Predicting deterioration in dengue using a low cost wearable for | ResearchBunny

Index

Abstract

This prospective observational clinical study in Vietnam (Jan 2020-Oct 2022) investigated the performance of a low-cost wearable using photoplethysmography (PPG) to predict dengue deterioration in hospitalized patients (n=153). A multi-modal transformer approach, using 10-min PPG segments and clinical data, continuously forecast clinical state. Predicting low-risk states (NEWS2 and CRAMS <6) achieved an AUPRC of 0.67 and AUROC of 0.83. This suggests potential for cost-effective triage and care.

Publisher

Nature Digital Medicine

Published On

Nov 22, 2024

Authors

Damien Keng Ming, John Daniels, Ho Quang Chanh, Stefan Karolcik, Bernard Hernandez, Vasileios Manginas, Van Hao Nguyen, Quang Huy Nguyen, Tu Qui Phan, Thi Hue Tai Luong, Huynh Trung Trieu, Alison Helen Holmes, Vinh Tho Phan, Pantelis Georgiou, Sophie Yacoub

Related Publications

Explore these studies to deepen your understanding of the subject.

Chemistry

Selective Formation of Methyl Branches in Ethylene Polymerization Using a Low-Cost Nickel Catalyst

Author1, Author2, et al.

Food Science and Technology

Designing a monitoring program for aflatoxin B1 in feed products using machine learning

X. Wang, Y. Bouzembrak, et al.

Psychology

Predicting recurrent chat contact in a psychological intervention for the youth using natural language processing

S. Hornstein, J. Scharfenberger, et al.

Medicine and Health

A microsystem for in vivo wireless monitoring of plastic biliary stents using magnetoelastic sensors

R. M. Nambisan, S. R. Green, 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