Related Experiment Video
Updated: Aug 7, 2025
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Elicitation of domain knowledge for a machine learning model for paediatric critical illness in South Africa
Michael A Pienaar1, Joseph B Sempa2, Nicolaas Luwes3
1Department of Paediatrics and Child Health, Paediatric Critical Care Unit, University of the Free State, Bloemfontein, South Africa.
Insights
This study details how expert knowledge was gathered using literature reviews and a Delphi process to build a machine learning model predicting severe illness and mortality in South African children.
Area of Science:
- Paediatric critical care research.
- Machine learning applications in healthcare.
- Clinical decision support systems.
Background:
- Delays in identifying, resuscitating, and referring critically ill children contribute to preventable mortality in South Africa.
- Machine learning models can aid in predicting adverse outcomes, but require robust domain knowledge integration.
- Existing models often lack comprehensive integration of clinical expertise.
Purpose of the Study:
- To describe the process of eliciting domain knowledge for a machine learning model predicting severe paediatric illness and mortality.
- To outline the methodology involving literature searches and expert consensus (Delphi procedure).
- To ensure the developed model is clinically relevant and practical for use.
Main Methods:
- A prospective mixed-methods study combining qualitative and quantitative approaches.
- A comprehensive literature search identifying 154 articles on risk factors for childhood mortality.
- A 3-round Delphi procedure with 12 paediatric specialists and anaesthesiologists to achieve consensus on clinical features.
Main Results:
- The literature search highlighted organ dysfunction features as common mortality predictors, with many studies from low- and middle-income countries.
- Experts reached consensus on key clinical features for severe illness prediction, prioritizing practicality and performance.
- Point-of-care capillary blood glucose testing was the only special investigation deemed essential for the model.
Conclusions:
- Eliciting and documenting domain knowledge is crucial for developing rigorous and effective machine learning models in healthcare.
- The integrated domain knowledge informed problem specification and feature selection for the predictive model.
- This systematic approach enhances the reliability and clinical utility of machine learning tools in paediatric care.
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 model except point-of-care capillary blood glucose testing. The results were integrated by the researcher and a final list of features was compiled.
Conclusion:
The elicitation of domain knowledge is important in effective machine learning applications. The documentation of this process enhances rigour in such models and should be reported in publications. A documented literature search, Delphi procedure and the integration of the domain knowledge of the researchers contributed to problem specification and selection of features prior to feature engineering, pre-processing and model development.
More Related Videos
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
