A Comparison of Random Forest Variable Selection Methods for Classification Prediction Modeling

Learning a neural network-based soft sensor with double-errors parallel optimization towards effluent variable prediction in wastewater treatment plants

With the development of machine learning and artificial intelligence (ML/AI) models, data-driven soft sensors, especially the neural network-based, have widespread utilization for the prediction of key water quality indicators in wastewater treatment plants (WWTPs). However, recent research indicates that the prediction performance and computational efficiency are greatly compromised due to the time-varying, nonlinear and high-dimensional nature of the wastewater treatment process. This paper proposes a neural network-based soft sensor with double-errors parallel optimization to achieve more accurate prediction for effluent variables timely. Firstly, relying on the Activity Based Classification (ABC) principle, an ensemble variable selection method that combines Pearson correlation coefficient (PCC) and mutual information (MI) is introduced to select the optimal process variables as auxiliary variables, thereby reducing the data dimensionality and simplifying the model complexity. Subsequently, a double-errors parallel optimization methodology with minimizing both point prediction error and distribution error simultaneously is proposed, aiming to enhancing the training efficiency and the fitting quality of neural networks. Finally, the effectiveness is quantitatively assessed in two datasets collected from the Benchmark Simulation Model no. 1 (BMS1) and an actual oxidation ditch WWTP. The experimental results illustrate that the proposed soft sensor achieves precise effluent variable prediction, with RMSE, MAE and R2 values being 0.0606, 0.0486, 0.99930, and 0.06939, 0.05381, 0.98040, respectively. Consequently, this soft sensor can expedite the convergence speed in the neural network training process and enhance the prediction performance, thereby contributing to the effective optimization management of WWTPs.

Exploring the spatial patterns of landslide susceptibility assessment using interpretable Shapley method: Mechanisms of landslide formation in the Sichuan-Tibet region

Machine learning models are often viewed as black boxes in landslide susceptibility assessment, lacking an analysis of how input features predict outcomes. This makes it challenging to understand the mechanisms and key factors behind landslides. To enhance the interpretability of machine learning models in wide-area landslide susceptibility assessments, this study uses the Shapely method to explore the contributions of feature factors from local, global, and spatial perspectives. Landslide susceptibility assessments were conducted using random forest (RF), support vector machine (SVM), and eXtreme Gradient Boosting (XGBoost) models, focusing on the geologically complex Sichuan-Tibet region. Initially, the study revealed the contributions of specific key feature factors to landslides from a local perspective. It then examines the overall impact of interactions among feature factors on landslide occurrence globally. Finally, it unveils the spatial distribution patterns of the contributions of various feature factors to landslide occurrence. The analysis indicates the following: (1) The XGBoost model excels in landslide susceptibility assessment, achieving accuracy, precision, recall, F1-score, and AUC values of 0.7815, 0.7858, 0.7962, 0.7910, and 0.86, respectively; (2) The Shapely method identifies the leading factors for landslides in the Sichuan-Tibet region as Elevation (3000-4000 m), PGA (1-2 g), NDVI (<0.5), and distance to rivers (<3 km); (3) Using the Shapely method, the study explains the contributions, interaction mechanisms, and spatial distribution patterns of landslide susceptibility feature factors across local, global, and spatial perspectives. These findings offer new avenues and methods for the in-depth exploration and scientific prediction of landslide risks.

Sediment subduction in Hadean revealed by machine learning

Due to the scarcity of rock samples, the Hadean Era predating 4 billion years ago (Ga) poses challenges in understanding geological processes like subaerial weathering and plate tectonics that are critical for the evolution of life. The Jack Hills zircon from Western Australia, the primary Hadean samples available, offer valuable insights into magma sources and tectonic genesis through trace element signatures. However, a consensus on these signatures has not been reached. To address this, we developed a machine learning classifier capable of deciphering the geochemical fingerprints of zircon. This allowed us to identify the oldest detrital zircon originating from sedimentary-derived "S-type" granites. Our results indicate the presence of S-type granites as early as 4.24 Ga, persisting throughout the Hadean into the Archean. Examining global detrital zircon across Earth's history reveals consistent supercontinent-like cycles from the present back to the Hadean. These findings suggest that a significant amount of Hadean continental crust was exposed, weathered into sediments, and incorporated into the magma sources of Jack Hills zircon. Only the early operation of both subaerial weathering and plate subduction can account for the prevalence of S-type granites we observe. Additionally, the periodic evolution of S-type granite proportions implies that subduction-driven tectonic cycles were active during the Hadean, at least around 4.2 Ga. The evidence thus points toward an early Earth resembling the modern Earth in terms of active tectonics and habitable surface conditions. This suggests the potential for life to originate in environments like warm ponds rather than extreme hydrothermal settings.

Network Security Prediction of Industrial Control Based on Projection Equalization Optimization Algorithm

This paper predicts the network security posture of an ICS, focusing on the reliability of Industrial Control Systems (ICSs). Evidence reasoning (ER) and belief rule base (BRB) techniques are employed to establish an ICS network security posture prediction model, ensuring the secure operation and prediction of the ICS. This model first integrates various information from the ICS to determine its network security posture value. Subsequently, through ER iteration, information fusion occurs and serves as an input for the BRB prediction model, which necessitates initial parameter setting by relevant experts. External factors may influence the experts' predictions; therefore, this paper proposes the Projection Equalization Optimization (P-EO) algorithm. This optimization algorithm updates the initial parameters to enhance the prediction of the ICS network security posture through the model. Finally, industrial datasets are used as experimental data to improve the credibility of the prediction experiments and validate the model's predictive performance in the ICS. Compared with other methods, this paper's prediction model demonstrates a superior prediction accuracy. By further comparing with other algorithms, this paper has a certain advantage when using less historical data to make predictions.

Uncovering substrate specificity determinants of class IIb aminoacyl-tRNA synthetases with machine learning

Specific amino acid (AA) binding by aminoacyl-tRNA synthetases (aaRSs) is necessary for correct translation of the genetic code. Sequence and structure analyses have revealed the main specificity determinants and allowed a partitioning of aaRSs into two classes and several subclasses. However, the information contributed by each determinant has not been precisely quantified, and other, minor determinants may still be unidentified. Growth of genomic data and development of machine learning classification methods allow us to revisit these questions. This work considered the subclass IIb, formed by the three enzymes aspartyl-, asparaginyl-, and lysyl-tRNA synthetase (LysRS). Over 35,000 sequences from the Pfam database were considered, and used to train a machine-learning model based on ensembles of decision trees. The model was trained to reproduce the existing classification of each sequence as AspRS, AsnRS, or LysRS, and to identify which sequence positions were most important for the classification. A few positions (5-8 depending on the AA substrate) sufficed for accurate classification. Most but not all of them were well-known specificity determinants. The machine learning models thus identified sets of mutations that distinguish the three subclass members, which might be targeted in engineering efforts to alter or swap the AA specificities for biotechnology applications.

Characteristics of the immune environment in prostate cancer as an adjunct to immunotherapy

Background and Aims

The tumor microenvironment (TME) exerts an important role in carcinogenesis and progression. Several investigations have suggested that immune cell infiltration (ICI) is of high prognostic importance for tumor progression and patient survival in many tumors, particularly prostate cancer. The pattern of immune infiltration of PCa, on the other hand, has not been thoroughly understood.

