logo
ResearchBunny Logo
Deciphering clinical abbreviations with a privacy protecting machine learning system

Medicine and Health

Deciphering clinical abbreviations with a privacy protecting machine learning system

A. Rajkomar, E. Loreaux, et al.

Physicians often rely on clinical abbreviations, leading to confusion for patients and even their peers. This groundbreaking research from Alvin Rajkomar and team harnesses a machine learning model to decode these shorthand terms with remarkable accuracy, sometimes outperforming board-certified physicians. Discover how technology can bridge the gap in medical communication!

00:00
00:00
Playback language: English
Abstract
Physicians use clinical abbreviations and shorthand in notes, causing comprehension issues for patients and even clinicians. This paper presents a machine learning model trained on public web data to decipher these abbreviations. A single translation model achieves 92.1%-97.1% accuracy in detecting and expanding thousands of abbreviations, exceeding the performance of board-certified physicians in some cases (97.6% vs 88.7% total accuracy). The method avoids using privacy-compromising data.
Publisher
Nature Communications
Published On
Dec 02, 2022
Authors
Alvin Rajkomar, Eric Loreaux, Yuchen Liu, Jonas Kemp, Benny Li, Ming-Jun Chen, Yi Zhang, Afroz Mohiuddin, Juraj Gottweis
Tags
machine learning
clinical abbreviations
comprehension issues
medical communication
accuracy
model performance
privacy

Related Publications

Explore these studies to deepen your understanding of the subject.

Detecting lithium plating dynamics in a solid-state battery with operando X-ray computed tomography using machine learning
Engineering and Technology

Detecting lithium plating dynamics in a solid-state battery with operando X-ray computed tomography using machine learning

Y. Huang, D. Perlmutter, et al.

On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare
Computer Science

On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare

S. Mittal, K. Thakral, et al.

Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals
Linguistics and Languages

Transforming machine translation: a deep learning system reaches news translation quality comparable to human professionals

M. Popel, M. Tomkova, et al.

Prognosis Individualized: Survival predictions for WHO grade II and III gliomas with a machine learning-based web application
Medicine and Health

Prognosis Individualized: Survival predictions for WHO grade II and III gliomas with a machine learning-based web application

M. Karabacak, P. Jagtiani, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny