Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
519 Bridging the Gap in Pathology Informatics Education: A Two-Year Comparative Study of Resident Performance and a Nationwide Training Framework
0
Zitationen
3
Autoren
2025
Jahr
Abstract
Abstract Introduction/Objective Pathology informatics is vital to modern diagnostics but often lacks structured integration in residency training. Currently, many programs have adopted the PIER-3 (Pathology Informatics Essentials for Residents) curriculum as a national standard. This study assesses the educational impact of informatics-focused lectures and a dedicated PGY4 rotation on resident RISE performance, and proposes scalable strategies for nationwide curriculum improvement. Methods/Case Report We retrospectively reviewed the ASCP RISE Pathology Informatics percentiles from 2024 and 2025 at the University of Missouri-Columbia. In 2024, residents attended 10 lectures and PGY4s completed an informatics rotation. In 2025, only one lecture was offered, though the rotation remained. We analyzed score trends by postgraduate year. Based on observed performance shifts, we propose a national educational model to improve informatics competency. Results The 2024 cohort showed strong performance across PGY levels, with PGY3–4 reaching the 90th percentile. In 2025, the overall score rose to the 84th percentile due to PGY2 gains (99th percentile), but PGY1 performance dropped to 22nd percentile, correlating with reduced didactic exposure. Conclusion To address such disparities nationally, we recommend: (1) a standardized tiered curriculum by PGY level; (2) year-round modular teaching; (3) hands-on projects; (4) virtual bootcamps; (5) informatics-embedded assessments; and (6) national mentorship programs. Broader adoption and evolution of PIER-3—and ultimately transitioning to an updated PIER-4 framework—will be key to cultivating a digitally fluent pathology workforce.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 13.819 Zit.
Dermatologist-level classification of skin cancer with deep neural networks
2017 · 13.394 Zit.
A survey on Image Data Augmentation for Deep Learning
2019 · 11.983 Zit.
QuPath: Open source software for digital pathology image analysis
2017 · 8.334 Zit.
Radiomics: Images Are More than Pictures, They Are Data
2015 · 8.101 Zit.