Methods

The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) datasets on PCa were obtained, and several datasets were merged into one data set using the "ComBat" algorithm. The ICI profiles of PCa patients were then to be uncovered by two computer techniques. The unsupervised clustering method was utilized to identify three ICI patterns in tumor samples, and Principal Component Analysis (PCA) was conducted to estimate the ICI score.

Results

Three different clusters of three ICIs were identified in 1341 PCa samples, which also correlated with different clinical features/characteristics and biological pathways. Patients with PCa are classified into high and low subtypes based on the ICI scores extracted from immune-associated signature genes. High ICI score subtypes are associated with a worse prognosis, which may intrigue the activation of cancer-related and immune-related pathways such as pathways involving Toll-like receptors, T-cell receptors, JAK-STAT, and natural killer cells. The ICI score was linked to tumor mutation load and immune/cancer-relevant signaling pathways, which explain prostate cancer's poor prognosis.

Conclusion

The findings of this study not only advanced our knowledge of the mechanism of immune response in the prostate tumor microenvironment but also provided a novel biomarker, that is, the ICI score, for disease prognosis and guiding precision immunotherapy.

Development of a screening system of gene sets for estimating the time of early skeletal muscle injury based on second-generation sequencing technology

The present study is aimed to address the challenge of wound age estimation in forensic science by identifying reliable genetic markers using low-cost and high-precision second-generation sequencing technology. A total of 54 Sprague-Dawley rats were randomly assigned to a control group or injury groups, with injury groups being further divided into time points (4 h, 8 h, 12 h, 16 h, 20 h, 24 h, 28 h, and 32 h after injury, n = 6) to establish rat skeletal muscle contusion models. Gene expression data were obtained using second-generation sequencing technology, and differential gene expression analysis, weighted gene co-expression network analysis (WGCNA) and time-dependent expression trend analysis were performed. A total of six sets of biomarkers were obtained: differentially expressed genes at adjacent time points (127 genes), co-expressed genes most associated with wound age (213 genes), hub genes exhibiting time-dependent expression (264 genes), and sets of transcription factors (TF) corresponding to the above sets of genes (74, 87, and 99 genes, respectively). Then, random forest (RF), support vector machine (SVM) and multilayer perceptron (MLP), were constructed for wound age estimation from the above gene sets. The results estimated by transcription factors were all superior to the corresponding hub genes, with the transcription factor group of WGCNA performed the best, with average accuracy rates of 96% for three models' internal testing, and 91.7% for the highest external validation. This study demonstrates the advantages of the indicator screening system based on second-generation sequencing technology and transcription factor level for wound age estimation.

A Novel Electrical Equipment Status Diagnosis Method Based on Super-Resolution Reconstruction and Logical Reasoning

The accurate detection of electrical equipment states and faults is crucial for the reliable operation of such equipment and for maintaining the health of the overall power system. The state of power equipment can be effectively monitored through deep learning-based visual inspection methods, which provide essential information for diagnosing and predicting equipment failures. However, there are significant challenges: on the one hand, electrical equipment typically operates in complex environments, thus resulting in captured images that contain environmental noise, which significantly reduces the accuracy of state recognition based on visual perception. This, in turn, affects the comprehensiveness of the power system's situational awareness. On the other hand, visual perception is limited to obtaining the appearance characteristics of the equipment. The lack of logical reasoning makes it difficult for purely visual analysis to conduct a deeper analysis and diagnosis of the complex equipment state. Therefore, to address these two issues, we first designed an image super-resolution reconstruction method based on the Generative Adversarial Network (GAN) to filter environmental noise. Then, the pixel information is analyzed using a deep learning-based method to obtain the spatial feature of the equipment. Finally, by constructing the logic diagram for electrical equipment clusters, we propose an interpretable fault diagnosis method that integrates the spatial features and temporal states of the electrical equipment. To verify the effectiveness of the proposed algorithm, extensive experiments are conducted on six datasets. The results demonstrate that the proposed method can achieve high accuracy in diagnosing electrical equipment faults.

Applicability of machine learning techniques to analyze Microplastic transportation in open channels with different hydro-environmental factors

This research utilized machine learning to analyze experiments conducted in an open channel laboratory setting to predict microplastic transport with varying discharge, velocity, water depth, vegetation pattern, and microplastic density. Four machine learning (ML) models, incorporating Random Forest (RF), Decision Tree (DT), Extreme Gradient Boost (XGB) and K-Nearest Neighbor (KNN) algorithms, were developed and compared with the Linear Regression (LR) statistical model, using 75% of the data for training and 25% for validation. The predictions of ML algorithms were more accurate than the LR, while XGB and RF provided the best predictions. To explain the ML results, Explainable artificial intelligence (XAI) was employed by using Shapley Additive Explanations (SHAP) to predict the global behavior of variables. RF was the most reliable model, with a coefficient of correlation of 0.97 and a mean absolute percentage error of 1.8% after hyperparameter tuning. Results indicated that discharge, velocity, water depth, and vegetation all influenced microplastic transport. Discharge and vegetation enhanced and reduced microplastic transport, respectively, and showed a response to different vegetation patterns. A strong linear positive correlation (R2 = 0.8) was noted between microplastic density and retention. In the absence of dedicated microplastic transport analytical models and infeasibility of using classical sediment transport models in predicting microplastic transport, ML proved to be helpful. Moreover, the use of XAI will reduce the black-box nature of ML models with effective interpretation enhancing the trust of domain experts in ML predictions. The developed model offers a promising tool for real-world open channel predictions, informing effective management strategies to mitigate microplastic pollution.

BiPLS-RF: A hybrid wavelength selection strategy for laser induced fluorescence spectroscopy of power transformer oil

In this paper, a method for indirect diagnosis of transformer faults based on the fluorescence spectrum and characteristic wavelength screening of transformer oil has been proposed. Specifically, a hybrid strategy (BiPLS-RF) for establishing the fluorescence spectrum feature screening of transformer oil using backward interval partial least squares (BiPLS) and random forest (RF) has been proposed. Aiming at the problem of transformer fault diagnosis, the laser induced fluorescence (LIF) spectroscopy of transformer oil in different states was first collected, and it is found that the fluorescence spectrum intensity of normal transformer oil was stronger than that of faulty transformer oil. Then the characteristic bands of the original fluorescence spectra were screened by BiPLS. It is found that when the original fluorescence spectra were divided into 15 sub-intervals, the minimum root mean squares error of cross-validation can be obtained by selecting 3 sub-intervals (including 411 wavelengths). On this basis, RF was employed to further screen the characteristic wavelengths and realized the identification of the fluorescence spectrum. It is found that in the RF model composed of 54 trees, the selected 196 characteristic wavelengths of the fluorescence spectrum can minimize the analysis error (0.56%). In addition, the selected characteristic wavelength information was fed into other common classifiers to construct a fluorescence spectrum identification model, which further proved the effectiveness of BiPLS-RF for wavelength selection for LIF spectroscopy of power transformer oil. The results show that it is feasible to use BiPLS-RF to screen the characteristic wavelength of LIF spectroscopy and apply it to transformer fault diagnosis, which provides a new solution for transformer fault diagnosis.

