Generalized Additive Model Model Research Articles

The interaction between water quality and meteorological factors on chlorophyll-a concentration in Honghu Lake: based on PiecewiseSEM-generalized additive model coupling model.

In order to explore the interactive effects of environmental factors on the chlorophyll-a (Chl-a) concentration variation in Honghu Lake, this study was based on the monitoring data of Chl-a mass concentration and water quality factors (water temperature, pH, dissolved oxygen, permanganate index, total nitrogen, total phosphorus) and meteorological factors (evaporation, precipitation, sunshine hours, average wind speed) at three research sites (Dakou, Chatan Island, Lantian) in Honghu Lake from January 2010 to December 2019. Time series analysis, piecewise structural equation model (PiecewiseSEM), and generalized additive model (GAM) were used to quantitatively study the spatial and temporal changes of different environmental factors and their interaction with chlorophyll-a concentration in Honghu Lake. The results showed that the effects of TN and DO on Chl-a at Dakou and Chatan Island were more significant than other environmental meteorological factors, while the effects of DO and CODMn on Chl-a at Lantian were more obvious. At the same time, it was found that Chl-a had a non-linear relationship with TN and DO at Dakou and Chatan Island, a non-linear relationship with DO at Lantian, and a linear relationship with CODMn. The interaction effect of dominant environmental meteorological factors on Chl-a was significantly higher than that of a single factor, and the explanation rates were 80.6%, 72.8%, and 64.6%, respectively. In conclusion, based on the Piecewise SEM and GAM model, it not only can reveal the influence of the interaction of influencing factors on the change of Chl-a concentration, but also has important significance for the early warning and control of lake eutrophication.

Phenol identification and mapping of rangeland species at laboratory and landscape scales using PRISMA hyperspectral data

ABSTRACT Secondary metabolites have high ecological and economic values. Measuring the amounts of these metabolites in plants through laboratory analysis is time-consuming and expensive. On the other hand, the laboratory results cannot be generalized to a wide area of rangelands with diverse climates, topography, and soil. Therefore, the present study aims to evaluate the potential of PRISMA hyperspectral data to estimate the rangeland phenol concentration at landscape scale in western Isfahan province, Iran. Phenol concentration and spectral signatures were extracted from 42 plant individuals, including Astragalus adscendens, Astragalus verus, Daphne mucronata, Anabasis aphylla, and Phlomis olivieri using laboratory methods and spectroscopy in the range of 350 to 2500 nm. Phenol-sensitive bands were identified by establishing a relationship between phenol concentration and all spectral bands by the Partial Least Square Regression (PLSR) method. The map of phenol spatial changes was then produced with the Bayesian Regularized Artificial Neural Network Model (BRNN), Random Forest (RF), Generalized Linear Model (GAM), Generalized Additive Model (GLM), and Gaussian Process Regression (GPR) in rangelands. The results showed that the phenol concentration in different individuals was between 3.65 and 20.13 (mgGAE/gDW), and species spectral absorptions ranged from 1.650 to 1.660. The very high coefficient of determination of phenol concentration with spectral data (R2 = 0.94) confirmed the use of these data in phenol mapping at the landscape scale. The maximum estimated phenol concentration by GLM, GAM, RF, BRNN, and GPR models was 36.40, 26.76, 18.07, 22.74, and 32.92 GAE/g DW, respectively; which RF model had the highest (R2 = 0.955) and GLM had the lowest accuracy (R2 = 0.816). The findings show that hyperspectral data can estimate secondary metabolites at the landscape scale and can supplement laboratory methods in managing rangeland plants.

Subject-level spinal osteoporotic fracture prediction combining deep learning vertebral outputs and limited demographic data.

