Air pollution-related health impacts from domestic waste burning and associated interventions: the merits of a traditional versus machine learning scoping review methodology
8 affiliations
- 1Climate Change and Health Research Programme, Environment and Health Research Unit, South African Medical Research Council, Pretoria, South Africa. [email protected]
- 2Climate Change and Health Research Programme, Environment and Health Research Unit, South African Medical Research Council, Pretoria, South Africa
- 3School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa
- 4Machine Intelligence and Neural Discovery Unit, University of the Witwatersrand, Johannesburg, South Africa
- 5Department of Environmental Health, University of Johannesburg, Johannesburg, South Africa
- 6Environment and Health Research Unit, South African Medical Research Council, Cape Town, South Africa
- 7Department of Environment, Climate Change and Health, World Health Organization, Geneva, Switzerland
- 8Department of Geography, Geoinformatics and Meteorology, University of Pretoria, Pretoria, South Africa
Abstract
Regularly updating repositories of air pollution impacts on health is essential for evidence-based policies, interventions, and progress monitoring. However, this is often time-consuming and labour-intensive. Automation can ensure up-to-date evidence; reduce retrieval, screening time, and costs; and make information accessible to non-academic stakeholders. This study investigated whether a machine learning approach can perform any stages of a traditional scoping review on the health impacts, policies, and interventions related to air pollution due to domestic waste burning. A traditional approach was conducted in parallel with machine learning methods enabling a comparison of the efficiency and quality of the partially automated approach against the manual review. Findings from the two approaches were compared and the final set of included articles were considered for (1) reported impacts of waste burning on health outcomes and (2) recommendations on solutions and interventions to prevent/reduce adverse effects on health from waste burning. We found a range of health impacts associated with waste burning, including low birth weight, hypertensive disorders of pregnancy, adverse respiratory outcomes like asthma and wheeze, cancer risk, and mortality. Few studies proposed solutions or evaluated the effectiveness of interventions. The ML approach showed a tendency towards false positives, which are preferable to false negatives (where relevant papers were excluded). Results showed that the model can conduct initial searches and decisions for the review. However, the articles included in the model should be screened manually for final acceptance. Therefore, we propose a hybrid approach be used until the automated model can be further refined.
Related
- Comparative Analysis of Traditional and Modern Extraction Techniques for Phenolic Compounds From Leontopodium and Optimization of Extraction Process Using Response Surface Methodology.
- Macrophage lipophagy in atherosclerosis: from molecular mechanisms to traditional Chinese medicine interventions
- Traditional Chinese medicine interventions and mitochondrial communication in myocardial and cerebral ischemia: a critical review
- Non-pharmacological traditional Chinese medicine interventions for depression: bibliometric mapping of Chinese databases and WoSCC, 2000-2025.
- Mechanisms of traditional Chinese medicine interventions in the gastric ‘inflammation-to-carcinoma’ cascade: advances in in vitro models from monolayer cells to organoids
BibTeX
@article{kapwata2026pollutionrelated,
title = {{Air pollution-related health impacts from domestic waste burning and associated interventions: the merits of a traditional versus machine learning scoping review methodology}},
author = {Thandi Kapwata and Candice Webster and Wen Guan Gavin Chen and Muhammad Ibrahim Suder and Devon Jarvis and Alex Vogt and Nomfundo Thobeka Mahlangeni and Tracey Leah Laban and Natasha Naidoo and Pierpaolo Mudu and Kerolyn K. Shairsingh and Caradee Y. Wright},
journal = {Environmental Monitoring and Assessment},
year = {2026},
month = may,
doi = {10.1007/s10661-026-15376-0},
url = {https://doi.org/10.1007/s10661-026-15376-0},
note = {CC BY},
}
RIS
TY - JOUR
TI - Air pollution-related health impacts from domestic waste burning and associated interventions: the merits of a traditional versus machine learning scoping review methodology
AU - Thandi Kapwata
AU - Candice Webster
AU - Wen Guan Gavin Chen
AU - Muhammad Ibrahim Suder
AU - Devon Jarvis
AU - Alex Vogt
AU - Nomfundo Thobeka Mahlangeni
AU - Tracey Leah Laban
AU - Natasha Naidoo
AU - Pierpaolo Mudu
AU - Kerolyn K. Shairsingh
AU - Caradee Y. Wright
PY - 2026
DA - 2026/05/18
JO - Environmental Monitoring and Assessment
DO - 10.1007/s10661-026-15376-0
UR - https://doi.org/10.1007/s10661-026-15376-0
AB - Regularly updating repositories of air pollution impacts on health is essential for evidence-based policies, interventions, and progress monitoring. However, this is often time-consuming and labour-intensive. Automation can ensure up-to-date evidence; reduce retrieval, screening time, and costs; and make information accessible to non-academic stakeholders. This study investigated whether a machine learning approach can perform any stages of a traditional scoping review on the health impacts, policies, and interventions related to air pollution due to domestic waste burning. A traditional approach was conducted in parallel with machine learning methods enabling a comparison of the efficiency and quality of the partially automated approach against the manual review. Findings from the two approaches were compared and the final set of included articles were considered for (1) reported impacts of waste burning on health outcomes and (2) recommendations on solutions and interventions to prevent/reduce adverse effects on health from waste burning. We found a range of health impacts associated with waste burning, including low birth weight, hypertensive disorders of pregnancy, adverse respiratory outcomes like asthma and wheeze, cancer risk, and mortality. Few studies proposed solutions or evaluated the effectiveness of interventions. The ML approach showed a tendency towards false positives, which are preferable to false negatives (where relevant papers were excluded). Results showed that the model can conduct initial searches and decisions for the review. However, the articles included in the model should be screened manually for final acceptance. Therefore, we propose a hybrid approach be used until the automated model can be further refined.
SN - 0167-6369
SN - 1573-2959
ER -