Independent Risk Factors for Prolonged Tube Feeding After Endotracheal Intubation and Ventilation

PURPOSE

Postextubation dysphagia (PED) can lead to prolonged tube feeding, but risk factors associated with prolonged tube feeding in this population are largely unknown. The purpose of this study was to identify factors independently associated with prolonged tube feeding in adult inpatients who required intubation and mechanical ventilation.

MATERIALS AND METHODS

Retrospective observational cohort study in a dataset of 1.3 million inpatients. Extubated adults without preventilation dysphagia or tube feeding who underwent instrumental swallowing assessment were included. To characterize factors independently associated with prolonged tube feeding, we compiled a set of potential factors, completed factor selection using a random forest algorithm, and performed logistic regression.

RESULTS

In total, 206 of 987 (20.9%) patients had prolonged tube feeding. The regression model produced an area under the curve of 0.79. Factors with the greatest influence on prolonged tube feeding included dysphagia with thickened liquids, dysphagia with soft/solid foods, preadmission weight loss, number of intubations, admission for neurologic disorder, and hospital of admission.

CONCLUSIONS

Several factors predicted prolonged tube feeding after extubation. The strongest were some, but not all, aspects of swallowing function and clinical practice pattern variability. Clinical decision-making should consider bolus-specific data from instrumental swallowing evaluation rather than binary presence or absence of dysphagia.

Identification of Dendrobium Using Laser-Induced Breakdown Spectroscopy in Combination with a Multivariate Algorithm Model

Dendrobium, a highly effective traditional Chinese medicinal herb, exhibits significant variations in efficacy and price among different varieties. Therefore, achieving an efficient classification of Dendrobium is crucial. However, most of the existing identification methods for Dendrobium make it difficult to simultaneously achieve both non-destructiveness and high efficiency, making it challenging to truly meet the needs of industrial production. In this study, we combined Laser-Induced Breakdown Spectroscopy (LIBS) with multivariate models to classify 10 varieties of Dendrobium. LIBS spectral data for each Dendrobium variety were collected from three circular medicinal blocks. During the data analysis phase, multivariate models to classify different Dendrobium varieties first preprocess the LIBS spectral data using Gaussian filtering and stacked correlation coefficient feature selection. Subsequently, the constructed fusion model is utilized for classification. The results demonstrate that the classification accuracy of 10 Dendrobium varieties reached 100%. Compared to Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN), our method improved classification accuracy by 14%, 20%, and 20%, respectively. Additionally, it outperforms three models (SVM, RF, and KNN) with added Principal Component Analysis (PCA) by 10%, 10%, and 17%. This fully validates the excellent performance of our classification method. Finally, visualization analysis of the entire research process based on t-distributed Stochastic Neighbor Embedding (t-SNE) technology further enhances the interpretability of the model. This study, by combining LIBS and machine learning technologies, achieves efficient classification of Dendrobium, providing a feasible solution for the identification of Dendrobium and even traditional Chinese medicinal herbs.

Lipoproteins and metabolites in diagnosing and predicting Alzheimer's disease using machine learning

BACKGROUND

Alzheimer's disease (AD) is a chronic neurodegenerative disorder that poses a substantial economic burden. The Random forest algorithm is effective in predicting AD; however, the key factors influencing AD onset remain unclear. This study aimed to analyze the key lipoprotein and metabolite factors influencing AD onset using machine-learning methods. It provides new insights for researchers and medical personnel to understand AD and provides a reference for the early diagnosis, treatment, and early prevention of AD.

METHODS

A total of 603 participants, including controls and patients with AD with complete lipoprotein and metabolite data from the Alzheimer's disease Neuroimaging Initiative (ADNI) database between 2005 and 2016, were enrolled. Random forest, Lasso regression, and CatBoost algorithms were employed to rank and filter 213 lipoprotein and metabolite variables. Variables with consistently high importance rankings from any two methods were incorporated into the models. Finally, the variables selected from the three methods, with the participants' age, sex, and marital status, were used to construct a random forest predictive model.

RESULTS

Fourteen lipoprotein and metabolite variables were screened using the three methods, and 17 variables were included in the AD prediction model based on age, sex, and marital status of the participants. The optimal random forest modeling was constructed with "mtry" set to 3 and "ntree" set to 300. The model exhibited an accuracy of 71.01%, a sensitivity of 79.59%, a specificity of 65.28%, and an AUC (95%CI) of 0.724 (0.645-0.804). When Mean Decrease Accuracy and Gini were used to rank the proteins, age, phospholipids to total lipids ratio in intermediate-density lipoproteins (IDL_PL_PCT), and creatinine were among the top five variables.

CONCLUSIONS

Age, IDL_PL_PCT, and creatinine levels play crucial roles in AD onset. Regular monitoring of lipoproteins and their metabolites in older individuals is significant for early AD diagnosis and prevention.

Prediction of robo-advisory acceptance in banking services using tree-based algorithms

The banking sector is increasingly recognising the need to implement robo-advisory. The introduction of this service may lead to increased efficiency of banks, improved quality of customer service, and a strengthened image of banks as innovative institutions. Robo-advisory uses data relating to customers, their behaviors and preferences obtained by banks from various communication channels. In the research carried out in the work, an attempt was made to obtain an answer to the question whether the data collected by banks can also be used to determine the degree of consumer interest in this type of service. This is important because the identification of customers interested in the service will allow banks to direct a properly prepared message to a selected group of addressees, increasing the effectiveness of their promotional activities. The aim of the article is to construct and examine the effectiveness of predictive models of consumer acceptance of robo-advisory services provided by banks. Based on the authors' survey on the use of artificial intelligence technology in the banking sector in Poland, in this article we construct tree-based models to predict customers' attitudes towards using robo-advisory in banking services using, as predictors, their socio-demographic characteristics, behaviours and attitudes towards modern digital technologies, experience in using banking services, as well as trust towards banks. In our study, we use selected machine learning algorithms, including a decision tree and several tree-based ensemble models. We showed that constructed models allow to effectively predict consumer acceptance of robo-advisory services.

Exploring the Association Between Structural Racism and Mental Health: Geospatial and Machine Learning Analysis

BACKGROUND

Structural racism produces mental health disparities. While studies have examined the impact of individual factors such as poverty and education, the collective contribution of these elements, as manifestations of structural racism, has been less explored. Milwaukee County, Wisconsin, with its racial and socioeconomic diversity, provides a unique context for this multifactorial investigation.

OBJECTIVE

This research aimed to delineate the association between structural racism and mental health disparities in Milwaukee County, using a combination of geospatial and deep learning techniques. We used secondary data sets where all data were aggregated and anonymized before being released by federal agencies.

METHODS

We compiled 217 georeferenced explanatory variables across domains, initially deliberately excluding race-based factors to focus on nonracial determinants. This approach was designed to reveal the underlying patterns of risk factors contributing to poor mental health, subsequently reintegrating race to assess the effects of racism quantitatively. The variable selection combined tree-based methods (random forest) and conventional techniques, supported by variance inflation factor and Pearson correlation analysis for multicollinearity mitigation. The geographically weighted random forest model was used to investigate spatial heterogeneity and dependence. Self-organizing maps, combined with K-means clustering, were used to analyze data from Milwaukee communities, focusing on quantifying the impact of structural racism on the prevalence of poor mental health.