Osteoporotic vertebral fractures are common and morbid. Automated opportunistic screening for incidental vertebral fractures from radiographs, the highest volume imaging modality, could improve osteoporosis detection and management. We consider how to form patient-level fracture predictions and summarization to guide management, using our previously developed vertebral fracture classifier on segmented radiographs from a prospective cohort study of US men (MrOS). We compare the performance of logistic regression (LR) and generalized additive models (GAM) with combinations of individual vertebral scores and basic demographic covariates. Subject-level LR and GAM models were created retrospectively using all fracture predictions or summary variables such as order statistics, adjacent vertebral interactions, and demographic covariates (age, race/ethnicity). The classifier outputs for 8663 vertebrae from 1176 thoracic and lumbar radiographs in 669 subjects were divided by subject to perform stratified fivefold cross-validation. Models were assessed using multiple metrics, including receiver operating characteristic (ROC) and precision-recall (PR) curves. The best model (AUC-ROC = 0.968) was a GAM using the top three maximum vertebral fracture scores and age. Using top-ranked scores only, rather than all vertebral scores, improved performance for both model classes. Adding age, but not ethnicity, to the GAMs improved performance slightly. Maximal vertebral fracture scores resulted in the highest-performing models. While combining multiple vertebral body predictions risks decreasing specificity, our results demonstrate that subject-level models maintain good predictive performance. Thresholding strategies can be used to control sensitivity and specificity as clinically appropriate.

Enhancing the health benefits of air quality improvement: a comparative study across diverse scenarios.

In many studies, linear methods were used to calculate health benefits of air quality improvement, but the relationship between air pollutants and diseases may be complex and nonlinear. In addition, previous studies using reference number as average number of diseases may overestimate the health benefits. Therefore, the nonlinear model estimation and resetting of the reference number were very important. Hospital admission data for coronary heart disease (CHD), meteorological data, and air pollutant data of Zibo City from 2015 to 2019 were collected. The generalized additive model (GAM) was used to explore the association between air pollutants and hospital admission for CHD, and to evaluate the effects on health benefits under different reference number settings. A total of 21,105 hospitalized cases for CHD were reported in Zibo during the study period. The results of the GAM showed there was a log-linear exposure-response relationship between O3 and hospital admissions for CHD, with RR (relative risk) of 1.0143 (95% CI: 1.0047 ~ 1.0239). There were log-nonlinear exposure-response relationships between PM10, PM2.5, SO2, and hospital admissions for CHD. With the increase of pollutants concentrations, the risk for hospital admission showed a trend of increasing first and then decreasing. Compared with the average hospital admissions as the reference number, health benefits calculated by hospital admissions predicted by the GAM model yielded lower. Using the World Health Organization air quality guidelines as reference, attributable fractions of O3, PM10, and PM2.5 were 1.97% (95% CI: 0.63 ~ 3.40%), 11.82% (95% CI: 8.60 ~ 15.24%), and 11.82% (95% CI: 8.79 ~ 15.04%), respectively. When quantifying health benefits brought by improving air quality, corresponding calculation methods should first be determined according to the exposure-response relationships between air pollutants and outcomes. Then, applying the average hospital admissions as reference number may overestimate health benefits resulting from improved air quality.

Machine learning models application for spatiotemporal patterns of particulate matter prediction and forecasting over Morocco in north of Africa

Atmospheric air pollution exposure raises morbidity and mortality rates and is a major cause of the world's illness burden. In this context, we explored spatial and temporal trends in particulate matter PM10 from 2003 to 2020 over Morocco to assess air pollution exposure. We use the capabilities of ML models to study PM10 trends using 26 predictor variables, including meteorological parameters, volatile organic compounds, atmospheric oxidants, and aerosol optical depth data from the Copernicus Atmosphere Monitoring Service (CAMS). For this purpose, three ML models were built: Multiple Linear Regression (MLR), Random Forest Regression (RFR), and Generalized Additive Model (GAM). To match and optimize these models, a set of ML algorithms has been coupled with each model. The results show all these models are highly accurate in predicting and forecasting PM10 total column trends. Cross-validation showed that GAM had better prediction ability for the PM10 total column with R2 = 0.994 and a very low root mean squared error (RMSE) not exceeding 0.046 × 10−16 kg/m2. The GAM model showed much higher predictive ability and lower bias than the other models. This finding can be explained by the advantages of GAMs, including their ability to capture complex and non-linear patterns in the data, making them particularly useful when relationships are not easily represented by linear models. This study has presented a comprehensive methodology for predicting the spatiotemporal variability of PM10. The proposed methodology holds potential applicability across all regions, facilitating the generation of high-resolution PM10 monitoring and the establishment of systems for the early detection of air pollution incidents in Morocco. Furthermore, the developed models exhibit versatility, enabling their application for estimating future trends of individual pollutants or making real-time predictions of air quality levels. This research contributes to advancing the understanding and proactive management of air quality in the context of Morocco, offering valuable insights for pollution control efforts.

