{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T11:46:49Z","timestamp":1782906409648,"version":"3.54.5"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:p>\n                    This study seeks to address critical gaps in household air pollution (HAP) exposure assessment in low- and middle-income settings by applying a proxy-based exposure reconstruction framework supported by machine learning to develop an exploratory proxy-based exposure index and examine associations with nonlinear health patterns in Kabale, Uganda. A quantitative cross-sectional survey (\n                    <jats:italic>N<\/jats:italic>\n                    \u202f=\u202f275) was conducted to capture behavioral, environmental, and socio-demographic proxies of exposure, including fuel type, cooking duration, ventilation, and cooking location. A latent exposure index was developed using Principal Component Analysis and validated with Random Forest and Gradient Boosting models, while nonlinear exposure\u2013health relationships were analyzed using ML classifiers and household typologies identified through\n                    <jats:italic>K<\/jats:italic>\n                    -Means clustering. The findings reveal that exposure is driven primarily by behavioral factors, particularly cooking duration, rather than fuel type alone. Nonlinear modeling suggested possible threshold-like and plateauing patterns in self-reported health outcomes, with acute symptoms such as eye irritation appearing at lower proxy-based exposure levels and chronic respiratory distress showing possible plateauing at higher exposure levels. Clustering analysis identifies a large high-risk group characterized by prolonged indoor biomass use and elevated symptom burden. ML models outperform traditional regression approaches in predicting chronic symptoms but show limited performance for clinical diagnoses. These findings suggest that proxy-based HAP exposure patterns may be multidimensional and potentially nonlinear and demonstrate the value of ML in proxy-based environments, emphasizing that policy interventions must move beyond fuel switching to address behavioral practices and structural constraints shaping exposure.\n                  <\/jats:p>","DOI":"10.3389\/fpubh.2026.1863424","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T10:54:33Z","timestamp":1782903273000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Proxy-based modeling of indoor air pollution exposure and nonlinear health patterns in biomass-dependent households using machine learning"],"prefix":"10.3389","volume":"14","author":[{"given":"Adeyinka","family":"Odebode","sequence":"first","affiliation":[{"name":"Bishop Barham University College, Uganda Christian University","place":["Kabale, Uganda"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olusiji","family":"Lasekan","sequence":"additional","affiliation":[{"name":"Universidad Cat\u00f3lica de Temuco","place":["Temuco, Chile"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayorinde","family":"Ogundele","sequence":"additional","affiliation":[{"name":"Universidad de La Frontera","place":["Temuco, Chile"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H\u00e9ctor H.","family":"Silva","sequence":"additional","affiliation":[{"name":"Universidad de La Frontera","place":["Temuco, Chile"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boluwatife","family":"Adigun","sequence":"additional","affiliation":[{"name":"ART Clinic, Regional Referral Hospital","place":["Kabale, Uganda"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"ref1","first-page":"1","article-title":"Biomass fuel smoke: a silent killer","volume":"28","author":"Ali","year":"2014","journal-title":"J Postgrad Med Inst"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"A424","DOI":"10.1289\/ehp.1002397","article-title":"The global burden of air pollution on mortality: the need to include exposure to household biomass fuel\u2013derived particulates","volume":"118","author":"Rylance","year":"2010","journal-title":"Environ Health Perspect"},{"key":"ref3","first-page":"332","volume-title":"In Textbook of Children\u2019s Environmental Health (2nd ed.)","author":"Roshan","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1186\/s12199-020-00902-4","article-title":"Household air pollution and under-five mortality in sub-Saharan Africa: an analysis of 14 demographic and health surveys","volume":"25","author":"Bickton","year":"2020","journal-title":"Environ Health Prev Med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e2022GH000673","DOI":"10.1029\/2022GH000673","article-title":"The effects of trash, residential biofuel, and open biomass burning emissions on local and transported PM2. 