RESULTS

While 12 influential factors collectively accounted for 95.11% of the variability in mental health across communities, the top 6 factors-smoking, poverty, insufficient sleep, lack of health insurance, employment, and age-were particularly impactful. Predominantly, African American neighborhoods were disproportionately affected, which is 2.23 times more likely to encounter high-risk clusters for poor mental health.

CONCLUSIONS

The findings demonstrate that structural racism shapes mental health disparities, with Black community members disproportionately impacted. The multifaceted methodological approach underscores the value of integrating geospatial analysis and deep learning to understand complex social determinants of mental health. These insights highlight the need for targeted interventions, addressing both individual and systemic factors to mitigate mental health disparities rooted in structural racism.

Deep Learning Radiomics Model of Contrast-Enhanced CT for Differentiating the Primary Source of Liver Metastases

RATIONALE AND OBJECTIVES

To develop and validate a deep learning radiomics (DLR) model based on contrast-enhanced computed tomography (CT) to identify the primary source of liver metastases.

MATERIALS AND METHODS

In total, 657 liver metastatic lesions, including breast cancer (BC), lung cancer (LC), colorectal cancer (CRC), gastric cancer (GC), and pancreatic cancer (PC), from 428 patients were collected at three clinical centers from January 2018 to October 2023 series. The lesions were randomly assigned to the training and validation sets in a 7:3 ratio. An additional 112 lesions from 61 patients at another clinical center served as an external test set. A DLR model based on contrast-enhanced CT of the liver was developed to distinguish the five pathological types of liver metastases. Stepwise classification was performed to improve the classification efficiency of the model. Lesions were first classified as digestive tract cancer (DTC) and non-digestive tract cancer (non-DTC). DTCs were divided into CRC, GC, and PC and non-DTCs were divided into LC and BC. To verify the feasibility of the DLR model, we trained classical machine learning (ML) models as comparison models. Model performance was evaluated using accuracy (ACC) and area under the receiver operating characteristic curve (AUC).

RESULTS

The classification model constructed by the DLR algorithm showed excellent performance in the classification task compared to ML models. Among the five categories task, highest ACC and average AUC were achieved at 0.563 and 0.796 in the validation set, respectively. In the DTC and non-DTC and the LC and BC classification tasks, AUC was achieved at 0.907 and 0.809 and ACC was achieved at 0.843 and 0.772, respectively. In the CRC, GC, and PC classification task, ACC and average AUC were the highest, at 0.714 and 0.811, respectively.

CONCLUSION

The DLR model is an effective method for identifying the primary source of liver metastases.

Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study

Postoperative sore throat (POST) is a prevalent complication after general anesthesia and targeting high-risk patients helps in its prevention. This study developed and validated a machine learning model to predict POST. A total number of 834 patients who underwent general anesthesia with endotracheal intubation were included in this study. Data from a cohort of 685 patients was used for model development and validation, while a cohort of 149 patients served for external validation. The prediction performance of random forest (RF), neural network (NN), and extreme gradient boosting (XGBoost) models was compared using comprehensive performance metrics. The Local Interpretable Model-Agnostic Explanations (LIME) methods elucidated the best-performing model. POST incidences across training, validation, and testing cohorts were 41.7%, 38.4%, and 36.2%, respectively. Five predictors were age, sex, endotracheal tube cuff pressure, endotracheal tube insertion depth, and the time interval between extubation and the first drinking of water after extubation. After incorporating these variables, the NN model demonstrated superior generalization capabilities in predicting POST when compared to the XGBoost and RF models in external validation, achieving an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% CI 0.74-0.89) and a precision-recall curve (AUPRC) of 0.77 (95% CI 0.66-0.86). The model also showed good calibration and clinical usage values. The NN model outperforms the XGBoost and RF models in predicting POST, with potential applications in the healthcare industry for reducing the incidence of this common postoperative complication.

Investigating the uses of machine learning algorithms to inform risk factor analyses: The example of avian infectious bronchitis virus (IBV) in broiler chickens

Infectious bronchitis virus (IBV) is a contagious coronavirus causing respiratory and urogenital disease in chickens and is responsible for significant economic losses for both the broiler and table egg layer industries. Despite IBV being regularly monitored using standard epidemiologic surveillance practices, knowledge and evidence of risk factors associated with IBV transmission remain limited. The study objective was to compare risk factor modeling outcomes between a traditional stepwise variable selection approach and a machine learning-based random forest Boruta algorithm using routinely collected IBV antibody titer data from broiler flocks. IBV antibody sampling events (n = 1111) from 166 broiler sites between 2016 and 2021 were accessed. Ninety-two geospatial-related and poultry-density variables were obtained using a geographic information system and data sets from publicly available sources. Seventeen and 27 candidate variables were screened to potentially have an association with elevated IBV antibody titers according to the manual selection and machine learning algorithm, respectively. Selected variables from both methods were further investigated by construction of multivariable generalized mixed logistic regression models. Six variables were shortlisted by both screening methods, which included year, distance to urban areas, main roads, landcover, density of layer sites and year, however, final models for both approaches only shared year as an important predictor. Despite limited significance of clinical outcomes, this work showcases the potential of a novel explorative modeling approach in combination with often unutilized resources such as publicly available geospatial data, surveillance health data and machine learning as potential supplementary tools to investigate risk factors related to infectious diseases.

Predicting environmental impacts of smallholder wheat production by coupling life cycle assessment and machine learning

Wheat grain production is a vital component of the food supply produced by smallholder farms but faces significant threats from climate change. This study evaluated eight environmental impacts of wheat production using life cycle assessment based on survey data from 274 households, then built random forest models with 21 input features to contrast the environmental responses of different farming practices across three shared socioeconomic pathways (SSPs), spanning from 2024 to 2100. The results indicate significant environmental repercussions. Compared to the baseline period of 2018-2020, a similar upward trend in environmental impacts is observed, showing an average annual growth rate of 5.88 % (ranging from 0.45 to 18.56 %) under the sustainable pathway (SSP119) scenario; 5.90 % (ranging from 1.00 to 18.15 %) for the intermediate development pathway (SSP245); and 6.22 % (ranging from 1.16 to 17.74 %) under the rapid economic development pathway (SSP585). Variation in rainfall is identified as the primary driving factor of the increased environmental impacts, whereas its relationship with rising temperatures is not significant. The results suggest adopting farming practices as a vital strategy for smallholder farms to mitigate climate change impacts. Emphasizing appropriate fertilizer application and straw recycling can significantly reduce the environmental footprint of wheat production. Standardized fertilization could reduce the environmental impact index by 11.10 to 47.83 %, while straw recycling might decrease respiratory inorganics and photochemical oxidant formation potential by over 40 %. Combined, these approaches could lower the impact index by 12.31 to 63.38 %. The findings highlight the importance of adopting enhanced farming practices within smallholder farming systems in the context of climate change. SPOTLIGHTS.

