Commercially available low-cost air quality sensors have low accuracy. The improved accuracy of low-cost PM_2.5 sensors allows the use of low-cost sensor systems to reasonably investigate PM_2.5 emissions from industrial activities or to accurately estimate individual exposure to PM_2.5. In this work, we developed a new PM_2.5 calibration model (HybridLSTM) by combining a deep neural network (DNN) optimized in calibration problems and a long short-term memory (LSTM) neural network optimized in time-dependent characteristics to improve the performance of conventional calibration algorithms of low-cost PM sensors. The PM_2.5 concentrations, temperature and humidity by low-cost sensors and gravimetric-based PM_2.5 measuring instrument were sampled for a sufficiently long time. The proposed model was compared with benchmarks (multiple linear regression model (MLR), DNN model) and low-cost sensor results. The gravimetric measurements were used as reference data to evaluate sensor accuracy. For root-mean-square error (RMSE) for PM_2.5 concentrations, the proposed model reduced 41–60% of error when compared with the raw data of low-cost sensors, reduced 30–51% of error when compared with the MLR model and reduced 8–40% of error when compared with the MLR model. R² of HybridLSTM, DNN, MLR and raw data were 93, 90, 80 and 59%, respectively. HybridLSTM showed the state-of-the-art calibration performance for a low-cost PM sensor. In other words, the proposed ML model has state-of-the-art calibration performance among the tested calibration algorithms.

OBJECTIVES: Exposure to humidifier disinfectants has been linked to respiratory diseases, including interstitial lung disease, asthma, and pneumonia. Consequently, numerous toxicological studies have explored respiratory damage as both a necessary and sufficient condition for these diseases. We systematically reviewed and integrated evidence from toxicological studies by applying the evidence integration method established in previous research to confirm the biological plausibility of the association between exposure and disease.METHODS: We conducted a literature search focusing on polyhexamethylene guanidine phosphate (PHMG) and chloromethylisothiazolinone/methylisothiazolinone (CMIT/MIT), the primary ingredients in humidifier disinfectants. We selected relevant studies based on their quality and the population, exposure, comparator, outcome (PECO) statements. These studies were categorized into three lines of evidence: hazard information, animal studies, and mechanistic studies. Based on a systematic review, we integrated the evidence to develop an aggregate exposure pathway–adverse outcome pathway (AEP-AOP) model for respiratory damage. The reliability and relevance of our findings were assessed by comparing them with the hypothesized pathogenic mechanisms of respiratory diseases.RESULTS: By integrating toxicological evidence for each component of the AEP-AOP framework for PHMG and CMIT/MIT, we developed an AEP-AOP model that elucidates how disinfectants released from humidifiers expose target sites, triggering molecular initiating events and key events that ultimately lead to respiratory damage. This model exhibits high reliability and relevance to the pathogenesis of respiratory diseases.CONCLUSIONS: The AEP-AOP model developed in this study provides strong evidence, based on evidence-based toxicology, that exposure to humidifier disinfectants causes respiratory diseases. This model demonstrates the pathways leading to respiratory damage, a hallmark of these conditions.

OBJECTIVES: Inhalation exposure to humidifier disinfectants has resulted to various types of health damages in Korea. To determine the epidemiological correlation necessary for presuming the legal causation, we aimed to develop a method to synthesize the entire evidence.METHODS: Epidemiological and toxicological studies are systematically reviewed. Target health problems are selected by criteria such as frequent complaints of claimants. Relevant epidemiologic studies are reviewed and the risk of bias and confidence level of the total evidence are evaluated. Toxicological literature reviews are conducted on three lines of evidence including hazard information, animal studies, and mechanistic studies, considering the source-to-exposure-to-outcome continuum. The confidence level of the body of evidence is then translated into the toxicological evidence levels for the causality between humidifier disinfectant exposure and health effects. Finally, the levels of epidemiological and toxicological evidence are synthesized.RESULTS: Under the Special Act revised in 2020, if the history of exposure and the disease occurred/worsened after exposure were approved, and the epidemiological correlation between the exposure and disease was verified, the legal causation is presumed unless the company proves the evidence against it. The epidemiological correlation can be verified through epidemiological investigations, health monitoring, cohort investigations and/or toxicological studies. It is not simply as statistical association as understood in judicial precedents, but a general causation established by the evidence as a whole, i.e., through weight-of-the-evidence approach.CONCLUSIONS: The weight-of-the-evidence approach differs from the conclusive single study approach and this systematic evidence integration can be used in presumption of causation.

There is a pressing need for tools that can rapidly predict ${\mathrm{PM}}_{2.5}$ concentrations and assess health impacts under various emission scenarios, aiding in the selection of optimal mitigation strategies. Traditional chemical transport models (CTMs) like CMAQ are accurate but computationally intensive, limiting practical scenario analysis. To address this, we propose a novel method integrating a conditional U-Net surrogate model with health impact assessments, enabling swift estimation of ${\mathrm{PM}}_{2.5}$ concentrations and related health effects. The U-Net model was trained with 2019 South Korean ${\mathrm{PM}}_{2.5}$ data, including precursor emissions and boundary conditions. Our model showed high accuracy and significant efficiency, reducing processing times while maintaining reliability. By combining this surrogate model with the EPA’s BenMAP-CE tool, we estimated potential premature deaths under various emission reduction scenarios in South Korea, extending projections to 2050 to account for demographic changes. Additionally, we assessed the required ${\mathrm{PM}}_{2.5}$ emission reductions needed to counteract the increase in premature deaths due to an aging population. This integrated framework offers an efficient, user-friendly tool that bridges complex air quality modeling with practical policy evaluation, supporting the development of effective strategies to reduce ${\mathrm{PM}}_{2.5}$-related health risks and estimate economic benefits.