Journal of the American College of Radiology最新文献

{"title":"Multi-Institutional Evaluation and Training of Breast Density Classification AI Algorithm Using ACR Connect and AI-LAB","authors":"Laura Brink ,&nbsp;Ricardo Amaya Romero ,&nbsp;Laura Coombs ,&nbsp;Mike Tilkin ,&nbsp;Sina Mazaheri MD ,&nbsp;Judy Gichoya MD ,&nbsp;Zachary Zaiman MD ,&nbsp;Hari Trivedi MD ,&nbsp;Adam Medina MD ,&nbsp;Bernardo C. Bizzo MD, PhD ,&nbsp;Ken Chang MD ,&nbsp;Jayashree Kalpathy-Cramer MD ,&nbsp;Mannudeep K. Kalra MD ,&nbsp;Bruno Astuto MD ,&nbsp;Carolina Ramirez MD ,&nbsp;Sharmila Majumdar MD ,&nbsp;Amie Y. Lee MD ,&nbsp;Christoph I. Lee MD, MS, MBA ,&nbsp;Nathan M. Cross MD, MS ,&nbsp;Po-Hao Chen MD ,&nbsp;Christoph Wald MD","doi":"10.1016/j.jacr.2024.11.003","DOIUrl":"10.1016/j.jacr.2024.11.003","url":null,"abstract":"<div><h3>Objective</h3><div>To demonstrate and test the capabilities of the ACR Connect and AI-LAB software platform by implementing multi-institutional artificial intelligence (AI) training and validation for breast density classification.</div></div><div><h3>Methods</h3><div>In this proof-of-concept study, six US-based hospitals installed Connect and AI-LAB. A breast density algorithm was trained and tested on retrospective mammograms. We recorded time to receive institutional review board approval, to install software locally, and to complete the testing and training. We calculated the performance of the breast density algorithm at each participating hospital and compared it to the performance of a holdout multi-institutional clinical trial testing dataset and a retrospective multi-institutional dataset. We calculated the performance of the locally fine-tuned models on the holdout test datasets.</div></div><div><h3>Results</h3><div>The median time to receive institutional review board approval was 66 days, and the median time to successfully install Connect and AI-LAB locally was 157 days. The median time to complete breast density algorithm testing and training was 216 days. The breast density algorithm performed worse at each hospital than on the holdout test dataset, suggesting poor generalizability of the base model. The fine-tuned models had mixed performance locally and performed poorly on the test dataset.</div></div><div><h3>Discussion</h3><div>In this study, we demonstrate the successful installation and implementation of Connect and AI-LAB software platforms at six facilities using a breast density algorithm. Our results suggest poor generalizability of an algorithm trained on a single dataset and algorithms fine-tuned at individual institutions, emphasizing the hypothetical importance of multi-institutional testing and training.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 211-219"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142649807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rethinking the Didactic Radiology Conference in the Era of New Generational Learners","authors":"Priscilla J. Slanetz MD, MPH ,&nbsp;Fatima Elahi DO ,&nbsp;Angela I. Choe MD ,&nbsp;Lauren Alexander MD","doi":"10.1016/j.jacr.2024.11.027","DOIUrl":"10.1016/j.jacr.2024.11.027","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 237-239"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142755751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond DEI Policies: Socioeconomic and Global Challenges in Radiology","authors":"Valeria del Castillo MD,&nbsp;Daniela Otalvaro MD,&nbsp;José David Cardona Ortegón MD,&nbsp;Javier Andrés Romero MD","doi":"10.1016/j.jacr.2024.10.021","DOIUrl":"10.1016/j.jacr.2024.10.021","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Page 149"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142775239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Table of Content","authors":"","doi":"10.1016/S1546-1440(25)00039-0","DOIUrl":"10.1016/S1546-1440(25)00039-0","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages A1-A4"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Projecting Demand for Health Care Services Through Utilization-Based Approaches","authors":"Joseph H. Joo MD ,&nbsp;Joshua M. Liao MD, MSc","doi":"10.1016/j.jacr.2025.01.008","DOIUrl":"10.1016/j.jacr.2025.01.008","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 159-160"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Overcoming Access Barriers to Hip and Knee MRI for Patients With Atraumatic Pain: Challenges and Proposed Solutions","authors":"Luis Fernando Pulido Cadavid MD,&nbsp;José David Cardona Ortegón MD,&nbsp;Karen Cifuentes Gaitan MD","doi":"10.1016/j.jacr.2024.11.014","DOIUrl":"10.1016/j.jacr.2024.11.014","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 149-150"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142717923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Projected US Radiologist Supply, 2025 to 2055","authors":"Eric W. Christensen PhD ,&nbsp;Jay R. Parikh MD ,&nbsp;Alexandra R. Drake MPH ,&nbsp;Eric M. Rubin MD ,&nbsp;Elizabeth Y. Rula PhD","doi":"10.1016/j.jacr.2024.10.019","DOIUrl":"10.1016/j.jacr.2024.10.019","url":null,"abstract":"<div><h3>Purpose</h3><div>To project the future radiologist workforce through 2055 and assess the contributions of residency positions and attrition to radiologist supply.