Predictors of radiation dose for uterine artery embolisation are angiography system-dependent

This study sought to achieve radiation dose reductions for patients receiving uterine artery embolisation (UAE) by evaluating radiation dose measurements for the preceding generation (Allura) and upgraded (Azurion) angiography system. Previous UAE regression models in the literature could not be applied to this centre’s practice due to being based on different angiography systems and radiation dose predictor variables. The aims of this study were to establish whether radiation dose is reduced with the upgraded angiography system and to develop a regression model to determine predictors of radiation dose specific to the upgraded angiography system. A comparison between Group I (Allura, n = 95) and Group II (Azurion, n = 95) demonstrated a significant reduction in KAP (kerma-area product) and Ka, r (reference air kerma) by 63% (143.2 Gy·cm2 vs 52.9 Gy·cm2; P < 0.001, d = 0.8) and 67% (0.6 Gy vs 0.2 Gy; P < 0.001, d = 0.8), respectively. The multivariable linear regression (MLR) model identified the UAE radiation dose predictors for KAP on the upgraded angiography system as total fluoroscopy dose, Ka, r, and total uterus volume. The predictive accuracy of the MLR model was assessed using a Bland-Altman plot. The mean difference was 0.39 Gy·cm2 and the limits of agreement (LoA) were +28.49 and -27.71 Gy·cm2, and thus illustrated no proportional bias. Our findings validated the upgraded angiography system and its advance capabilities to significantly reduce radiation dose for our patients. Interventional radiologist and interventional radiographer familiarisation of the system’s features and the implementation of the newly established MLR model would further facilitate dose optimisation for all centres performing UAE procedures using the upgraded angiography system.

Livelihood Assets and Income Generating Activities: A Comparative Analysis in the Scheduled and Non-Scheduled Areas of Jharkhand

The main objective of the article is to identify different types of livelihood assets, income generating activities (IGAs) and choices of these activities by households across social groups in the Fifth and non-Fifth Scheduled areas of Jharkhand in eastern India. It is based on a primary survey of 785 households randomly selected across caste and Scheduled Tribe groups in Giridih and Latehar districts of Jharkhand. K-means clustering is applied for determination of latent class activity clusters and Multinomial Logistic Regression (MLR) model used for understanding the importance of livelihood assets in determining livelihood activity cluster (LC) for income generation. Further, discriminant analysis is applied to obtain probability of choice of individual households in determining livelihood generating activity. The analysis shows that forest-based activity remains a better livelihood support system in the Fifth Scheduled areas, which is less significant and further diminishing in the non-Fifth Scheduled areas. Rural households engaged in a diverse set of IGAs to obtain additional income to reduce risk and maintain a balanced consumption. Occupational transition is marked by the decline of agriculture and increasing reliance on daily-wage activities as the primary source of income. Other traditional livelihood activities such as animal husbandry and the collection of forest produce have less scope for income in the absence of institutional support.

Azole Compounds as Inhibitors of Candida albicans: QSAR Modelling

Candida albicans is a pathogenic opportunistic yeast found in the human gut flora. It may also live outside of the human body, causing diseases ranging from minor to deadly. Candida albicans begins as a budding yeast that can become hyphae in response to a variety of environmental or biological triggers. The hyphae form is responsible for the development of multidrug resistant biofilms, despite the fact that both forms have been associated to virulence Here, we have proposed a linear and SPA-linear quantitative structure activity relationship (QSAR) modeling and prediction of Candida albicans inhibitors. A data set that consisted of 60 derivatives of benzoxazoles, benzimidazoles, oxazolo (4, 5-b) pyridines have been used. In this study, that after applying the leverage analysis method to detect outliers’ molecules, the total number of these compounds reached 55. SPA-MLR model shows superiority over the multiple linear regressions (MLR) by accounting 90% of the Q2 of anti-fungus derivatives ‘activity. This paper focuses on investigating the role of SPA-MLR in developing model. The accuracy of SPA-MLR model was illustrated using leave-one-out (LOO). The mean effect of descriptors and sensitivity analysis show that RDF090u is the most important parameter affecting the as behavior of the inhibitors of Candida albicans.

Particulate matter (PM10) prediction based on multiple linear regression: a case study in Chiang Rai Province, Thailand

Background The northern regions of Thailand have been facing haze episodes and transboundary air pollution every year in which particulate matter, particularly PM10, accumulates in the air, detrimentally affecting human health. Chiang Rai province is one of the country’s most popular tourist destinations as well as an important economic hub. This study aims to develop and compare the best-fitted model for PM10 prediction for different seasons using meteorological factors. Method The air pollution and weather data acquired from the Pollution Control Department (PCD) spanned from the years 2011 until 2018 at two stations on an hourly basis. Four different stepwise Multiple Linear Regression (MLR) models for predicting the PM10 concentration were then developed, namely annual, summer, rainy, and winter seasons. Results The maximum daily PM10 concentration was observed in the summer season for both stations. The minimum daily concentration was detected in the rainy season. The seasonal variation of PM10 was significantly different for both stations. CO was moderately related to PM10 in the summer season. The PM10 summer model was the best MLR model to predict PM10 during haze episodes. In both stations, it revealed an R2 of 0.73 and 0.61 in stations 65 and 71, respectively. Relative humidity and atmospheric pressure display negative relationships, although temperature is positively correlated with PM10 concentrations in summer and rainy seasons. Whereas pressure plays a positive relationship with PM10 in the winter season. Conclusions In conclusion, the MLR models are effective at estimating PM10 concentrations at the local level for each seasonal. The annual MLR model at both stations indicates a good prediction with an R2 of 0.61 and 0.52 for stations 65 and 73, respectively.