A UV-Vis spectroscopic detection method for cobalt ions in zinc sulfate solution based on discrete wavelet transform and extreme gradient boosting

Zinc is a crucial strategic metal resource. The concentration of cobalt ions in zinc refining solution significantly impacts the efficiency of zinc electrolysis production. The traditional method of detecting cobalt ions in zinc solution is time-consuming, labor-intensive and ineffective. However, optical detection offers the advantage of high efficiency and low cost, making it a potential replacement for the traditional method. In this study, the spectral curve of cobalt ions in zinc solution is detected by ultraviolet-visible (UV-Vis) spectrophotometry. Additionally, we propose a model for the concentration-absorbance relationship of cobalt ions in zinc solution based on discrete wavelet transform and extreme gradient boosting (DWT-XGBoost) algorithms. First, the spectral curve's information region is denoised by using Savitzky-Golay (S-G) smoothing. Then, the denoised spectra is utilized to extract features through discrete wavelet transform and principal component analysis. These features are used as inputs to the XGBoost model to establish prediction models for low and high cobalt ions in zinc solution. Bayesian optimization is implemented to adjust the model's hyperparameters, including learning rate, feature sampling ratio, to enhance the prediction performance. Finally, applying the model to zinc solution samples from a zinc smelter and compared with other state-of-the-art algorithms, the DWT-XGBoost algorithm exhibits the lowest RMSE, MAE and MAPE, with values of 0.034 mg/L, 0.025 mg/L, 6.983 % for low cobalt and with values of 0.231 mg/L, 0.067 mg/L and 0.472 % for high cobalt. The experimental results demonstrate that the DWT-XGBoost model exhibits significantly superior prediction performance.

Machine learning pipeline to analyze clinical and proteomics data: experiences on a prostate cancer case

Proteomic-based analysis is used to identify biomarkers in blood samples and tissues. Data produced by devices such as mass spectrometry requires platforms to identify and quantify proteins (or peptides). Clinical information can be related to mass spectrometry data to identify diseases at an early stage. Machine learning techniques can be used to support physicians and biologists in studying and classifying pathologies. We present the application of machine learning techniques to define a pipeline aimed at studying and classifying proteomics data enriched using clinical information. The pipeline allows users to relate established blood biomarkers with clinical parameters and proteomics data. The proposed pipeline entails three main phases: (i) feature selection, (ii) models training, and (iii) models ensembling. We report the experience of applying such a pipeline to prostate-related diseases. Models have been trained on several biological datasets. We report experimental results about two datasets that result from the integration of clinical and mass spectrometry-based data in the contexts of serum and urine analysis. The pipeline receives input data from blood analytes, tissue samples, proteomic analysis, and urine biomarkers. It then trains different models for feature selection, classification and voting. The presented pipeline has been applied on two datasets obtained in a 2 years research project which aimed to extract hidden information from mass spectrometry, serum, and urine samples from hundreds of patients. We report results on analyzing prostate datasets serum with 143 samples, including 79 PCa and 84 BPH patients, and an urine dataset with 121 samples, including 67 PCa and 54 BPH patients. As results pipeline allowed to identify interesting peptides in the two datasets, 6 for the first one and 2 for the second one. The best model for both serum (AUC=0.87, Accuracy=0.83, F1=0.81, Sensitivity=0.84, Specificity=0.81) and urine (AUC=0.88, Accuracy=0.83, F1=0.83, Sensitivity=0.85, Specificity=0.80) datasets showed good predictive performances. We made the pipeline code available on GitHub and we are confident that it will be successfully adopted in similar clinical setups.

Classifying protein kinase conformations with machine learning

Protein kinases are key actors of signaling networks and important drug targets. They cycle between active and inactive conformations, distinguished by a few elements within the catalytic domain. One is the activation loop, whose conserved DFG motif can occupy DFG-in, DFG-out, and some rarer conformations. Annotation and classification of the structural kinome are important, as different conformations can be targeted by different inhibitors and activators. Valuable resources exist; however, large-scale applications will benefit from increased automation and interpretability of structural annotation. Interpretable machine learning models are described for this purpose, based on ensembles of decision trees. To train them, a set of catalytic domain sequences and structures was collected, somewhat larger and more diverse than existing resources. The structures were clustered based on the DFG conformation and manually annotated. They were then used as training input. Two main models were constructed, which distinguished active/inactive and in/out/other DFG conformations. They considered initially 1692 structural variables, spanning the whole catalytic domain, then identified ("learned") a small subset that sufficed for accurate classification. The first model correctly labeled all but 3 of 3289 structures as active or inactive, while the second assigned the correct DFG label to all but 17 of 8826 structures. The most potent classifying variables were all related to well-known structural elements in or near the activation loop and their ranking gives insights into the conformational preferences. The models were used to automatically annotate 3850 kinase structures predicted recently with the Alphafold2 tool, showing that Alphafold2 reproduced the active/inactive but not the DFG-in proportions seen in the Protein Data Bank. We expect the models will be useful for understanding and engineering kinases.

The application of laser‑induced fluorescence in oil spill detection

Over the past two decades, oil spills have been one of the most serious ecological disasters, causing massive damage to the aquatic and terrestrial ecosystems as well as the socio-economy. In view of this situation, several methods have been developed and utilized to analyze oil samples. Among these methods, laser-induced fluorescence (LIF) technology has been widely used in oil spill detection due to its classification method, which is based on the fluorescence characteristics of chemical material in oil. This review systematically summarized the LIF technology from the perspective of excitation wavelength selection and the application of traditional and novel machine learning algorithms to fluorescence spectrum processing, both of which are critical for qualitative and quantitative analysis of oil spills. It can be seen that an appropriate excitation wavelength is indispensable for spectral discrimination due to different kinds of polycyclic aromatic hydrocarbons' (PAHs) compounds in petroleum products. By summarizing some articles related to LIF technology, we discuss the influence of the excitation wavelength on the accuracy of the oil spill detection model and proposed several suggestions on the selection of excitation wavelength. In addition, we introduced some traditional and novel machine learning (ML) algorithms and discussed the strengths and weaknesses of these algorithms and their applicable scenarios. With an appropriate excitation wavelength and data processing algorithm, it is believed that laser-induced fluorescence technology will become an efficient technique for real-time detection and analysis of oil spills.

Machine learning reveals the selection pressure exerted by nonantibiotic pharmaceuticals at environmentally relevant concentrations on antibiotic resistance genotypes

The emergence and increasing prevalence of antibiotic resistance pose a global public risk for human health, and nonantimicrobial pharmaceuticals play an important role in this process. Herein, five nonantimicrobial pharmaceuticals, including acetaminophen (ACT), clofibric acid (CA), carbamazepine (CBZ), caffeine (CF) and nicotine (NCT), tetracycline-resistant strains, five ARGs (sul1, sul2, tetG, tetM and tetW) and one integrase gene (intI1), were detected in 101 wastewater samples during two typical sewage treatment processes including anaerobic-oxic (A/O) and biological aerated filter (BAF) in Harbin, China. The impact of nonantibiotic pharmaceuticals at environmentally relevant concentrations on both the resistance genotypes and resistance phenotypes were explored. The results showed that a significant impact of nonantibiotic pharmaceuticals at environmentally relevant concentrations on tetracycline resistance genes encoding ribosomal protection proteins (RPPs) was found, while no changes in antibiotic phenotypes, such as minimal inhibitory concentrations (MICs), were observed. Machine learning was applied to further sort out the contribution of nonantibiotic pharmaceuticals at environmentally relevant concentrations to different ARG subtypes. The highest contribution and correlation were found at concentrations of 1400-1800 ng/L for NCT, 900-1500 ng/L for ACT and 7000-10,000 ng/L for CF for tetracycline resistance genes encoding RPPs, while no significant correlation was found between the target compounds and ARGs when their concentrations were lower than 500 ng/L for NCT, 100 ng/L for ACT and 1000 ng/L for CF, which were higher than the concentrations detected in effluent samples. Therefore, the removal of nonantibiotic pharmaceuticals in WWTPs can reduce their selection pressure for resistance genes in wastewater.