</div></div><div><h3>Methods</h3><div>The CMS National Downloadable Files (2014-2023) were used to assess both the current supply of radiologists and model the attrition based on years of practice. Using a nonlinear regression model, differences in attrition patterns were assessed by gender as well as pre–COVID-19 and post–COVID-19. New entrants to the workforce were modeled via linear regression based on National Residency Matching Program data (2005-2024) for radiology residency positions and filled positions. Attrition and new entrants were combined to generate estimates of radiologist supply through 2055.</div></div><div><h3>Results</h3><div>In 2023, 37,482 radiologists were enrolled to provide care to Medicare patients. If residency positions do not grow after 2024, the projected number of radiologists in 2055 is 47,119 or 25.7% higher than in 2023. If residency positions grow after 2024, these projections are 52,591 radiologists in 2055, 40.3% higher. Based on 2014 to 2023 attrition, average years of practice is 35.7 for male and 34.2 for female radiologists. Attrition rates were substantially higher post–COVID-19 versus pre–COVID-19, which difference is equivalent to 3,116 radiologists in 2055.</div></div><div><h3>Conclusions</h3><div>This study projected that the 2055 radiologist workforce will be 40.3% or 25.7% larger than in 2023 if residency positions, respectively, do or do not grow in the future. The study found that should attrition rates continue to be higher as they have been thus far post–COVID-19, the 2055 radiologist workforce would be substantially smaller.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 161-169"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Communicating Imaging Risks to Patients: Time to Gather Consensus and Standardize Best Practices","authors":"Tarimobo M. Otobo BMedSci, MSc, MD, PhD ,&nbsp;Hansel J. Otero MD","doi":"10.1016/j.jacr.2024.10.005","DOIUrl":"10.1016/j.jacr.2024.10.005","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 183-184"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142482483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unintended Consequences of Price Transparency Initiatives: Examining Patient Decision Making in Imaging Services","authors":"George Grant BS ,&nbsp;Ali Rashidi MD ,&nbsp;Ruth C. Carlos MD, MS ,&nbsp;Gelareh Sadigh MD","doi":"10.1016/j.jacr.2024.10.002","DOIUrl":"10.1016/j.jacr.2024.10.002","url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 185-190"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142482495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Projected US Imaging Utilization, 2025 to 2055","authors":"Eric W. Christensen PhD ,&nbsp;Alexandra R. Drake MPH ,&nbsp;Jay R. Parikh MD ,&nbsp;Eric M. Rubin MD ,&nbsp;Elizabeth Y. Rula PhD","doi":"10.1016/j.jacr.2024.10.017","DOIUrl":"10.1016/j.jacr.2024.10.017","url":null,"abstract":"<div><h3>Purpose</h3><div>To project the future imaging utilization through 2055 and assess the contributions of population growth and aging, insurance type, and utilization trends on it.</div></div><div><h3>Methods</h3><div>The study used claims data from two sources (2018-2022): a CMS 5% sample of Medicare fee-for-service beneficiaries and the Inovalon Insights, LLC, database for individuals with commercial insurance, Medicare Advantage, or Medicaid. Based on sex, age, and insurance type, future utilization was statistically modeled based on US Census Bureau population projections and recent utilization trends by modality.</div></div><div><h3>Results</h3><div>The statistical analysis was based on person-year samples of 348,214,053 insured individuals covering those with Medicare fee-for-service, Medicare Advantage, Medicaid, and commercial insurance. Assuming no continuation of recent utilization trends, projected imaging utilization is 16.9% to 26.9% higher in 2055 compared with 2023 with this range, reflecting differences by modality. If recent utilization trends continue through 2030, this range is 5.6% less to 45.2% more. Population growth accounts for 73% to 88% of utilization increases across modalities; population aging accounts for 12% to 27%. Average utilization differed by insurance type (eg, average CT use was 0.70 for Medicare fee-for-service and 0.40 Medicare Advantage).</div></div><div><h3>Conclusions</h3><div>Projected imaging utilization in 2055 is 16.9% to 26.9% higher than 2023 levels assuming current per-person utilization will persist into the future, but continuation of recent per-person utilization trends broadens this range. Population growth is the largest driver of increasing future utilization. The continued shift to Medicare Advantage lowers utilization growth given its lower per-person utilization compared with Medicare fee-for-service.</div></div>","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"22 2","pages":"Pages 151-158"},"PeriodicalIF":4.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}