Environmental drivers behind the exceptional increase in cyanobacterial blooms in Okavango Delta, Botswana

The Okavango Delta region in Botswana experienced exceptionally intense landscape-wide cyanobacterial harmful algal blooms (CyanoHABs) in 2020. In this study, the drivers behind CyanoHABs were determined from thirteen independent environmental variables, including vegetation indices, climate and meteorological parameters, and landscape variables. Annual Land Use Land Cover (LULC) maps were created from 2017 to 2020, with ∼89% accuracy to compute landscape variables such as LULC change. Generalized Additive Models (GAM) and Structural Equation Models (SEM) were used to determine the most important drivers behind the CyanoHABs. Normalized Difference Chlorophyll Index (NDCI) and Green Line Height (GLH) algorithms served as proxies for chlorophyll-a (green algae) and phycocyanin (cyanobacteria) concentrations. GAM models showed that seven out of the thirteen variables explained 89.9% of the variance for GLH. The models showcased that climate variables, including monthly precipitation (8.8%) and Palmer Severity Drought Index- PDSI (3.2%), along with landscape variables such as changes in Wetlands area (7.5%), and Normalized Difference Vegetation Index (NDVI) (5.4%) were the determining drivers behind the increased cyanobacterial activity within the Delta. Both PDSI and NDVI showed negative correlations with GLH, indicating that increased drought conditions could have led to large increases in toxic CyanoHAB activity within the region. This study provides new information about environmental drivers which can help monitor and predict regions at risk of future severe CyanoHABs outbreaks in the Okavango Delta, Botswana, and other similar data-scarce and ecologically sensitive areas in Africa.Plain Language Summary: The waters of the Okavango Delta in Northern Botswana experienced an exceptional increase in toxic cyanobacterial activity in recent years. Cyanobacterial blooms have been shown to affect local communities and wildlife in the past. To determine the drivers behind this increased bloom activity, we analyzed the effects of thirteen independent environmental variables using two different statistical models. Within this research, we focused on vegetation indices, meteorological, and landscape variables, as previous studies have shown their effect on cyanobacterial activity in other parts of the world. While driver determination for cyanobacteria has been done before, the environmental conditions most important for cyanobacterial growth can be specific to the geographic setting of a study site. The statistical analysis indicated that the increases in cyanobacterial bloom activity within the region were mainly driven by persistent drier conditions. To our knowledge, this is the first study to determine the driving factors behind cyanobacterial activity in this region of the world. Our findings will help to predict and monitor areas at risk of future severe cyanobacterial blooms in the Okavango Delta and other similar African ecosystems.

Interpretable diurnal impacts on extreme urban PM2.5 concentrations of soil temperature, soil water content, humidity and temperature inversion

Inhabitants of megacities around the world are suffering from severely unhealthy concentrations of PM2.5 as a result of intense emissions from numerous sectors, often combined with adverse meteorological conditions. Machine learning algorithms can be applied to multiyear datasets of hourly measurements in order to identify the main drivers causing intense pollution. In particular, Generalized Additive Models (GAM) provide interpretable associations of the interplay between emissions and meteorology. GAM simulations were developed for five dry seasons in Kolkata and Dhaka. In the model, soil temperature was associated with 21% of PM2.5 variability. Instead of 2-m humidity, model performance was improved by including air humidity at 1000 hPa and soil water content individually, with each accounting for around 6% of PM2.5 variability. Boundary layer heights have a significant impact on daytime concentrations, but the GAM output showed that temperature inversion intensity better characterized the stability of the nocturnal boundary layer and had a larger contribution to the PM2.5 variability. The GAM model could also identify interactions between parameters and showed that boundary layer height, temperature inversion intensity and air humidity had impacts that varied by time of day. By using GAM factors for winds at 100 m above the surface in combination with the Trajectory Cluster Contribution Function, the model estimated that local winds were associated with around 6% of variability whereas long range transport was associated with around 9% of variability. The analysis shows that there are no silver bullets for improving air quality and that adverse meteorology is making the problem harder to solve. Nevertheless, the results show that sustained efforts at controlling both local and regional sources will yield cleaner air that is greatly needed to improve the health of people living in large metropolitan areas.

