Skip to main navigation Skip to search Skip to main content

Optimizing Timeliness of Healthcare Delivery in Diagnostic Radiology at U.S. Academic Centers

  • Cedric W. Pluguez-Turull
  • , Joel Koshy
  • , Morgan P. McBee
  • , Eniola Oluyemi
  • , Diana L. Lam
  • , Sarah M. Desoky
  • , Stephane L. Desouches
  • , Sara Siddiqui
  • , Taha Lodhi
  • , Nina Capiro
  • , Vikas Agarwal
  • , Tanvi Kongara
  • , Katharine Lampen-Sachar
  • , Lauren T. Hui
  • , Angela I. Choe

Research output: Contribution to journal › Article › peer-review

Abstract

Rationale and Objectives Timely radiology access is essential for accurate diagnosis, treatment planning, and efficient care delivery. U.S. academic health centers face distinctive pressures, including workforce shortages, complex workflows, health inequities, and the need to balance trainee education with increasing clinical demand. Materials and Methods This article summarizes consensus conclusions and literature review findings from the Radiology Research Alliance task force on optimizing healthcare delivery in U.S. academic centers. Task force members reviewed operational and systemic contributors to delayed imaging access and radiology report turnaround time (RTAT), with attention to disparities, workflow design, trainee involvement, and emerging artificial intelligence (AI) applications. Results Delays in radiology care arise from social and insurance-related barriers, staffing shortages, workflow inefficiencies, and reporting delays. Underserved populations experience reduced access to preventive imaging, which may be improved through culturally tailored outreach, frontline staff engagement, and patient navigation. In academic settings, RTAT is influenced by image transmission, case complexity, reporting practices, and trainee participation. Evidence suggests that structured reporting, subspecialty or optimized workflow organization, critical results notification, and dual-reader trainee-attending models can improve efficiency while maintaining educational value. AI and machine learning (ML) show promise for clinical decision support (CDS), scheduling, no-show reduction, risk prediction, workflow optimization, and demand forecasting. Conclusion Improving radiology delivery in academic centers requires coordinated system-level strategies that address equity, staffing, workflow, and reporting efficiency. Thoughtful integration of AI, alongside operational redesign that preserves trainee development, can help academic radiology advance timely, high-quality, and equitable care.

Original languageEnglish (US)
Pages (from-to)2809-2814
Number of pages6
JournalAcademic Radiology
Volume33
Issue number7
DOIs
StatePublished - Jul 2026

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Optimizing Timeliness of Healthcare Delivery in Diagnostic Radiology at U.S. Academic Centers'. Together they form a unique fingerprint.

Cite this