5 and its attributed mortality in Africa","volume":"7","author":"Gordon","year":"2023","journal-title":"GeoHealth"},{"key":"ref6","article-title":"Improving household air quality: the neglected cultural dimension","volume":"33","author":"Kaba","year":"2019","journal-title":"Ethiop J Heal Dev"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"118979","DOI":"10.1016\/j.ecoenv.2025.118979","article-title":"Trends in all-cause mortality attributable to particulate matter 2.5 pollution in sub-Saharan Africa: an age-period-cohort analysis","volume":"303","author":"Bao","year":"2025","journal-title":"Ecotoxicol Environ Saf"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1186\/s12940-025-01216-0","article-title":"Impact of prenatal and postnatal household air pollution exposure on respiratory morbidity and lung function in sub-Saharan African children: a systematic review and meta-analysis","volume":"24","author":"Zigabe","year":"2025","journal-title":"Environ Health"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e76","DOI":"10.1002\/ail2.76","article-title":"Applying machine learning for large scale field calibration of low-cost PM\u2082.\u2085 and PM\u2082.\u2085 air pollution sensors","volume":"3","author":"Adong","year":"2022","journal-title":"Applied AI Letters"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"59","DOI":"10.56893\/ajhes2024v03i01.06","article-title":"Monitoring and predicting African rural household air pollution using internet of things and artificial intelligence","volume":"3","author":"Ooko","year":"2024","journal-title":"Pan-Afr J Health Environ Sci"},{"key":"ref11","first-page":"1","volume-title":"AI_r: Transforming Air Quality Monitoring Through Cost-effective AI Solutions. 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Turkiye","author":"Tshuma","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1080\/104732200301962","article-title":"A tiered approach to deterministic models for indoor air exposures","volume":"15","author":"Keil","year":"2000","journal-title":"Appl Occup Environ Hyg"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"33","DOI":"10.4236\/ojap.2014.32004","article-title":"Use of ventilation-index in the development of exposure model for indoor air pollution\u2014a review","volume":"3","author":"Mukhopadhyay","year":"2014","journal-title":"Open J Air Pollut"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1007\/s42452-019-0405-8","article-title":"Impact of household air pollution on human health: source identification and systematic management approach","volume":"1","author":"Ahmed","year":"2019","journal-title":"SN Appl Sci"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/978-981-15-1334-3_4","volume-title":"Indoor Environmental Quality: Select Proceedings of the 1st ACIEQ","author":"Ravindra","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e119","DOI":"10.1097\/EE9.0000000000000119","article-title":"A hierarchical model for estimating the exposure-response curve by combining multiple studies of acute lower respiratory infections in children and household fine particulate matter air pollution","volume":"4","author":"Keller","year":"2020","journal-title":"Environ Epidemiol"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/B978-0-12-801238-3.11494-1","article-title":"Household Air Pollution and Associated Health Effects in Low and Middle Income Countries","volume-title":"Encyclopedia of Respiratory Medicine","author":"Newell","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"105001","DOI":"10.1289\/EHP7010","article-title":"Systems science approaches for global environmental health research: enhancing intervention design and implementation for household air pollution (HAP) and water, sanitation, and hygiene (WASH) programs","volume":"128","author":"Rosenthal","year":"2020","journal-title":"Environ Health Perspect"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1289\/ehp.021101069","article-title":"Daily average exposures to respirable particulate matter from combustion of biomass fuels in rural households of southern India","volume":"110","author":"Balakrishnan","year":"2002","journal-title":"Environ Health Perspect"},{"key":"ref20","first-page":"426","article-title":"Indoor air quality for poor families: new evidence from Bangladesh","volume-title":"Indoor Air.","author":"Dasgupta","year":"2006"},{"key":"ref21","first-page":"1","article-title":"Improved chulahs to reduce indoor air pollution","volume":"5","author":"Venmathi","year":"2010","journal-title":"J Environ Res Dev"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e22198","DOI":"10.1002\/tqem.22198","article-title":"Optimizing indoor air quality: investigating particulate matter exposure in household kitchens and source identification","volume":"34","author":"Alhajeri","year":"2024","journal-title":"Environ Qual Manag"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.jer.2023.100126","article-title":"Investigating major sources of air pollution