Cardiovascular mortality in patients with atrial fibrillation and physical activity intensity: delineating the threshold of vigorous activity

Abstract Background/Introduction There is a correlation between light-to-moderate physical activity and reduced atrial fibrillation (AF) incidence and cardiovascular risk. Vigorous activities reduced the benefits and increased the risk of AF. The exact threshold at which physical activity increases the risk of cardiovascular death (CVD) in patients with AF remains to be determined. Purpose To determine the threshold of vigorous activity in patients with AF. Methods In this study, data from 23856 individuals from the Taiwan Biobank (2017) were analyzed. Physical activity levels were quantified in metabolic equivalent task (MET) hours/week and categorized into four groups based on 20 MET-hour increments. The study employed Kaplan-Meier survival analysis and an adjusted generalized additive model (GAM) to assess the impact of physical activity on CVD risk (adjusting for age, sex, diabetes, hypertension, chronic obstructive pulmonary disease, and chronic kidney disease), with follow-up data from 2017 to 2022. Results Over a median 5.51-year follow-up, 238 AF cases (cumulative rate of AF: 0.998%) were identified (48.7% female, mean age 61.7 years). The linear model indicated a lower CVD risk in participants engaging in moderate physical activity (20-40 MET-hours/week; adjusted hazard ratio [HR]: 0.38, 95% CI: 0.16-0.95) compared to the reference group (0-20 MET-hours/week). Notably, the GAM model demonstrated a significant increase in CVD risk for activities exceeding 40 MET-hours/week after multivariable adjustment. Conclusions Physical activity levels and CVD risk in AF patients are correlated in a J-shaped manner. The CVD risk of AF decreased with mild to moderate physical activity. For AF patients, it establishes a critical threshold of 40 MET-hours/week beyond which there is an increased risk of CVD, thus clarifying safe physical activity limits.Figure 1:KM sruvival curveFigure 2:Smooth model of GAM

Time to Operation and Mortality Risk in Elderly Patients with Intestinal Fistula: Not Too Early and Not Too Late.

This study aimed to ascertain the risk factors contributing to in-patient mortality in elderly patients 65 years and older who were admitted emergently, diagnosed with intestinal fistula, and underwent surgery. Data were extracted from the National Inpatient Sample (NIS) spanning the years 2005-2014. Multivariable logistic regression and a generalized additive model (GAM) were employed to investigate predictors of mortality. Continuous variables are presented as mean values with standard deviations (SD). The study encompassed 34,853 patients with a mean age of 77.7 years-56.5% were female and 79.4% were White. Patients were categorized into three groups based on the time elapsed between admission and surgery: less than two days (17,761), two to three days (8,407), and more than three days (4,233). Mortality rates were 2.7%, 6%, and 6.1% for patients who underwent surgery within two to three days, within two days, and after more than three days of admission, respectively. Notably, the group that operated more than three days from admission experienced nearly double the hospital length of stay (12 days, SD: 7.2) compared to the other two groups (6.3, SD: 6 and 6.1, SD: 4.8). Furthermore, the association between mortality and time to operation, as indicated by the GAM model, revealed a significant non-linear relationship after adjusting for age, gender, race, zip code, hospital location, and comorbidities (p<0.001). Elderly patients diagnosed with intestinal fistula should undergo operative treatment as soon as possible, once they are resuscitated. Delaying the operation more than three days after admission substantially increases the risk of mortality.

