Root Mean Square Error Of Prediction Research Articles

Detection of Al, Mg, Ca, and Zn in copper slag by LIBS combined with calibration curve and PLSR methods

The precise measurement of Al, Mg, Ca, and Zn composition in copper slag is crucial for effective process control of copper pyrometallurgy. In this study, a remote laser-induced breakdown spectroscopy (LIBS) system was utilized for the spectral analysis of copper slag samples at a distance of 2.5 m. The composition of copper slag was then analyzed using both the calibration curve (CC) method and the partial least squares regression (PLSR) analysis method based on the characteristic spectral intensity ratio. The performance of the two analysis methods was gauged through the determination coefficient (R 2), average relative error (ARE), root mean square error of calibration (RMSEC), and root mean square error of prediction (RMSEP). The results demonstrate that the PLSR method significantly improved both R 2 for the calibration and test sets while reducing ARE, RMSEC, and RMSEP by 50% compared to the CC method. The results suggest that the combination of LIBS and PLSR is a viable approach for effectively detecting the elemental concentration in copper slag and holds potential for online detection of the elemental composition of high-temperature molten copper slag.

Comparison of Generalized Linear Model between Gamma and Tweedie Compound Response for Rainfall Prediction in Lampung Province

Rainfall plays a pivotal role in influencing agricultural production in Lampung province. The precision of rainfall predictions holds significant importance for enhancing agricultural yields in the region. One effective approach for modeling rainfall is Statistical Downscaling (SD), which employs statistical models to examine the correlation between large-scale (global) climatological data and small-scale (local) data. SD addresses the limitation of global scale data, such as the General Circulation Model (GCM), which lacks the resolution to directly forecast localized climate conditions like rainfall. Rainfall can be broadly categorized into continuous and discrete components. The continuous component delineates the intensity of rainfall, while the discrete component describes the occurrence of rain. Both components are integral to accurate rainfall predictions. The mixed Tweedie distribution, combining Gamma and Poisson distributions, is proficient in handling both continuous and discrete components of rainfall. GCMs commonly encounter multicollinearity issues in SD modeling, which can be mitigated through Principal Component Analysis. This study seeks to compare two regression models: the generalized linear model with a gamma response and the Tweedie compound response. Rainfall data from three distinct regions in Lampung province, representing high, medium, and lowlands, is utilized. The research findings indicate that, for high and lowlands, the Tweedie compound exhibits a smaller Root Mean Square Error of Prediction (RMSEP) compared to gamma. Conversely, in medium lands, gamma-GLM demonstrates a smaller RMSEP value than the Tweedie compound. Thus, the distribution of the Tweedie compound is better suited for use than Gamma-GLM, especially for high and lowland areas.

Substrate-Assisted Laser-Induced Breakdown Spectroscopy Combined with Variable Selection and Extreme Learning Machine for Quantitative Determination of Fenthion in Soybean Oil

The quality and safety of edible vegetable oils are closely related to human life and health, meaning it is of great significance to explore the rapid detection methods of pesticide residues in edible vegetable oils. This study explored the applicability potential of substrate-assisted laser-induced breakdown spectroscopy (LIBS) for quantitatively determining fenthion in soybean oils. First, we explored the impact of laser energy, delay time, and average oil film thickness on the spectral signals to identify the best experimental parameters. Afterward, we quantitatively analyzed soybean oil samples using these optimized conditions and developed a full-spectrum extreme learning machine (ELM) model. The model achieved a prediction correlation coefficient (RP2) of 0.8417, a root mean square error of prediction (RMSEP) of 167.2986, and a mean absolute percentage error of prediction (MAPEP) of 26.46%. In order to enhance the prediction performance of the model, a modeling method using the Boruta algorithm combined with the ELM was proposed. The Boruta algorithm was employed to identify the feature variables that exhibit a strong correlation with the fenthion content. These selected variables were utilized as inputs for the ELM model, with the RP2, RMSEP, and MAPEP of Boruta-ELM being 0.9631, 71.4423, and 10.06%, respectively. Then, the genetic algorithm (GA) was used to optimize the parameters of the Boruta-ELM model, with the RP2, RMSEP, and MAPEP of GA-Boruta-ELM being 0.9962, 11.005, and 1.66%, respectively. The findings demonstrate that the GA-Boruta-ELM model exhibits excellent prediction capability and effectively predicts the fenthion contents in soybean oil samples. It will be valuable for the LIBS quantitative detection and analysis of pesticide residues in edible vegetable oils.