Identification of population-informative markers from high-density genotyping data through combined feature selection and machine learning algorithms: Application to European autochthonous and cosmopolitan pig breeds

Large genotyping datasets, obtained from high-density single nucleotide polymorphism (SNP) arrays, developed for different livestock species, can be used to describe and differentiate breeds or populations. To identify the most discriminating genetic markers among thousands of genotyped SNPs, a few statistical approaches have been proposed. In this study, we applied the Boruta algorithm, a wrapper of the machine learning random forest algorithm, on a database of 23 European pig breeds (20 autochthonous and three cosmopolitan breeds) genotyped with a 70k SNP chip, to pre-select informative SNPs. To identify different sets of SNPs, these pre-selected markers were then ranked with random forest based on their mean decrease accuracy and mean decrease gene indexes. We evaluated the efficiency of these subsets for breed classification and the usefulness of this approach to detect candidate genes affecting breed-specific phenotypes and relevant production traits that might differ among breeds. The lowest overall classification error (2.3%) was reached with a subpanel including only 398 SNPs (ranked based on their mean decrease accuracy), with no classification error in seven breeds using up to 49 SNPs. Several SNPs of these selected subpanels were in genomic regions in which previous studies had identified signatures of selection or genes associated with morphological or production traits that distinguish the analysed breeds. Therefore, even if these approaches have not been originally designed to identify signatures of selection, the obtained results showed that they could potentially be useful for this purpose.

Insights into biogeochemistry and hot spots distribution characteristics of redox-sensitive elements in the hyporheic zone: Transformation mechanisms and contributing factors

Biogeochemical hot spots play a crucial role in the cycling and transport of redox-sensitive elements (RSEs) in the hyporheic zone (HZ). However, the transformation mechanisms of RSEs and patterns of RSEs hot spots in the HZ remain poorly understood. In this study, hydrochemistry and multi-isotope (N/C/S/O) datasets were collected to investigate the transformation mechanisms of RSEs, and explore the distribution characteristics of RSEs transformation hot spots. The results showed that spatial variability in key drivers was evident, while temporal change in RSEs concentration was not significant, except for dissolved organic carbon. Bacterial sulfate reduction (BSR) was the primary biogeochemical process for sulfate and occurred throughout the area. Ammonium enrichment was mainly caused by the mineralization of nitrogenous organic matter and anthropogenic inputs, with adsorption serving as the primary attenuation mechanism. Carbon dynamics were influenced by various biogeochemical processes, with dissolved organic carbon mainly derived from C3 plants and dissolved inorganic carbon from weathering of carbonate rocks and decomposition of organic matter. The peak contribution of dissolved organic carbon decomposition to the DIC pool was 46.44 %. The concentration thresholds for the ammonium enrichment and BSR hot spots were identified as 1.5 mg/L and 8.84 mg/L, respectively. The distribution pattern of RSEs hot spots was closely related to the hydrogeological conditions. Our findings reveal the complex evolution mechanisms and hot spots distribution characteristics of RSEs in the HZ, providing a basis for the safe utilization and protection of groundwater resources.

Bioaerosols in the coastal region of Qingdao: Community diversity, impact factors and synergistic effect

Atmospheric bioaerosols are influenced by multiple factors, including physical, chemical, and biotic interactions, and pose a significant threat to the public health and the environment. The nonnegligible truth however is that the primary driver of the changes in bioaerosol community diversity remains unknown. In this study, putative biological association (PBA) was obtained by constructing an ecological network. The relationship between meteorological conditions, atmospheric pollutants, water-soluble inorganic ions, PBA and bioaerosol community diversity was analyzed using random forest regression (RFR)-An ensemble learning algorithm based on a decision tree that performs regression tasks by constructing multiple decision trees and integrating the predicted results, and the contribution of different rich species to PBA was predicted. The species richness, evenness and diversity varied significantly in different seasons, with the highest in summer, followed by autumn and spring, and was lowest in winter. The RFR suggested that the explanation rate of alpha diversity increased significantly from 73.74 % to 85.21 % after accounting for the response of the PBA to diversity. The PBA, temperature, air pollution, and marine source air masses were the most crucial factors driving community diversity. PBA, particularly putative positive association (PPA), had the highest significance in diversity. We found that under changing external conditions, abundant taxa tend to cooperate to resist external pressure, thereby promoting PPA. In contrast, rare taxa were more responsive to the putative negative association because of their sensitivity to environmental changes. The results of this research provided scientific advance in the understanding of the dynamic and temporal changes in bioaerosols, as well as support for the prevention and control of microbial contamination of the atmosphere.

Machine Learning Methods Using Artificial Intelligence Deployed on Electronic Health Record Data for Identification and Referral of At-Risk Patients From Primary Care Physicians to Eye Care Specialists: Retrospective, Case-Controlled Study

BACKGROUND

Identification and referral of at-risk patients from primary care practitioners (PCPs) to eye care professionals remain a challenge. Approximately 1.9 million Americans suffer from vision loss as a result of undiagnosed or untreated ophthalmic conditions. In ophthalmology, artificial intelligence (AI) is used to predict glaucoma progression, recognize diabetic retinopathy (DR), and classify ocular tumors; however, AI has not yet been used to triage primary care patients for ophthalmology referral.

OBJECTIVE

This study aimed to build and compare machine learning (ML) methods, applicable to electronic health records (EHRs) of PCPs, capable of triaging patients for referral to eye care specialists.

METHODS

Accessing the Optum deidentified EHR data set, 743,039 patients with 5 leading vision conditions (age-related macular degeneration [AMD], visually significant cataract, DR, glaucoma, or ocular surface disease [OSD]) were exact-matched on age and gender to 743,039 controls without eye conditions. Between 142 and 182 non-ophthalmic parameters per patient were input into 5 ML methods: generalized linear model, L1-regularized logistic regression, random forest, Extreme Gradient Boosting (XGBoost), and J48 decision tree. Model performance was compared for each pathology to select the most predictive algorithm. The area under the curve (AUC) was assessed for all algorithms for each outcome.

RESULTS

XGBoost demonstrated the best performance, showing, respectively, a prediction accuracy and an AUC of 78.6% (95% CI 78.3%-78.9%) and 0.878 for visually significant cataract, 77.4% (95% CI 76.7%-78.1%) and 0.858 for exudative AMD, 79.2% (95% CI 78.8%-79.6%) and 0.879 for nonexudative AMD, 72.2% (95% CI 69.9%-74.5%) and 0.803 for OSD requiring medication, 70.8% (95% CI 70.5%-71.1%) and 0.785 for glaucoma, 85.0% (95% CI 84.2%-85.8%) and 0.924 for type 1 nonproliferative diabetic retinopathy (NPDR), 82.2% (95% CI 80.4%-84.0%) and 0.911 for type 1 proliferative diabetic retinopathy (PDR), 81.3% (95% CI 81.0%-81.6%) and 0.891 for type 2 NPDR, and 82.1% (95% CI 81.3%-82.9%) and 0.900 for type 2 PDR.