Predicting influenza-like illness trends based on sentinel surveillance data in China from 2011 to 2019: A modelling and comparative study1

BackgroundInfluenza is an acute respiratory infectious disease with a significant global disease burden. Additionally, the coronavirus disease 2019 pandemic and its related non-pharmaceutical interventions (NPIs) have introduced uncertainty to the spread of influenza. However, comparative studies on the performance of innovative models and approaches used for influenza prediction are limited. Therefore, this study aimed to predict the trend of influenza-like illness (ILI) in settings with diverse climate characteristics in China based on sentinel surveillance data using three approaches and evaluate and compare their predictive performance. MethodsThe generalized additive model (GAM), deep learning hybrid model based on Gate Recurrent Unit (GRU), and autoregressive moving average-generalized autoregressive conditional heteroscedasticity (ARMA—GARCH) model were established to predict the trends of ILI 1-, 2-, 3-, and 4-week-ahead in Beijing, Tianjin, Shanxi, Hubei, Chongqing, Guangdong, Hainan, and the Hong Kong Special Administrative Region in China, based on sentinel surveillance data from 2011 to 2019. Three relevant metrics, namely, Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R squared, were calculated to evaluate and compare the goodness of fit and robustness of the three models. ResultsConsidering the MAPE, RMSE, and R squared values, the ARMA—GARCH model performed best, while the GRU-based deep learning hybrid model exhibited moderate performance and GAM made predictions with the least accuracy in the eight settings in China. Additionally, the models’ predictive performance declined as the weeks ahead increased. Furthermore, blocked cross-validation indicated that all models were robust to changes in data and had low risks of overfitting. ConclusionsOur study suggested that the ARMA—GARCH model exhibited the best accuracy in predicting ILI trends in China compared to the GAM and GRU-based deep learning hybrid model. Therefore, in the future, the ARMA—GARCH model may be used to predict ILI trends in public health practice across diverse climatic zones, thereby contributing to influenza control and prevention efforts.

Robust Analysis of the Influencing Factors for Hospitalization Costs of Senile Cataracts Patients in Chengdu Considering Different Types of Insurance

Chengdu is one of the earliest pilot cities for urban-rural basic medical insurance integration in China. This study aimed to analyze the influencing factors of hospitalization costs of senile cataract in a tertiary hospital in Chengdu by robust method, especially considering the influence of medical insurance type. A total of 1310 discharged patients from a tertiary hospital from January 2020 to June 2021 who were mainly diagnosed with senile cataracts were selected as the research subjects. Kruskal-Wallis H test and Spearman correlation analysis are used to conduct univariate statistical analysis. The robust multivariate linear regression model and a semi-parametric multivariate regression model are established to obtain the influencing factors for their hospitalization costs. The robust multivariate regression model results show that reimbursement ratio, number of surgeries, type of medical insurance, hospitalization days, number of additional diagnoses and material proportion have significant correlations with the response variable, i.e. total hospitalization costs of the senile cataract patients. In the robust multivariate regression analysis, the type of insurance is significantly associated with the hospitalization costs. Fixing other variables, the hospitalization costs of patients with UEBMI insurance were 7.6% higher than those with URRBMI insurance. Generalized additive model (GAM) can express the nonlinear relationship between explanatory variables and response variable. Because of the nonlinear part of the GAM, the interpretation and description of the model can provide more knowledge than the linear models. In the GAM model, the type of insurance is also significantly related to the total costs. According to the regression effects of reimbursement ratio, number of surgeries, type of medical insurance, hospitalization days, number of additional diagnoses and material proportion on total costs, the paper aims to provide some references for promoting the reform of the local medical system and improving the eye health status and quality of life of middle-aged and elderly groups.