Predicting bathymetry based on vertical gravity gradient anomaly and analyses for various influential factors

The prediction of bathymetry has advanced significantly with the development of satellite altimetry. However, the majority of its data originate from marine gravity anomaly. In this study, based on the expression of vertical gravity gradient (VGG) of a rectangular prism, the governing equations for determining sea depths to invert bathymetry. The governing equation is solved by linearization through an iterative process, and numerical simulations verify its algorithm and its stability. We also study the processing methods of different interference errors. The regularization method improves the stability of the inversion process for errors. A piecewise bilinear interpolation function roughly replaces the low-frequency error, and numerical simulations show that the accuracy can be improved by 41.2 % after this treatment. For variable ocean crust density, simulation simulations verify that the root-mean-square (RMS) error of prediction is approximately 5 m for the sea depth of 6 km if density is chosen as the average one. Finally, two test regions in the South China Sea are predicted and compared with ship soundings data, RMS errors of predictions are 71.1 m and 91.4 m, respectively.

Strategies for the quality control of Chrysanthemi Flos: Rapid quantification and end-to-end fingerprint conversion based on FT-NIR spectroscopy.

Chrysanthemi Flos (CF) is widely used as a natural medicine or tea. Due to its diverse cultivation regions, CF exhibits varying quality. Therefore, the quality and swiftness in evaluation holds paramount significance for CF. The aim of the study was to construct a comprehensive evaluation strategy for assessing CF quality using HPLC, near-infrared (NIR) spectroscopy, and chemometrics, which included the rapid quantification analyses of chemical components and the Fourier transform (FT)-NIR to HPLC conversion of fingerprints. A total of 145 CF samples were utilised for data collection via NIR spectroscopy and HPLC. The partial least squares regression (PLSR) models were optimised using various spectral preprocessing and variable selection methods to predict the chemical composition content in CF. Both direct standardisation (DS) and PLSR algorithms were employed to establish the fingerprint conversion model from the FT-NIR spectrum to HPLC, and the model's performance was assessed through similarity and cluster analysis. The optimised PLSR quantitative models can effectively predict the content of eight chemical components in CF. Both DS and PLSR algorithms achieve the calibration conversion of CF fingerprints from FT-NIR to HPLC, and the predicted and measured HPLC fingerprints are highly similar. Notably, the best model relies on CF powder FT-NIR spectra and DS algorithm [root mean square error of prediction (RMSEP) = 2.7590, R2 = 0.8558]. A high average similarity (0.9184) prevails between predicted and measured fingerprints of test set samples, and the results of the clustering analysis exhibit a high level of consistency. This comprehensive strategy provides a novel and dependable approach for the rapid quality evaluation of CF.

Rapid Lignin Thermal Property Prediction through Attenuated Total Reflectance-Infrared Spectroscopy and Chemometrics.

To expedite the valorisation of lignin as a sustainable component in materials applications, rapid and generally available analytical methods are essential to overcome the bottleneck of lignin characterisation. Where features of a lignin's chemical structure have previously been found to be predicted by Partial Least Squares (PLS) regression models built on Infrared (IR) data, we now show for the first time that this approach can be extended to prediction of the glass transition temperature (Tg), a key physicochemical property. This methodology is shown to be convenient and more robust for prediction of Tg than prediction through empirically derived relationships (e. g., Flory-Fox). The chemometric analysis provided root mean squared errors of prediction (RMSEP) as low as 10.0 °C for a botanically, and a process-diverse set of lignins, and 6.2 °C for kraft-only samples. The PLS models could separately predict both the Tg as well as the degree of allylation (%allyl) for allylated lignin fractions, which were all derived from a single lignin source. The models performed exceptionally well, delivering RMSEP of 6.1 °C, and 5.4 %, respectively, despite the conflicting influences of increasing molecular weight and %allyl on Tg. Finally, the method provided accurate determinations of %allyl with RMSEP of 5.2 %.