Comparison of PM2.5 in Seoul, Korea Estimated from the Various Ground-Based and Satellite AOD

Based on multiple linear regression (MLR) models, we estimated the PM2.5 at Seoul using a number of aerosol optical depth (AOD) values obtained from ground-based and satellite remote sensing observations. To construct the MLR model, we consider various parameters related to the ambient meteorology and air quality. In general, all AOD values resulted in the high quality of PM2.5 estimation through the MLR method: mostly correlation coefficients >~0.8. Among various polar-orbit satellite AODs, AOD values from the MODIS measurement contribute to better PM2.5 estimation. We also found that the quality of estimated PM2.5 shows some seasonal variation; the estimated PM2.5 values consistently have the highest correlation with in situ PM2.5 in autumn, but are not well established in winter, probably due to the difficulty of AOD retrieval in the winter condition. MLR modeling using spectral AOD values from the ground-based measurements revealed that the accuracy of PM2.5 estimation does not depend on the selected wavelength. Although all AOD values used in this study resulted in a reasonable accuracy range of PM2.5 estimation, our analyses of the difference in estimated PM2.5 reveal the importance of utilizing the proper AOD for the best quality of PM2.5 estimation.

307. Predictors of Respiratory Bacterial Co-Infection in Hospitalized COVID-19 Patients

Background COVID-19 pneumonia can be indistinguishable from other infectious respiratory etiologies, so providers are challenged with deciding whether empiric antibiotics should be prescribed to hospitalized patients with SARS-CoV-2. This study aimed to evaluate predictors of respiratory bacterial co-infections (RBCI) in hospitalized patients with COVID-19. Methods Retrospective study evaluating COVID-19 inpatients from Feb 1, 2020 to Sept 30, 2020 at a tertiary academic medical center. Patients with RBCI were matched with three COVID-19 inpatients lacking RBCI admitted within 7 days of each other. The primary objectives of this study were to determine the prevalence of and identify variables associated with RBCI in COVID-19 inpatients. Secondary outcomes included length of stay and mortality. Data collected included demographics; inflammatory markers; bacterial culture/antigen results; antibiotic exposure; and COVID-19 severity. Wilcoxon rank sum, Chi Square tests, or Fisher’s exact tests were utilized as appropriate. A multivariable logistic regression (MLR) model was conducted to identify covariates associated with RBCI. Results Seven hundred thirty-five patients were hospitalized with COVID-19 during the study period. Of these, 82 (11.2%) had RBCI. Fifty-seven of these patients met inclusion criteria and were matched to three patients lacking RBCI (N = 228 patients). Patients with RBCI were more likely to receive antibiotics [57 (100%) vs. 130 (76%), p &lt; 0.0001] and for a longer cumulative duration [19 (13-33) vs. 8 (4-13) days, p &lt; 0.0001] compared to patients lacking RBCI. The MLR model revealed risk factors of RBCI to be admission from SNF/LTAC/NH (AOR 6.8, 95% CI 2.6-18.2), severe COVID-19 (AOR 3.03, 95% CI 0.78-11.9), and leukocytosis (AOR 3.03, 95% CI 0.99-1.16). Conclusion Although RBCI is rare in COVID-19 inpatients, antibiotic use is common. COVID-19 inpatients may be more likely to have RBCI if they are admitted from a SNF/LTAC/NH, have severe COVID-19, or present with leukocytosis. Early and prompt recognition of RBCI predictors in COVID-19 inpatients may facilitate timely antimicrobial therapy while improving antimicrobial stewardship among patients at low risk for co-infection. Disclosures All Authors: No reported disclosures

Assessment and Calibration of a Low-Cost PM2.5 Sensor Using Machine Learning (HybridLSTM Neural Network): Feasibility Study to Build an Air Quality Monitoring System

Commercially available low-cost air quality sensors have low accuracy. The improved accuracy of low-cost PM2.5 sensors allows the use of low-cost sensor systems to reasonably investigate PM2.5 emissions from industrial activities or to accurately estimate individual exposure to PM2.5. In this work, we developed a new PM2.5 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 PM2.5 concentrations, temperature and humidity by low-cost sensors and gravimetric-based PM2.5 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 PM2.5 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.

Estimation of Health-Related Physical Fitness (HRPF) Levels of the General Public Using Artificial Neural Network with the National Fitness Award (NFA) Datasets

Estimation of health-related physical fitness (HRPF) levels of individuals is indispensable for providing personalized training programs in smart fitness services. In this study, we propose an artificial neural network (ANN)-based estimation model to predict HRPF levels of the general public using simple affordable physical information. The model is designed to use seven inputs of personal physical information, including age, gender, height, weight, percent body fat, waist circumference, and body mass index (BMI), to estimate levels of muscle strength, flexibility, maximum rate of oxygen consumption (VO2max), and muscular endurance. HRPF data (197,719 sets) gathered from the National Fitness Award dataset are used for training (70%) and validation (30%) of the model. In-depth analysis of the model’s estimation accuracy is conducted to derive optimal estimation accuracy. This included input/output correlation, hidden layer structures, data standardization, and outlier removals. The performance of the model is evaluated by comparing the estimation accuracy with that of a multiple linear regression (MLR) model. The results demonstrate that the proposed model achieved up to 10.06% and 30.53% improvement in terms of R2 and SEE, respectively, compared to the MLR model and provides reliable estimation of HRPF levels acceptable to smart fitness applications.