Global health systems' data science approach for precision diagnosis of sepsis in early life

Iregbu, Kenneth, Dramowski, Angela, Milton, Rebecca, Nsutebu, Emmanuel, Howie, Stephen R C, Chakraborty, Mallinath, Lavoie, Pascal M, Costelloe, Ceire E and Ghazal, Peter ORCID: https://orcid.org/0000-0003-0035-2228 2022. Global health systems' data science approach for precision diagnosis of sepsis in early life. The Lancet Infectious Diseases 22 (5) , E143-E152. 10.1016/S1473-3099(21)00645-9

Preview

PDF - Accepted Post-Print Version Download (292kB) | Preview

Abstract

Neonates and children in low-income and middle-income countries (LMICs) contribute to the highest number of sepsis-associated deaths globally. Interventions to prevent sepsis mortality are hampered by a lack of comprehensive epidemiological data and pathophysiological understanding of biological pathways. In this review, we discuss the challenges faced by LMICs in diagnosing sepsis in these age groups. We highlight a role for multi-omics and health care data to improve diagnostic accuracy of clinical algorithms, arguing that health-care systems urgently need precision medicine to avoid the pitfalls of missed diagnoses, misdiagnoses, and overdiagnoses, and associated antimicrobial resistance. We discuss ethical, regulatory, and systemic barriers related to the collection and use of big data in LMICs. Technologies such as cloud computing, artificial intelligence, and medical tricorders might help, but they require collaboration with local communities. Co-partnering (joint equal development of technology between producer and end-users) could facilitate integration of these technologies as part of future care-delivery systems, offering a chance to transform the global management and prevention of sepsis for neonates and children.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Medicine Centre for Trials Research (CNTRR)
Publisher:	Elsevier
ISSN:	1473-3099
Date of First Compliant Deposit:	14 January 2022
Date of Acceptance:	13 December 2021
Last Modified:	05 May 2023 00:26
URI:	https://orca.cardiff.ac.uk/id/eprint/146701

Citation Data

Cited 4 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item