Laser-induced breakdown spectroscopy as an analytical tool for total carbon quantification in tropical and subtropical soils: evaluation of calibration algorithms

The demand for efficient, accurate, and cost-effective methods of measuring soil carbon (C) in agriculture is growing. Traditional approaches are time consuming and expensive, highlighting the need for alternatives. This study tackles the challenge of utilizing laser-induced breakdown spectroscopy (LIBS) as a more economical method while managing its potential accuracy issues due to physical–chemical matrix effects. A set of 1,019 soil samples from 11 Brazilian farms was analyzed using various univariate and multivariate calibration strategies. The artificial neural network (ANN) demonstrated the best performance with the lowest root mean square error of prediction (RMSEP) of 0.48 wt% C, a 28% reduction compared to the following best calibration method (matrix-matching calibration – MMC inverse regression and multiple linear regression – MLR at 0.67 wt% C). Furthermore, the study revealed a strong correlation between total C determined by LIBS and the elemental CHNS analyzer for soils samples in nine farms (R² ≥ 0.73). The proposed method offers a reliable, rapid, and cost-efficient means of measuring total soil C content, showing that LIBS and ANN modeling can significantly reduce errors compared to other calibration methods. This research fills the knowledge gap in utilizing LIBS for soil C measurement in agriculture, potentially benefiting producers and the soil C credit market. Specific recommendations include further exploration of ANN modeling for broader applications, ensuring that agricultural soil management becomes more accessible and efficient.

Rapid determination of alprazolam in gin tonic cocktails based on the coupling of IR spectroscopy and chemometrics: A feasibility study

“Drug-facilitated sexual assault" (DFSA) is a sexual assault perpetrated against a person rendered unconscious by a substance that changes her/his physical and/or mental condition, such as ethanol or drugs. Several active pharmaceutical ingredients, whether used alone or with alcoholic beverages, can produce anterograde amnesia and loss of inhibition. The most common pharmaceuticals found in DFSAs are GHB (-hydroxybutyric acid), benzodiazepines (Valium, Xanax, or Roipnol), antidepressants (Venlafaxine), muscle relaxants (cyclobenzaprine), antihistamines, sleeping pills (diphenhydramines), hallucinogens, and opioids. Biological samples are typically examined in cases of suspected DFSA; however, occasionally, samples are sent to labs a long period after being collected, jeopardizing the accuracy of the analysis. As a result, in recent years, the focus has shifted to directly detecting the presence of drugs in alcoholic beverages. In light of this, the purpose of the current study is to build a FT-IR-based approach for the determination of alprazolam in a common long drink (gin and tonic). To achieve this goal, pure (Class Pure) and spiked gin tonics (Class Spiked) were analyzed by Fourier-transform infrared spectroscopy (FT-IR). Afterward, two classifiers were used: Sequential preprocessing through ORThogonalization Linear Discriminant Analysis (SPORT-LDA) and Soft Independent Modeling of Class Analogies (SIMCA). Both approaches provided good results: SPORT-LDA achieved a 95% and a 98% accuracy rate (on the external test set of samples) for spiked and pure cocktails, respectively. This corresponds to the misclassification of 5 spiked and 1 pure drinks. The SIMCA model of class pure achieved 98.2% and 91.7% of specificity and sensitivity, respectively, coinciding with 55 pure samples (over 60) correctly accepted and 2 (over 110) erroneously rejected by the model. In conclusion, the SIMCA model of class pure seems preferable, because it minimizes the type II error. Eventually, the study was circumscribed to the spiked cocktails and a novel SPORT model was used to quantify alprazolam in spiked cocktails. This provided noteworthy results, in fact, it led to a Root Mean Square Error in Prediction (RMSEP) of 0.95, and a R2pred of 0.98.

Quantitative detection of moisture content of corn by olfactory visualization technology

In this study, a novel method for quantitatively detecting the moisture content of corn by olfactory visualization technology is proposed. First of all, an olfactory visualization system was developed to obtain odor information of corn samples with varying moisture contents using sensor arrays. The sensor array was constructed with twelve chemical dyes, which helped assemble the system. Then, the RreliefF algorithm was utilized to sort the characteristic variables of the sensor image by weight, and the analytical model based on different combinations of input features was built using support vector regression (SVR). Moreover, the ability of three optimization algorithms, namely grid search (GS), particle swarm optimization (PSO) and dung beetle optimizer (DBO), was compared to determine their effectiveness in optimizing the parameters of the SVR model. The results reveal that the RreliefF-GS-SVR model demonstrates an enhanced correlation coefficient of prediction (RP), with an increase from 0.97 to 0.98, as well as the root mean square error of prediction (RMSEP), is reduced from 0.66% to 0.53% when compared to the GS-SVR model. Similarly, in comparison to the RreliefF-GS-SVR model and RreliefF-PSO-SVR model, the RreliefF-DBO-SVR model shows better predictive performance, with an increase in RP to 0.99 and a decrease in RMSEP to 0.25%. The comprehensive findings indicate that integrating olfactory visualization technology and multivariate analysis is feasible for conducting quantitative analysis of grain moisture content.