CONCLUSIONS

The 5 ML methods deployed were able to successfully identify patients with elevated odds ratios (ORs), thus capable of patient triage, for ocular pathology ranging from 2.4 (95% CI 2.4-2.5) for glaucoma to 5.7 (95% CI 5.0-6.4) for type 1 NPDR, with an average OR of 3.9. The application of these models could enable PCPs to better identify and triage patients at risk for treatable ophthalmic pathology. Early identification of patients with unrecognized sight-threatening conditions may lead to earlier treatment and a reduced economic burden. More importantly, such triage may improve patients' lives.

Towards identification of postharvest fruit quality transcriptomic markers in Malus domestica

Gene expression is highly impacted by the environment and can be reflective of past events that affected developmental processes. It is therefore expected that gene expression can serve as a signal of a current or future phenotypic traits. In this paper we identify sets of genes, which we call Prognostic Transcriptomic Biomarkers (PTBs), that can predict firmness in Malus domestica (apple) fruits. In apples, all individuals of a cultivar are clones, and differences in fruit quality are due to the environment. The apples transcriptome responds to these differences in environment, which makes PTBs an attractive predictor of future fruit quality. PTBs have the potential to enhance supply chain efficiency, reduce crop loss, and provide higher and more consistent quality for consumers. However, several questions must be addressed. In this paper we answer the question of which of two common modeling approaches, Random Forest or ElasticNet, outperforms the other. We answer if PTBs with few genes are efficient at predicting traits. This is important because we need few genes to perform qPCR, and we answer the question if qPCR is a cost-effective assay as input for PTBs modeled using high-throughput RNA-seq. To do this, we conducted a pilot study using fruit texture in the 'Gala' variety of apples across several postharvest storage regiments. Fruit texture in 'Gala' apples is highly controllable by post-harvest treatments and is therefore a good candidate to explore the use of PTBs. We find that the RandomForest model is more consistent than an ElasticNet model and is predictive of firmness (r2 = 0.78) with as few as 15 genes. We also show that qPCR is reasonably consistent with RNA-seq in a follow up experiment. Results are promising for PTBs, yet more work is needed to ensure that PTBs are robust across various environmental conditions and storage treatments.

Machine learning-based prediction of in-hospital mortality in patients with pneumonic chronic obstructive pulmonary disease exacerbations

OBJECTIVE

While linear regression and LASSO models have been established for predicting in-hospital mortality, there is currently no validated clinical prediction algorithm to predict in-hospital mortality for patients with chronic obstructive pulmonary disease (COPD) exacerbations using machine learning. Thus, we will evaluate the BAP-65 and CURB-65, and construct a novel prediction model using the random forest (RF) technique.

METHODS

A dataset of 1,418 patients with COPD exacerbations was collected. Age, gender, mental status, vital signs, and laboratory results were all taken into account for predictors. The categorical outcome variable was hospital-based mortality of people over 65 years. The dataset was divided randomly into a training dataset (70%) and a testing dataset (30%). We trained three prediction models, BAP-65, CURB-65, and the RF model, estimated the area under the receiver operating characteristic curve (AUROC) for the entire dataset. We also conducted a comparison of the AUROC values using the Delong test.

RESULTS

A total of 658 individuals with COPD acute exacerbations were enrolled. Our analysis using the receiver operating characteristic curve demonstrated that the RF model exhibited excellent performance, with an AUROC of 0.80 (95% confidence interval: 0.75-0.84). In comparison, the BAP-65 prediction model yielded an AUROC of 0.72 (0.68-0.75), while the CURB-65 prediction model achieved an AUROC of 0.69 (0.67-0.73).

CONCLUSIONS

The RF model demonstrated superior predictive capabilities than the BAP-65 and CURB-65 models in predicting in-hospital mortality. The results further highlighted significant factors for predicting in-hospital mortality, including blood eosinophil count, systolic blood pressure, and prior history of asthma.

Prediction of lymph node metastasis in advanced gastric adenocarcinoma based on dual-energy CT radiomics: focus on the features of lymph nodes with a short axis diameter ≥6 mm

Objective

To explore the value of the features of lymph nodes (LNs) with a short-axis diameter ≥6 mm in predicting lymph node metastasis (LNM) in advanced gastric adenocarcinoma (GAC) based on dual-energy CT (DECT) radiomics.

Materials and methods

Data of patients with GAC who underwent radical gastrectomy and LN dissection were retrospectively analyzed. To ensure the correspondence between imaging and pathology, metastatic LNs were only selected from patients with pN3, nonmetastatic LNs were selected from patients with pN0, and the short-axis diameters of the enrolled LNs were all ≥6 mm. The traditional features of LNs were recorded, including short-axis diameter, long-axis diameter, long-to-short-axis ratio, position, shape, density, edge, and the degree of enhancement; univariate and multivariate logistic regression analyses were used to establish a clinical model. Radiomics features at the maximum level of LNs were extracted in venous phase equivalent 120 kV linear fusion images and iodine maps. Intraclass correlation coefficients and the Boruta algorithm were used to screen significant features, and random forest was used to build a radiomics model. To construct a combined model, we included the traditional features with statistical significance in univariate analysis and radiomics scores (Rad-score) in multivariate logistic regression analysis. Receiver operating curve (ROC) curves and the DeLong test were used to evaluate and compare the diagnostic performance of the models. Decision curve analysis (DCA) was used to evaluate the clinical benefits of the models.

Results

This study included 114 metastatic LNs from 36 pN3 cases and 65 nonmetastatic LNs from 28 pN0 cases. The samples were divided into a training set (n=125) and a validation set (n=54) at a ratio of 7:3. Long-axis diameter and LN shape were independent predictors of LNM and were used to establish the clinical model; 27 screened radiomics features were used to build the radiomics model. LN shape and Rad-score were independent predictors of LNM and were used to construct the combined model. Both the radiomics model (area under the curve [AUC] of 0.986 and 0.984) and the combined model (AUC of 0.970 and 0.977) outperformed the clinical model (AUC of 0.772 and 0.820) in predicting LNM in both the training and validation sets. DCA showed superior clinical benefits from radiomics and combined models.

Conclusion

The models based on DECT LN radiomics features or combined traditional features have high diagnostic performance in determining the nature of each LN with a short-axis diameter of ≥6 mm in advanced GAC.