Meteorological Conditions and PM2.5 Impact on COVID-19 Case Fatality Ratios (CFR) in Bangkok Metropolitan Region

The emergence of a novel coronavirus strain triggered a global health crisis, impacting both health and economies worldwide, including Thailand since 2019. While prior research hinted at connections between environmental factors and rising COVID-19 cases, these links remained inconclusive. This study investigated indoor and outdoor (I/O) ratios and explored potential correlations between fine particulate matter (PM2.5), meteorological conditions, and the case fatality rate (CFR%) of COVID-19 in Bangkok and its metropolitan area from January to December 2021. In Spearman’s Rank correlation analysis, the results found that CFR% exhibited a positive correlation with relative humidity (RH) (r=0.187) and a negative correlation with PM2.5 (r=-0.190) and wind speed (WS) (r=-0.039). The generalized additive model (GAM) indicated that RH, PM2.5, temperature, and WS adversely affect the CFR% of COVID-19. Consistent relationships between PM2.5, RH, and WS were observed in both Spearman’s Rank correlation and the GAM model. This study underscored the complexity of understanding pandemic dynamics across seasons, I/O ratios, and the influence of lag days. By presenting the results, they may serve as a valuable reference for planning interventions during future pandemics.

Enhancing Risk Management Strategies: GAM Analysis of Health Insurance Claim Determinants

Health insurance plays a crucial role in providing financial protection and ensuring access to necessary healthcare services. The awareness of Indonesian society regarding the importance of health insurance continues to grow, as evidenced by a 22% increase in premium income according to AAJI data as of March 2023. Despite the benefits of health insurance, an increasing number of insurance participants raises risks for insurance companies. The Generalized Additive Models (GAM) P-Spline can overcome these problems. The non-linear relationship between claim amount with age, body mass index, and blood pressure can be modelled with GAM P-Spline. The formed GAM model with PIRLS unable to give a clear information of relationship between variables explicitly, but can be seen by the shape of the function of each predictor associated with the link function used.

Spatial Distribution and Relationship between Slope Micro-Topography Changes and Soil Aggregate Stability under Rainfall Conditions

Natural rainfall affects the stability of soil aggregates by the kinetic energy of the rain changing the morphological characteristics of slope micro-topographic factors. Although the relationship between the stability of soil aggregates and micro-topography is not very significant at the slope scale, there are also rules to be found. This study aims to explore the relationship between slope micro-topography and aggregate stability, and to observe the spatial distribution of aggregate stability after water erosion. In this study, a digital elevation model of slope micro-topography was established by using a three-dimensional laser scanner to observe the slope erosion changes after rainfall events and clarify the spatial changes of soil aggregate stability and its relationship with slope micro-topography by combining geostatistics and generalized additive model (GAM). The results showed that the area of serious water erosion in the lower part of the slope accounted for 38.67% of the slope, and the micro-topography index of the slope changed obviously after rainfall, with the slope increasing by 3.1%, the surface roughness increasing by 5.34%, the surface cutting degree increasing by 26.67%, and the plane curvature decreasing by 61.7%. In addition, the GAM model was used to fit the multivariate variables. The results revealed that the slope and surface roughness were the key factors affecting the stability of water-stable aggregate. The slope and surface roughness were negatively correlated with the stability of water-stable aggregates.

Predicting the Fishery Ground of Jumbo Flying Squid (Dosidicus gigas) off Peru by Extracting Features of the Ocean Environment

We introduce a novel method that combines satellite data, advanced clustering techniques, machine learning feature extraction, and statistical models to enhance fishery forecasting accuracy. Focusing on jumbo flying squid in the southeast Pacific Ocean near Peru, we utilize MODIS-Aqua and MODIS-Terra satellite data on sea surface temperature (SST) to construct a deep convolutional embedded clustering (DCEC) model and extract the monthly SST features (FM) based on an optimized number of clusters determined by the Davies–Bouldi index (DBI). We use the extracted FM to construct a series of Generalized Additive Models (GAM) to forecast the catch per unit effort (CPUE) of jumbo flying squid within a spatial resolution of 0.5° × 0.5°. Our results demonstrate the following findings: (1) The SST feature clusters obtained through the DCEC model could capture the SST monthly variations; (2) The GAM models with FM outperform the models with the traditional monthly average SST in terms of predictive accuracy; (3) Using both FM and average SST together can further improve model performance. This study demonstrates the effectiveness of the DCEC combined with DBI in extracting marine environmental features and highlights the ocean environment feature extraction method to enhance the precision and reliability of fishery forecasting models.