Adaptive modeling optimized by the data fusion strategy: Real-time dying cell percentage prediction using capacitance spectroscopy.

The previous research showcased a partial least squares (PLS) regression model accurately predicting cell death percentages using in-line capacitance spectra. The current study advances the model accuracy through adaptive modeling employing a data fusion approach. This strategy enhances prediction performance by incorporating variables from the Cole-Cole model, conductivity and its derivatives over time, and Mahalanobis distance into the predictor matrix (X-matrix). Firstly, the Cole-Cole model, a mechanistic model with parameters linked to early cell death onset, was integrated to enhance prediction performance. Secondly, the inclusion of conductivity and its derivatives over time in the X-matrix mitigated prediction fluctuations resulting from abrupt conductivity changes during process operations. Thirdly, Mahalanobis distance, depicting spectral changes relative to a reference spectrum from a previous time point, improved model adaptability to independent test sets, thereby enhancing performance. The final data fusion model substantially decreased root-mean squared error of prediction (RMSEP) by around 50%, which is a significant boost in prediction accuracy compared to the prior PLS model. Robustness against reference spectrum selection was confirmed by consistent performance across various time points. In conclusion, this study illustrates that the data fusion strategy substantially enhances the model accuracy compared to the previous model relying solely on capacitance spectra.

Simultaneous determination of tartrazine and auramine O using FTIR spectroscopy and partial least square

Nowadays, the use of colouring agents are needed to increase customers’ acceptability of foods. However, the development of food technology averts a big opportunity to use prohibited food colouring agents. Tartrazine (TAR) and Auramine O (AO) are two colouring agents may be used as food colorants. TAR is allowed, while AO is not allowed to be used in food colorants, respectively. For this study, the goal was to validate and apply Fourier transform infrared (FTIR) combined with multivariate calibrations for quantitative analysis of TAR and AO in beverages. An attenuated total reflectance FTIR scan of samples was performed at wavenumbers ranging from 4000-650 cm-1 . Quantitative analysis using FTIR spectroscopy was made by plotting the actual levels of TAR and AO obtained using HPLC and the prediction levels facilitated by partial least square (PLS) from the sample series. Internal cross-validation is performed on the model using the leave-one-out method. The root mean square error of prediction (RMSEP), the root mean square error of cross validation (RMSECV), the root mean square error of calibration (RMSEC), as well as the coefficient of determination (R2 ) become validation criteria. The results exhibited that calibration model was gained using variables of FTIR spectra at wavenumbers of 1730-1264 cm-1 . Correlation coefficients (r) of 0.9437 (TAR) and 0.9381 (FTIR) are present in the calibration model for the correlation of actual and predicted values. The method for analyzing tartrazine and auramine O in powdered beverages was validated using multivariate PLS FTIR calibration spectroscopy. FTIR spectroscopy could be further developed as an alternative technique for analysis of TAR and AO in beverages.

Non-destructive prediction of the total viable count (TVC) in Fujian oysters (Crassostrea angulata) based on the colorimetric sensor array

The total viable count (TVC) is a traditional method for evaluating seafood freshness. This study aimed to predict the TVC of Fujian oysters stored at 4℃ by using the colorimetric sensing array (CSA) technique combined with imaging and visible near-infrared (Vis-NIR) information channels. An optimal quantitative prediction model based on partial least squares (PLS) was established by combining feature variable selection with a data fusion strategy. All three data-fusion strategies showed better predictive performance than the individual datasets. The high-level fusion strategy performed the best, with a root mean square error of prediction (RMSEP) of 0.17, mean absolute error of prediction (MAEP) of 0.14, coefficient of determination of prediction (Rp2) of 0.9822, and residual prediction deviation (RPD) of 7.37. The experimental results showed that CSA combined with multiple detection channels could be effectively used to predict the TVC of Fujian oysters. In this study, a reliable and comprehensive evaluation model was established to achieve a rapid and accurate prediction of oyster freshness.

