Adverse impacts of Asian dust events on human health and the environment-A probabilistic risk assessment study on particulate matter-bound metals and bacteria in Seoul, South Korea.

This study aimed to assess the impact of Asian dust (AD) on the human health and the environment. Particulate matter (PM) and PM-bound trace elements and bacteria were examined to determine the chemical and biological hazards associated with AD days and compared with non-AD days in Seoul. On AD days, the mean PM10 concentration was ∼3.5 times higher than that on non-AD days. Elements generated from the Earth's crust (Al, Fe, and Ca) and anthropogenic sources (Pb, Ni, and Cd) were identified as major contributors to coarse and fine particles, respectively. During AD days, the study area was recognized as "severe" for pollution index and pollution load index levels, and "moderately to heavily polluted" for geoaccumulation index levels. The potential cancer risk (CR) and non-CR were estimated for the dust generated during AD events. On AD days, total CR levels were significant (in 1.08 × 10-5-2.22 × 10-5), which were associated with PM-bound As, Cd, and Ni. In addition, inhalation CR was found to be similar to the incremental lifetime CR levels estimated using the human respiratory tract mass deposition model. In a short exposure duration (14 days), high PM and bacterial mass deposition, significant non-CR levels, and a high presence of potential respiratory infection-causing pathogens (Rothia mucilaginosa) were observed during AD days. Significant non-CR levels were observed for bacterial exposure, despite insignificant levels of PM10-bound elements. Therefore, the substantial ecological risk, CR, and non-CR levels for inhalation exposure to PM-bound bacteria, and the presence of potential respiratory pathogens, indicate that AD events pose a significant risk to both human lung health and the environment. This study provides the first comprehensive examination of significant non-CR levels for bacteria and carcinogenicity of PM-bound metals during AD events.

Self-optimization of training dataset improves forecasting of cyanobacterial bloom by machine learning.

Data-driven model (DDM) prediction of aquatic ecological responses, such as cyanobacterial harmful algal blooms (CyanoHABs), is critically influenced by the choice of training dataset. However, a systematic method to choose the optimal training dataset considering data history has not yet been developed. Providing a comprehensive procedure with self-based optimal training dataset-selecting algorithm would self-improve the DDM performance. In this study, a novel algorithm was developed to self-generate possible training dataset candidates from the available input and output variable data and self-choose the optimal training dataset that maximizes CyanoHAB forecasting performance. Nine years of meteorological and water quality data (input) and CyanoHAB data (output) from a site on the Nakdong River, South Korea, were acquired and pretreated via an automated process. An artificial neural network (ANN) was chosen from among the DDM candidates by first-cut training and validation using the entire collected dataset. Optimal training datasets for the ANN were self-selected from among the possible self-generated training datasets by systematically simulating the performance in response to 46 periods and 40 sizes (number of data elements) of the generated training datasets. The best-performing models were screened to identify the candidate models. The best performance corresponded to 6-7 years of training data (∼18 % lower error) for forecasting 1-28 d ahead (1-28 d of forecasting lead time (FLT)). After the hyperparameters of the screened model candidates were fine-tuned, the best-performing model (7 years of data with 14 d FLT) was self-determined by comparing the forecasts with unseen CyanoHAB events. The self-determined model could reasonably predict CyanoHABs occurring in Korean waters (cyanobacteria cells/mL ≥ 1000). Thus, our proposed method of self-optimizing the training dataset effectively improved the predictive accuracy and operational efficiency of the DDM prediction of CyanoHAB.

Challenges of diet planning for children using artificial intelligence.

BACKGROUND/OBJECTIVES: Diet planning in childcare centers is difficult because of the required knowledge of nutrition and development as well as the high design complexity associated with large numbers of food items. Artificial intelligence (AI) is expected to provide diet-planning solutions via automatic and effective application of professional knowledge, addressing the complexity of optimal diet design. This study presents the results of the evaluation of the utility of AI-generated diets for children and provides related implications. MATERIALS/METHODS: We developed 2 AI solutions for children aged 3-5 yrs using a generative adversarial network (GAN) model and a reinforcement learning (RL) framework. After training these solutions to produce daily diet plans, experts evaluated the human- and AI-generated diets in 2 steps. RESULTS: In the evaluation of adequacy of nutrition, where experts were provided only with nutrient information and no food names, the proportion of strong positive responses to RL-generated diets was higher than that of the human- and GAN-generated diets (P < 0.001). In contrast, in terms of diet composition, the experts' responses to human-designed diets were more positive when experts were provided with food name information (i.e., composition information). CONCLUSIONS: To the best of our knowledge, this is the first study to demonstrate the development and evaluation of AI to support dietary planning for children. This study demonstrates the possibility of developing AI-assisted diet planning methods for children and highlights the importance of composition compliance in diet planning. Further integrative cooperation in the fields of nutrition, engineering, and medicine is needed to improve the suitability of our proposed AI solutions and benefit children's well-being by providing high-quality diet planning in terms of both compositional and nutritional criteria.

Factors Associated with Frequency of Peanut Consumption in Korea: A National Population-Based Study.

Household peanut exposure via skin in infants with impaired skin barrier function is a risk factor for peanut allergy development. The aim of this study is to investigate the peanut consumption of Koreans using national representative data. We used data from the Korean National Health and Nutrition Examination Survey 2012-2016, consisting of data from 17,625 adults who complete the survey. Peanut intake was assessed using a 24-h recall method. Of the study population, 10,552 (59.9%), 6726 (38.2%), and 347 (1.9%) subjects were categorized into non-intake, intermittent intake, and frequent intake group, respectively. Ordered logistic regression models were used to examine the association between sociodemographic and dietary factors and the frequency of peanut intake. After adjusting for confounders, increasing age (adjusted odds ratio (aOR) 1.03; 95% confidence interval (CI) 1.03-1.04), higher education (high school graduates: aOR 1.75, 95 CI 1.39-2.19; higher than college: aOR 2.11, 95% CI 1.65-2.70), and prudent dietary scores in the second (aOR 1.71; 95% CI 1.47-1.99), third (aOR 2.53; 95% CI 2.16-2.97) and the fourth quartiles (aOR 3.72; 95%CI 3.16-4.40) were associated with a high frequency of peanut consumption. This information may be helpful not only in public health research for nutrition but also in personal management for the prevention of peanut allergy in Korea.