and improving spatiotemporal forecast accuracy using supervised machine learning and a proxy","volume":"11","author":"Alolayan","year":"2023","journal-title":"J Eng Res"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e2024GH001188","DOI":"10.1029\/2024GH001188","article-title":"Methods for quantifying source-specific air pollution exposure to serve epidemiology, risk assessment, and environmental justice","volume":"8","author":"Shan","year":"2024","journal-title":"GeoHealth"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1016\/j.jaci.2019.04.019","article-title":"Assessing exposure to outdoor air pollution for epidemiological studies: model-based and personal sampling strategies","volume":"143","author":"Brokamp","year":"2019","journal-title":"J Allergy Clin Immunol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s40572-021-00310-y","article-title":"Fine-scale air pollution models for epidemiologic research: insights from approaches developed in the multi-ethnic study of atherosclerosis and air pollution (MESA air)","volume":"8","author":"Kirwa","year":"2021","journal-title":"Curr Environ Health Rep"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/jes.2013.62","article-title":"Exposure prediction approaches used in air pollution epidemiology studies: key findings and future recommendations","volume":"23","author":"Baxter","year":"2013","journal-title":"J Expo Sci Environ Epidemiol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2843","DOI":"10.1021\/acs.est.1c01739","article-title":"Selecting data analytic and modeling methods to support air pollution and environmental justice investigations: a critical review and guidance framework","volume":"56","author":"Gardner-Frolick","year":"2022","journal-title":"Environ Sci Technol"},{"key":"ref29","first-page":"1","volume-title":"Deep Learning Model to Estimate Air Pollution using M-BP to Fill in Missing Proxy Urban Data","author":"Li","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1097\/MCP.0000000000001126","article-title":"Household air pollution and respiratory health in Africa: persistent risk and unchanged health burdens","volume":"31","author":"Jafta","year":"2025","journal-title":"Curr Opin Pulm Med"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e95","DOI":"10.1016\/S2542-5196(23)00272-3","article-title":"Household concentrations and female and child exposures to air pollution in peri-urban sub-Saharan Africa: measurements from the CLEAN-air (Africa) study","volume":"8","author":"Shupler","year":"2024","journal-title":"Lancet Planet Heath"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"6856","DOI":"10.1038\/s41598-024-81413-y","article-title":"Multinational modelling of PM2. 5 and CO exposures from household air pollution in peri-urban Cameroon, Ghana and Kenya","volume":"15","author":"Williams","year":"2025","journal-title":"Sci Rep"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"34249","DOI":"10.1038\/s41598-025-16294-w","article-title":"Common symptoms experienced while cooking with biomass fuel among pregnant women in South Gondar zone","volume":"15","author":"Enyew","year":"2025","journal-title":"Sci Rep"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"122619","DOI":"10.1016\/j.envres.2025.122619","article-title":"Air pollution and health in Rwandan and Kenyan schools cooking with polluting fuels: a cross-sectional impact study","volume":"285","author":"Nabukwangwa","year":"2025","journal-title":"Environ Res"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-026-38186-3","article-title":"Impact of household air pollution on under 5 mortalities and ARI in sub Saharan Africa: evidence from demographic and health survey 2010\u20132020","volume":"16","author":"Joseph","year":"2026","journal-title":"Sci Rep"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e612","DOI":"10.1016\/S2214-109X(26)00002-1","article-title":"Household energy use and health in low-income and middle-income countries","volume":"14","author":"Pillarisetti","year":"2026","journal-title":"Lancet Glob Health"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"180593","DOI":"10.1016\/j.scitotenv.2025.180593","article-title":"Machine learning for air quality prediction and data analysis: Review on recent advancements, challenges, and outlooks","volume":"1002","author":"Karmoude","year":"2025","journal-title":"Science of The Total Environment"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1863424\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T10:54:41Z","timestamp":1782903281000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1863424\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":37,"alternative-id":["10.3389\/fpubh.2026.1863424"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1863424","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"article-number":"1863424"}}