Comparison of principal component regression (PCR) and partial least square regression (PLSR) modeling methods for quantifying polyethylene (PE) in recycled polypropylene (rPP) with near-infrared spectrometry (NIR)

Recycled polypropylene (rPP) often contains a small amount of polyethylene (PE). Since polypropylene (PP) and PE are incompatible, the presence of PE compromises the performance of rPP materials and needs to be closely monitored. In our previous work, Raman and near-infrared (NIR) spectrometries were evaluated to monitor PE content in rPP with partial least square regression (PLSR) modeling. The NIR spectrometry exhibited a wider application range, but the accuracy of the prediction models might be further improved. In the current work, a different modeling method, principal component regression (PCR) was employed to analyze PE content in rPP with NIR spectrometry. Spectrum pretreatment methods, including multivariate scatter correction (MSC), standard normal variate transformation (SNV), smoothing, and first derivative, were investigated to improve the NIR spectrum quality. Forward and backward interval methods were used to optimize spectral range selection. The outcomes were compared with our previous PLSR modeling results. The highest accuracy in independent validation was achieved by a PCR model with an R 2 of 0.9991 and a root-mean-square error of prediction (RMSEP) of 0.1596 PE%. On the other hand, a PLSR model achieved the lowest RMSEP of 0.9712 PE% for a non-colored post-consumer rPP sample. The PCR models might be sensitive to interference and more suitable for post-industrial materials, which have a simpler chemical composition. The PLSR models might have better stability and be more suitable for complicated post-consumer samples. Both the PCR and PLSR models were successfully applied to a gray commercial rPP sample.

Predicting fat cover in beef cattle to make on-farm management decisions: a review of assessing fat and of modeling fat deposition.

Demands of domestic and foreign market specifications of carcass weight and fat cover, of beef cattle, have led to the development of cattle growth models that predict fat cover to assist on-farm managers make management decisions. The objectives of this paper are 4-fold: 1) conduct a brief review of the biological basis of adipose tissue accretion, 2) briefly review live and carcass assessments of beef cattle, and carcass grading systems used to develop quantitative compositional and quality indices, 3) review fat deposition models: Davis growth model (DGM), French National Institute for Agricultural Research growth model (IGM), Cornell Value Discovery System (CVDS), and BeefSpecs drafting tool (BeefSpecsDT), and 4) appraise the process of translating science and practical skills into research/decision support tools that assist the Beef industry improve profitability. The r2 for live and carcass animal assessments, using several techniques across a range of species and traits, ranged from 0.61 to 0.99 and from 0.52 to 0.99, respectively. Model evaluations of DGM and IGM were conducted using Salers heifers (n = 24) and Angus-Hereford steers (n = 15) from an existing publication and model evaluations of CVDS and BeefSpecsDT were conducted using Angus steers (n = 33) from a research trial where steers were grain finished for 101 d in a commercial feedlot. Evaluating the observed and predicted fat mass (FM) is the focus of this review. The FM mean bias for Salers heifers were 7.5 and 1.3kg and the root mean square error of prediction (RMSEP) were 31.2 and 27.8kg and for Angus-Hereford steers the mean bias were -4.0 and -10.5kg and the RMSEP were 9.14 and 21.5kg for DGM and IGM, respectively. The FM mean bias for Angus steers were -5.61 and -2.93kg and the RMSEP were 12.3 and 13.4kg for CVDS and BeefSpecsDT, respectively. The decomposition for bias, slope, and deviance were 21%, 12%, and 68% and 5%, 4%, and 91% for CVDS and BeefSpecsDT, respectively. The modeling efficiencies were 0.38 and 0.27 and the models were within a 20kg level of tolerance 91% and 88% for CVDS and BeefSpecsDT, respectively. Fat deposition models reported in this review have the potential to assist the beef industry make on-farm management decisions on live cattle before slaughter and improve profitability. Modelers need to continually assess and improve their models but with a caveat of 1) striving to minimize inputs, and 2) choosing on-farm inputs that are readily available.

