Elicitation of domain knowledge for a machine learning model for paediatric critical illness in South Africa - Objectives, design and Delphi procedure

Aug 3, 2026

Upload by Finn

Delays in identification, resuscitation and referral contribute to preventable severity and mortality among South African children, motivating development of a machine learning model predicting a compound outcome of death prior to discharge and/or admission to a paediatric intensive care unit. The study documents how domain knowledge was elicited using a documented literature search and a Delphi procedure. Findings describe selected risk factors and consensus-derived severe-illness clinical features, supporting rigorous feature selection.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Objectives

Design

Setting and Participants

Measurements and Main Results

Conclusion

Keywords

TYPE Original Research PUBLISHED 21 February 2023 DOI 10.3389/fped.2023.1005579 EDITED BY Stephen Aronoff, Temple University, United States REVIEWED BY Monty Mazer, Rainbow Babies & Children’s Hospital, United States Nicole Rübsamen, University of Münster, Germany *CORRESPONDENCE Michael A. Pienaar [pienaarma1@ufs.ac.za](pienaarma1@ufs.ac.za) SPECIALTY SECTION This article was submitted to Pediatric Critical Care, a section of the journal Frontiers in Pediatrics RECEIVED 28 July 2022 ACCEPTED 25 January 2023 PUBLISHED 21 February 2023 CITATION Pienaar MA, Sempa JB, Luwes N, George EC and Brown SC (2023) Elicitation of domain knowledge for a machine learning model for paediatric critical illness in South Africa. Front. Pediatr. 11:1005579 . doi: 10.3389/fped.2023.1005579 COPYRIGHT © 2023 Pienaar, Sempa, Luwes, George and Brown. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Elicitation of domain knowledge fora machine learning model for paediatric critical illness in South Africa Michael A. Pienaar1*, Joseph B. Sempa2, Nicolaas Luwes3, Elizabeth C. George4 and Stephen C. Brown5 1Department of Paediatrics and Child Health, Paediatric Critical Care Unit, University of the Free State, Bloemfontein, South Africa, 2Department of Biostatistics, Faculty of Health Sciences, University of the Free State, Bloemfontein, South Africa, 3Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Built Environment and Information Technology, Central University of Technology, Bloemfontein, South Africa, 4Medical Research Council Clinical Trials Unit, University College London, London, United Kingdom, 5Paediatric Cardiology Unit, Department of Paediatrics and Child Health, University of the Free State, Bloemfontein, South Africa Objectives: Delays in identiﬁcation, resuscitation and referral have been identiﬁed as a preventable cause of avoidable severity of illness and mortality in South African children. To address this problem, a machine learning model to predict a compound outcome of death prior to discharge from hospital and/or admission to the PICU was developed. A key aspect of developing machine learning models is the integration of human knowledge in their development. The objective of this study is to describe how this domain knowledge was elicited, including the use of a documented literature search and Delphi procedure. Design: A prospective mixed methodology development study was conducted that included qualitative aspects in the elicitation of domain knowledge, together with descriptive and analytical quantitative and machine learning methodologies. Setting: A single centre tertiary hospital providing acute paediatric services. Participants: Three paediatric intensivists, six specialist paediatricians and three specialist anaesthesiologists. Interventions: None. Measurements and main results: The literature search identiﬁed 154 full-text articles reporting risk factors for mortality in hospitalised children. These factors were most commonly features of speciﬁc organ dysfunction. 89 of these publications studied children in lower-and middle-income countries. The Delphi procedure included 12 expert participants and was conducted over 3 rounds. Respondents identiﬁed a need to achieve a compromise between model performance, comprehensiveness and veracity and practicality of use. Participants achieved consensus on a range of clinical features associated with severe illness in children. No special investigations were considered for inclusion in the mod

FAQs

What clinical problem does the study address in South African paediatric care?

The study addresses preventable delays in identification, resuscitation and referral that lead to avoidable severity of illness and mortality in South African children.

How was domain knowledge elicited for the machine learning model?

Domain knowledge was elicited through a documented literature search of mortality risk factors and a Delphi procedure involving expert clinicians over three rounds.

What was the Delphi procedure used to determine?

Experts reached consensus on clinical features associated with severe illness, guiding the final list of features for model development and reducing reliance on special investigations.

Aug 3, 2026

Upload by Finn