A Novel Approach on Deep Learning-Based Decision Support System Applying Multiple Output LSTM-Autoencoder: Focusing on Identifying Variations by PHSMs' Effect over COVID-19 Pandemic.

Following the outbreak of the COVID-19 pandemic, the continued emergence of major variant viruses has caused enormous damage worldwide by generating social and economic ripple effects, and the importance of PHSMs (Public Health and Social Measures) is being highlighted to cope with this severe situation. Accordingly, there has also been an increase in research related to a decision support system based on simulation approaches used as a basis for PHSMs. However, previous studies showed limitations impeding utilization as a decision support system for policy establishment and implementation, such as the failure to reflect changes in the effectiveness of PHSMs and the restriction to short-term forecasts. Therefore, this study proposes an LSTM-Autoencoder-based decision support system for establishing and implementing PHSMs. To overcome the limitations of existing studies, the proposed decision support system used a methodology for predicting the number of daily confirmed cases over multiple periods based on multiple output strategies and a methodology for rapidly identifying varies in policy effects based on anomaly detection. It was confirmed that the proposed decision support system demonstrated excellent performance compared to models used for time series analysis such as statistical models and deep learning models. In addition, we endeavored to increase the usability of the proposed decision support system by suggesting a transfer learning-based methodology that can efficiently reflect variations in policy effects. Finally, the decision support system proposed in this study provides a methodology that provides multi-period forecasts, identifying variations in policy effects, and efficiently reflects the effects of variation policies. It was intended to provide reasonable and realistic information for the establishment and implementation of PHSMs and, through this, to yield information expected to be highly useful, which had not been provided in the decision support systems presented in previous studies.

Impact of warfarin discharge education program on hospital readmission and treatment costs.

Background Although warfarin is highly effective, management of patients prescribed warfarin is complex due to its narrow therapeutic window. Objective To evaluate the impact of a formal warfarin discharge education program (WDEP) on hospital readmission and treatment costs in patients who received warfarin therapy. Setting Robert Wood Johnson University Hospital Somerset in Somerville, New Jersey, USA. Method In this interventional cohort study, patients were assigned to either the WDEP group or the usual care group. The effects of the WDEP on readmission within 90 days after discharge were analyzed using Cox proportional hazards models. Factors influencing treatment cost were identified using generalized linear model with log-link function and gamma distribution. Main outcome measure Hospital readmission within 90 days and treatment costs associated with hospital readmission. Results Among 692 eligible patients, 203 in each group were matched using propensity scores and there were no statistically significant differences in the patient baseline characteristics between two groups. The risk of all-cause readmission within 90 days was significantly lower in the WDEP group compared to the usual care group (relative risk = 0.46, 95% CI 0.28-0.76). The treatment costs associated with hospital readmission in the WDEP group were 19% lower than those in the usual care group after adjusting for the study variables. Conclusion A formal, individualized WDEP provided by pharmacists resulted in significant reduction of readmission and treatment costs. The economic burden of treatment costs associated with warfarin can be controlled if well-organized warfarin education is provided to patients who received warfarin therapy.

Application of toxicity identification evaluation procedure to toxic industrial effluent in South Korea.

Toxicity identification evaluation (TIE) was applied to the effluent from a pharmaceutical industrial complex, following the US EPA TIE guidelines. The whole effluent toxicity (WET) test found toxicity greater than 16toxic units (TU) in the effluent. Dissolved non-polar organic compounds were identified as the major contributor to the observed toxicity in the TIE manipulations in phases I and II. Among the 48 organic compounds identified, three compounds (i.e., acetophenone, benzoimide, and benzothiazole) were related to the pharmaceutical production procedure; however, no contribution to toxicity was predicted in the compounds. The results of the ECOSAR model, which predicts toxicity, indicated that the alkane compounds caused significant toxicity in the effluent. The toxicity test and heavy metal analysis, which used IC and ICP/MS, identified that particulate and heavy metals, such as Cu and Zn, contributed to the remaining toxicity, except dissolved organics. The results showed the applicability of the TIE method for predicting regional effluents produced by the industrial pharmaceutical complex in this study. Although the location was assumed to be affected by discharge of pharmaceutical related compounds in the river, no correlations were observed in the study. Based on the results, advanced treatment processes, such as activated carbon adsorption, are recommended for the wastewater treatment process in this location.

Human health risks associated with dietary exposure to persistent organic pollutants (POPs) in river water in Korea.