Developing a compact coal quality rapid detection integrated machine based on laser‐induced breakdown spectroscopy

AbstractCoal's calorific value and carbon content are crucial in calculating carbon emissions. Accurately detecting these two indicators is of great significance for carbon accounting. In this study, we developed a compact coal quality rapid detection integrated machine based on laser‐induced breakdown spectroscopy (LIBS), which can directly measure coal particle flow. A partial least squares model, based on data set selection according to cluster analysis results, was applied to establish the relationship between coal quality and plasma spectra. The R2 of the calorific value is .93, the root mean square error of prediction (RMSEP) is 0.41 MJ/kg, and the mean absolute error (MAE) is 0.33 MJ/kg. The R2 of carbon content is .94, the RMSEP is 0.97%, and the MAE is 0.91%. These results indicated that the developed compact coal quality rapid detection integrated machine could conduct precise coal quality analysis in real time.

PREDICTING BODY WEIGHT THROUGH BIOMETRIC MEASUREMENTS IN BOLIVIAN LLAMAS

The objective of this study was to evaluate the relationship between body weight (BW) and different biometric measurements in llamas (Lama glama) from the Bolivian highlands and to generate prediction models of BW. A total of 515 individual records of BW and biometric measurements were used. The measurements were taken on 202 males and 313 females aged between 0.5 and 5 years, and included: neck length (NL), withers height (WH), rump height (RH), heart girth (HG), body length (BL), abdomen circumference (AC), rib depth (RD), hip width (HW), pin bone width (PBW), thoracic width (TW), and back length (BKL). The relationships between BW and biometric measurements were developed using simple linear and multiple regression. For the evaluation, the relationship between the observed and predicted values of BW was determined by linear regression, the mean squared error of prediction (MSEP) and root MSEP (RMSEP); concordance correlation coefficient analysis was also used. The BW ranged from 22 to 122 kg. Regression equations between BW, HG and RD had an r2 of 0.94 and 0.92, respectively (RMSEP= 6.06 and 6.70 kg, respectively). The equations were highly precise (r2 >0.86) and accurate (Cb>0.98), with a reproducibility index > 0.92. The model efficiency (MEF) indicated a higher efficiency of prediction (MEF ≥ 0.86). Using a single predictor, HG and RD accounted for more than 92% of the variation in BW. Overall, HG may be used as a single predictor to predict BW in llamas maintained under the conditions of the Bolivian highlands.

Prediction of physical attributes in fresh grapevine (Vitis vinifera L.) organs using infrared spectroscopy and chemometrics

Spectra obtained from fresh grapevine organs provide information on chemical composition but could also contain valuable information on the morphological and physical attributes. The prediction of grapevine organs physical attributes using infrared spectroscopy is explored for the first time in this study. Near infrared spectroscopy (NIR) using a solid probe (NIR-SP) and a rotating integrating sphere (NIR-RS) and mid infrared (MIR) were used to obtain spectra from fresh and intact grapevine shoots, leaves, and berries. Linear partial least squares (PLS) and non-linear least absolute shrinkage and selection operator (LASSO), and extreme gradient boost (XGBoost) were implemented to predict relevant physical attributes in grapevine organs. NIR-RS using XGBoost showed coefficients of determination in validation (R2val) of 91.01% and root mean square error of prediction (RMSEP) of 0.71 mm (6.80%) for berry diameter. Shoot diameter was predicted at R2val of 62.08% and RMSEP at 0.82 mm (12.75%) using NIR-RS with LASSO regression. Monitoring these attributes throughout the growing season can lead to important viticultural information on grapevine yield, growth, and health.

Comparison of nine machine learning regression models in predicting hospital length of stay for patients admitted to a general medicine department