Enhancing Chub Mackerel Catch Per Unit Effort (CPUE) Standardization through High-Resolution Analysis of Korean Large Purse Seine Catch and Effort Using AIS Data

Accurate determination of fishing effort from Automatic Identification System (AIS) data improves catch per unit effort (CPUE) estimation and precise spatial management. By combining AIS data with catch information, a weighted distribution method is applied to allocate catches across various fishing trajectories, accounting for temporal dynamics. A Generalized Linear Model (GLM) and Generalized Additive Model (GAM) were used to examine the influence of spatial–temporal and environmental variables (year, month, Sea Surface Temperature (SST), Sea Surface Salinity (SSS), current velocity, depth, longitude, and latitude) and assess the quality of model fit for these effects on chub mackerel CPUE. Month, SST, and year exhibited the strongest relationship with CPUE in the GLM model, while the GAM model emphasizes the importance of month and year. CPUE peaked within specific temperature and salinity ranges and increased with longitude and specific latitudinal bands. Month emerged as the most influential variable, explaining 38% of the CPUE variance, emphasizing the impact of regulatory measures on fishery performance. The GAM model performed better, explaining 69.9% of the nominal CPUE variance. The time series of nominal and standardized indices indicated strong seasonal cycles, and the application of fine-scale fishing effort improved nominal and standardized CPUE estimates and model performance.

Passive UHF RFID-based real-time intravenous fluid level sensor.

Ultra high frequency (UHF) passive radio frequency identification (RFID) tag-based sensors are proposed for intravenous (IV) fluid level monitoring in medical Internet of Things (IoT) applications. Two versions of the sensor are proposed: a binary sensor (i.e., full vs. empty state sensing) and a real-time (i.e., continuous level) sensor. The operating principle is demonstrated using full-wave electromagnetic simulation at 910 MHz and validated with experimental results. Generalized Additive Model (GAM) and random forest algorithms are employed for each interrogation dataset. Real-time sensing is accomplished with small deviations across the models. A minimum of 72% and a maximum of 97% of cases are within a 20% error for the GAM model and 62% to 98% for the random forest model. The proposed sensor is battery-free, lightweight, low-cost, and highly reliable. The read range of the proposed sensor is 4.6 m.

Comparison of model selection and data bias on the prediction performance of purpleback flying squid (Sthenoteuthis oualaniensis) fishing ground in the Northwest Indian Ocean

Purpleback flying squid (Sthenoteuthis oualaniensis, PFS) is one of the critical economically cephalopod species in the northwest Indian Ocean, and the accurate model and dataset selection are critical parameters for predicting and managing the PFS fishing grounds. In this study, the PFS fishery data for the years 2016–2021 was analyzed using the gravity center of fishing grounds method, generalized additive model (GAM), gradient boosted trees (GBT), 3D Convolutional Neural Network (3DCNN), and 3D Convolutional Neural Networks-Convolutional LSTM Network (3DCNN-ConvLSTM) to explore the differences in annual catches, the annual gravity center of fishing ground, model performance, and importance of environmental variables in the case of datasets A (no moonlight days) and B (no moonlight days + bright moonlight days). The results are as follows: 1) Datasets A and B exhibit similar patterns of variation, with annual catches rising and then declining and the annual gravity center of fishing ground moving northeastward overall; 2) The GAM and GBT models had better model performance on dataset B (GAM (average F1-score ± standard deviation): 0.678658 ± 0.014684; GBT: 0.737422 ± 0.011748)than on dataset A (GAM: 0.676802 ± 0.013403; GBT: 0.736547 ± 0.013323), but almost negligible, and the standard deviation of the GAM model on dataset B becomes larger. 3DCNN and 3DCNN-ConvLSTM models perform in contrast, with significantly better F1-score and standard deviations on dataset A (3DCNN: 0.75048 ± 0.019763; 3DCNN-ConvLSTM: 0.740041 ± 0.023927) than on dataset B (3DCNN: 0.746378 ± 0.020337; 3DCNN-ConvLSTM: 0.736927 ± 0.04498); 3) The 3DCNN (optimal prediction of performance) or GBT (Optimal model stability) model is optimal for predicting the PFS fishing grounds; 4) GBT, 3DCNN, and 3DCNN-ConvLSTM model results all showed that the differences in the importance of environmental variables obtained from datasets A and B were significant; 5) Unlike the GBT model, the 3DCNN and 3DCNN-ConvLSTM models were more susceptible to dataset influences, with significant dependence on environmental variables that have large positive and negative sample differences. This study provides rich suggestions for constructing a predictive model for the PFS fishing grounds in the context of climate change. It also provides a new perspective on cleaning up biased data for light fisheries.

