerned with breast cancer.