BackgroundThe General Medicine (GM) department has the highest patient volume and heterogeneity among other hospital specialties. Closely examining hospitalization data is crucial because patients come with various conditions or traits. Length of stay (LoS) in hospitals is often used as an efficiency indicator. It is influenced by various factors, including the patient's medical background, demographics, and type of diseases/signs/symptoms at the triage. LoS is a variable that can vary widely, making it difficult to estimate it promptly and accurately, but doing so is highly beneficial. Moreover, efficiently grouping and managing patients based on their expected LoS remains a significant challenge for healthcare organizations. ObjectivesThis study aimed to compare the predictive ability of nine Machine Learning (ML) regression models in estimating the actual number of LoS days using demographics and clinical information recorded at admission as independent variables. MethodsWe analyzed data collected on patients hospitalized at the GM department of the Sant'Orsola-Malpighi University Hospital in Bologna, Italy, who were admitted through the Emergency Department. The data were collected from January 1, 2022, to October 26, 2022. Nine ML regression models were used to predict LoS by analyzing historical data and patient information. The models' performance was assessed through root mean squared prediction error (RMSPE) and mean absolute prediction error (MAPE). Moreover, we used K-means clustering to group patients' medical and organizational criticalities (such as diseases, signs, symptoms, and administrative problems) into four clusters. Feature Importance plots and SHAP (SHapley Additive exPlanations) values were employed to identify the more essential features and enhance the interpretability of the results. ResultsWe analyzed the LoS of 3757 eligible patients, which showed an average of 13 days and a standard deviation of 11.8 days. We randomly divided patients into a training cohort of 2630 (70 %) and a test cohort of 1127 (30 %). The predictive performance of the different models was between 11.00 and 16.16 days for RMSPE and between 7.52 and 10.78 days for MAPE. The eXtreme Gradient Boosting Regression (XGBR) model had the lowest prediction error, both in terms of RMSPE (11.00 days) and MAE (7.52 days). Sex, arrival via own vehicle/walk-in, ambulance arrival, light blue risk category, age 70 or older, and orange risk category are some of the top features. ConclusionThe ML models evaluated in this study reported good predictive performance, with the XGBR model exhibiting the lowest prediction error. This model holds the potential to aid physicians in administering appropriate clinical interventions for patients in the GM department. This model can also help healthcare services predict the resources necessary to better manage hospitalization.

Trace level detection of melamine and cyanuric acid extracted from pet liquid food (milk) using a SERS Au nanogap substrate

This study reported an application of Au nanogap substrates for surface-enhanced Raman scattering (SERS) measurements to quantitatively analyze melamine and its derivative products at trace levels in pet liquid food (milk) combined with a waveband selection approach, namely variable importance in projection (VIP). Six different concentrations of melamine, cyanuric acid, and melamine combined with cyanuric acid were created, and SERS spectra were acquired from 550 to 1620cm−1. Detection was possible up to 200 pM for melamine-contaminated samples, and 400 pM concentration detection for other two groups. The VIP-PLSR models obtained correlation coefficient (R2) values of 0.997, 0.985, and 0.981, with root mean square error of prediction (RMSEP) values of 18.492 pM, 19.777 pM, and 15.124 pM for prediction datasets. Additionally, partial least square discriminant analysis (PLS-DA) was used to classify both pure and different concentrations of spiked samples. The results showed that the maximum classification accuracy for melamine was 100%, for cyanuric acid it was 96%, and for melamine coupled with cyanuric acid it was 95%. The results obtained clearly demonstrated that the Au nanogap substrate offers low-concentration, rapid, and efficient detection of hazardous additive chemicals in pet consuming liquid food.

Determination of fumonisin content in maize using near-infrared hyperspectral imaging (NIR-HSI) technology and chemometric methods.

Maize (Zea mays L.) is of socioeconomic importance as an essential food for human and animal nutrition. However, cereals are susceptible to attack by mycotoxin-producing fungi, which can damage health. The methods most commonly used to detect and quantify mycotoxins are expensive and time-consuming. Therefore, alternative non-destructive methods are required urgently. The present study aimed to use near-infrared spectroscopy with hyperspectral imaging (NIR-HSI) and multivariate image analysis to develop a rapid and accurate method for quantifying fumonisins in whole grains of six naturally contaminated maize cultivars. Fifty-eight samples, each containing 40 grains, were subjected to NIR-HSI. These were subsequently divided into calibration (38 samples) and prediction sets (20 samples) based on the multispectral data obtained. The averaged spectra were subjected to various pre-processing techniques (standard normal variate (SNV), first derivative, or second derivative). The most effective pre-treatment performed on the spectra was SNV. Partial least squares (PLS) models were developed to quantify the fumonisin content. The final model presented a correlation coefficient (R2) of 0.98 and root mean square error of calibration (RMSEC) of 508 µg.kg-1 for the calibration set, an R2 of 0.95 and root mean square error of prediction (RMSEP) of 508 µg.kg-1 for the test validation set and a ratio of performance to deviation of 4.7. It was concluded that NIR-HSI with partial least square regression is a rapid, effective, and non-destructive method to determine the fumonisin content in whole maize grains.