Non-Linear Association of Serum Sex Hormone Binding Globulin Concentration with Female Infertility.

Accumulating proofs suggested that disturbance of serum sex hormone-binding globulin (SHBG) concentration can affect the reproductive system. However, the effect of serum SHBG on female infertility remains to be clarified. Data from 1,787 adults from the National Health and Nutrition Examination Survey (NHANES) was applied to examine the correlation between serum SHBG and female infertility. Multivariate logistic regression was used to evaluate the independent association between serum SHBG and female infertility. Furthermore, generalized additive model (GAM) and two-piecewise linear regression model were applied to assess the underlying non-linear association in our participants. We observed a reverse association between serum SHBG and infertility based on a fully-adjusted model (OR = 0.99, 95% CI: 0.99-1, p = 0.002), and the results were stable in several sensitive analyses. Furthermore, we detected a non-linear link by GAM and two-piecewise linear regression model. A protective association was observed at < 58.84 nmol/L serum SHGB; in contrast, no statistical link was found at > 58.84 nmol/L serum SHGB. Our results provide evidence for a non-linear association with serum SHBG and female infertility. This finding needs to be further confirmed in future large-scale prospective cohort studies.

Consumption of foods contaminated with heavy metals and their association with cardiovascular disease (CVD) using GAM software (cohort study)

IntroductionHeavy metals can enter the environment and food through industrial activities, acid rain, chemical fertilizers, pesticides, and sewage. A large amount of these metals is dangerous because they tend to bio accumulate. A concern with these metals is the long-term, low-dose exposure seen in the general population. HMs can cause disorders in the cardiovascular system through various mechanisms such as the production of free radicals, DNA damage, lipid peroxidation, and oxidative stress. Material and methodFood items measured in the present study included rice, bread, and vegetables. 210 participants (105 controls and 105 patients) were randomly selected for this study. The demographic information of the subjects was obtained from the Hoveyzeh Cohort Center. The relationship between heavy metals in food and cardiovascular diseases is investigated by The Generalized Additive Model (GAM). ResultThe results of the present study showed that when urine Cd was smoothed based on rice Cd, there was a significant correlation between urine Cd and Cd consumed in vegetables and rice. The GAM coefficient for urinary Cd excreted in case-control groups and Cd consumed in vegetables were 479.79(SE: 6.49–73.87) and 818.56(SE: 11.96–68.43), respectively, and for rice consumed, it was 0.03(SE: 0.015–2.103) and 0.04(SE: 0.017–2.338), respectively. The GAM coefficient for As consumption in vegetables and As in urine of case and control groups was 1.61 (SE: 9.48–0.16) and 22.36 (SE: 13.60–1.64), respectively. The same coefficient for rice consumption in case and control groups was 4.5 (SE: 0.62–7.22) and 10.48 (SE: 1.46–7.16), respectively. There was a very strong and significant correlation between the Sr in the urine of both groups and the Sr in the food consumed, so that the urinary Sr in the control group is excreted more than in the cardiovascular group. ConclusionGAM analysis indicates that As in vegetable and rice is more than the standard limitation value. Also, Sr and Cd in vegetables, rice, and bread were more than the standard limitation value. According to the GAM model As had a significant value in rice and vegetables indicating that As is more than the standard limitation value, therefore, it is associated with CVD.