Because of their persistence, bioaccumulation tendency, and toxicity, organochlorine pesticides (OCPs) were banned several decades ago. However, they are still detected in natural water and pose a serious risk to human health and the environment. In the present study, seven OCPs were measured in river water collected from 28 sampling sites between 2010 and 2011 in the Yeongsan (YS) and Seomjin (SJ) Rivers, Korea. Gas chromatography/high-resolution mass spectrometry (HRMS) was used for the chemical analysis. The potential health risks of consuming OCPs in fish were assessed in the monitoring region (YS and SJ River basins) by measuring the residual level of OCPs. The human health risks were characterized by considering both the exposure level and the corresponding cancer slope factors; we incorporated both deterministic and probabilistic approaches. The risks were calculated using the probabilistic Maximum Likelihood Estimation (MLE) method. Risk uncertainty and sensitivity were calculated by performing a Monte Carlo analysis. Of the six OCPs, dieldrin, heptachlor epoxide, and hexachlorobenzene exceeded the acceptable risk level in the heavy and light fish consumer groups. The cancer risks associated with these OCPs were 2.99×10(-6), 5.81×10(-6) and 3.72×10(-6), respectively, using the deterministic approach and 1.64×10(-5), 3.36×10(-2) and 5.52×10(-5), respectively, at the 95th percentile using the probabilistic approach. Because there is a high cancer risk associated with these three OCPs, individuals who consume large amounts of freshwater fish may be subject to a high risk of cancer. However, the calculations may have over- or underestimated the risk because of the uncertainty of the environmental concentration and fish intake rate or the use of left-censored monitoring data.

Occurrence of estrogenic chemicals in South Korean surface waters and municipal wastewaters.

Broad scale monitoring of estrogenic compounds was performed at 19 sampling points throughout the Yeongsan and Seomjin river basins and 5 wastewater treatment plants (WWTPs) adjacent to the Gwangju area, Korea, from December 2005 to August 2007. The concentrations of estrogenic compounds, including estrone (E1), 17ß-estradiol (E2), 17α-ethynylestradiol (EE2), bisphenol-A, nonylphenol (NP) and 4-octylphenol (OP), in the samples was measured with gas chromatography/mass spectrometry (GC-MS). In addition, the estrogenic activities throughout the river were investigated using the E-screen assay. Of the six estrogenic chemicals, NP (114.6-336.1 ng L(-1)) and EE2 (0.23-1.90 ng L(-1)) were detected at the highest and lowest levels, respectively in both the river waters and the WWTP effluents. Bisphenol-A showed the largest concentration range, from 7.5 to 335 ng L(-1). The concentrations of E1, E2 and octylphenol ranges were 3.6-69.1, 1.2-10.7, and 2.2-16.9 ng L(-1), respectively. According to the calculated estradiol equivalent concentration (EEQ); however, no estrogenic contribution was observed due to the phenolic compounds in the river waters and effluents. E1 and E2 dominated in both the river water and effluent samples, with contributions to the calculated EEQ of over 79 and 77%, respectively. Conversely, EE2 was rarely detected in the river waters (21%) and effluents (0%). The largest contribution of EE2 to the calculated EEQ was 21% in the river water at S-7. The levels of E1, E2, and EE2 were remarkably decreased in the effluents, indicating that the 5 WWTPs did not contribute to the estrogenic effect of the receiving streams. Overall, the WWTPs did not contributed to the estrogenic activity of the receiving waters, but the livestock industry or wildlife may play an important role in the estrogenic contribution to river water.

Role of food and clay particles in toxicity of copper and diazinon using Daphnia magna.

Toxicity changes in copper and diazinon were investigated in the presence of food, clay, and their mixture by using Daphnia magna. In sorption equilibrium experiments, copper was significantly attracted (>34% sorbed) to food, clay, and food-clay mixture due to their negative zeta potential, while diazinon was less sorbed (<11%). In the exposure test with food and clay particles, it was revealed that copper was remarkably reduced in the presence of clay particles indicating the change in bioavailability of copper by sorption to clay. This was considered as the primary mechanism for toxicity reduction whereas diazinon toxicity was food dependent in the analysis of toxicity using toxicity change index (TCI). It was also shown that certain foods could not only act as a sorbent to copper and diazinon, but also as a material of energy source to alleviate the toxic damage. Meanwhile, clay can be considered as a prominent sorbent to copper but not to diazinon and can inhibit the sorption interaction between foodstuffs and toxicants through the aggregation and sedimentation processes. Furthermore, clay particles, as shown in TCI analysis, may be a potentially risky material as a physiological stressor or a toxicant carrier in contaminated environments.