Mechanical Framework for Geopolymer Gels Construction: An Optimized LSTM Technique to Predict Compressive Strength of Fly Ash-Based Geopolymer Gels Concrete

As an environmentally responsible alternative to conventional concrete, geopolymer concrete recycles previously used resources to prepare the cementitious component of the product. The challenging issue with employing geopolymer concrete in the building business is the absence of a standard mix design. According to the chemical composition of its components, this work proposes a thorough system or framework for estimating the compressive strength of fly ash-based geopolymer concrete (FAGC). It could be possible to construct a system for predicting the compressive strength of FAGC using soft computing methods, thereby avoiding the requirement for time-consuming and expensive experimental tests. A complete database of 162 compressive strength datasets was gathered from the research papers that were published between the years 2000 and 2020 and prepared to develop proposed models. To address the relationships between inputs and output variables, long short-term memory networks were deployed. Notably, the proposed model was examined using several soft computing methods. The modeling process incorporated 17 variables that affect the CSFAG, such as percentage of SiO2 (SiO2), percentage of Na2O (Na2O), percentage of CaO (CaO), percentage of Al2O3 (Al2O3), percentage of Fe2O3 (Fe2O3), fly ash (FA), coarse aggregate (CAgg), fine aggregate (FAgg), Sodium Hydroxide solution (SH), Sodium Silicate solution (SS), extra water (EW), superplasticizer (SP), SH concentration, percentage of SiO2 in SS, percentage of Na2O in SS, curing time, curing temperature that the proposed model was examined to several soft computing methods such as multi-layer perception neural network (MLPNN), Bayesian regularized neural network (BRNN), generalized feed-forward neural networks (GFNN), support vector regression (SVR), decision tree (DT), random forest (RF), and LSTM. Three main innovations of this study are using the LSTM model for predicting FAGC, optimizing the LSTM model by a new evolutionary algorithm called the marine predators algorithm (MPA), and considering the six new inputs in the modeling process, such as aggregate to total mass ratio, fine aggregate to total aggregate mass ratio, FASiO2:Al2O3 molar ratio, FA SiO2:Fe2O3 molar ratio, AA Na2O:SiO2 molar ratio, and the sum of SiO2, Al2O3, and Fe2O3 percent in FA. The performance capacity of LSTM-MPA was evaluated with other artificial intelligence models. The results indicate that the R2 and RMSE values for the proposed LSTM-MPA model were as follows: MLPNN (R2 = 0.896, RMSE = 3.745), BRNN (R2 = 0.931, RMSE = 2.785), GFFNN (R2 = 0.926, RMSE = 2.926), SVR-L (R2 = 0.921, RMSE = 3.017), SVR-P (R2 = 0.920, RMSE = 3.291), SVR-S (R2 = 0.934, RMSE = 2.823), SVR-RBF (R2 = 0.916, RMSE = 3.114), DT (R2 = 0.934, RMSE = 2.711), RF (R2 = 0.938, RMSE = 2.892), LSTM (R2 = 0.9725, RMSE = 1.7816), LSTM-MPA (R2 = 0.9940, RMSE = 0.8332), and LSTM-PSO (R2 = 0.9804, RMSE = 1.5221). Therefore, the proposed LSTM-MPA model can be employed as a reliable and accurate model for predicting CSFAG. Noteworthy, the results demonstrated the significance and influence of fly ash and sodium silicate solution chemical compositions on the compressive strength of FAGC. These variables could adequately present variations in the best mix designs discovered in earlier investigations. The suggested approach may also save time and money by accurately estimating the compressive strength of FAGC with low calcium content.

Classification and clinical significance of immunogenic cell death-related genes in Plasmodium falciparum infection determined by integrated bioinformatics analysis and machine learning

BACKGROUND

Immunogenic cell death (ICD) is a type of regulated cell death that plays a crucial role in activating the immune system in response to various stressors, including cancer cells and pathogens. However, the involvement of ICD in the human immune response against malaria remains to be defined.

METHODS

In this study, data from Plasmodium falciparum infection cohorts, derived from cross-sectional studies, were analysed to identify ICD subtypes and their correlation with parasitaemia and immune responses. Using consensus clustering, ICD subtypes were identified, and their association with the immune landscape was assessed by employing ssGSEA. Differentially expressed genes (DEGs) analysis, functional enrichment, protein-protein interaction networks, and machine learning (least absolute shrinkage and selection operator (LASSO) regression and random forest) were used to identify ICD-associated hub genes linked with high parasitaemia. A nomogram visualizing these genes' correlation with parasitaemia levels was developed, and its performance was evaluated using receiver operating characteristic (ROC) curves.

RESULTS

In the P. falciparum infection cohort, two ICD-associated subtypes were identified, with subtype 1 showing better adaptive immune responses and lower parasitaemia compared to subtype 2. DEGs analysis revealed upregulation of proliferative signalling pathways, T-cell receptor signalling pathways and T-cell activation and differentiation in subtype 1, while subtype 2 exhibited elevated cytokine signalling and inflammatory responses. PPI network construction and machine learning identified CD3E and FCGR1A as candidate hub genes. A constructed nomogram integrating these genes demonstrated significant classification performance of high parasitaemia, which was evidenced by AUC values ranging from 0.695 to 0.737 in the training set and 0.911 to 0.933 and 0.759 to 0.849 in two validation sets, respectively. Additionally, significant correlations between the expressions of these genes and the clinical manifestation of P. falciparum infection were observed.

CONCLUSION

This study reveals the existence of two ICD subtypes in the human immune response against P. falciparum infection. Two ICD-associated candidate hub genes were identified, and a nomogram was constructed for the classification of high parasitaemia. This study can deepen the understanding of the human immune response to P. falciparum infection and provide new targets for the prevention and control of malaria.

Multilayer factors associated with excess all-cause mortality during the omicron and non-omicron waves of the COVID-19 pandemic: time series analysis in 29 countries

BACKGROUND

The COVID-19 pandemic has resulted in significant excess mortality globally. However, the differences in excess mortality between the Omicron and non-Omicron waves, as well as the contribution of local epidemiological characteristics, population immunity, and social factors to excess mortality, remain poorly understood. This study aims to solve the above problems.

METHODS

Weekly all-cause death data and covariates from 29 countries for the period 2015-2022 were collected and used. The Bayesian Structured Time Series Model predicted expected weekly deaths, stratified by gender and age groups for the period 2020-2022. The quantile-based g-computation approach accounted for the effects of factors on the excess all-cause mortality rate. Sensitivity analyses were conducted using alternative Omicron proportion thresholds.

RESULTS

From the first week of 2021 to the 30th week of 2022, the estimated cumulative number of excess deaths due to COVID-19 globally was nearly 1.39 million. The estimated weekly excess all-cause mortality rate in the 29 countries was approximately 2.17 per 100,000 (95% CI: 1.47 to 2.86). Weekly all-cause excess mortality rates were significantly higher in both male and female groups and all age groups during the non-Omicron wave, except for those younger than 15 years (P < 0.001). Sensitivity analysis confirmed the stability of the results. Positive associations with all-cause excess mortality were found for the constituent ratio of non-Omicron in all variants, new cases per million, positive rate, cardiovascular death rate, people fully vaccinated per hundred, extreme poverty, hospital patients per million humans, people vaccinated per hundred, and stringency index. Conversely, other factors demonstrated negative associations with all-cause excess mortality from the first week of 2021 to the 30th week of 2022.

CONCLUSION

Our findings indicate that the COVID-19 Omicron wave was associated with lower excess mortality compared to the non-Omicron wave. This study's analysis of the factors influencing excess deaths suggests that effective strategies to mitigate all-cause mortality include improving economic conditions, promoting widespread vaccination, and enhancing overall population health. Implementing these measures could significantly reduce the burden of COVID-19, facilitate coexistence with the virus, and potentially contribute to its elimination.

Data-driven modelling for assessing trophic status in marine ecosystems using machine learning approaches

Assessing eutrophication in coastal and transitional waters is of utmost importance, yet existing Trophic Status Index (TSI) models face challenges like multicollinearity, data redundancy, inappropriate aggregation methods, and complex classification schemes. To tackle these issues, we developed a novel tool that harnesses machine learning (ML) and artificial intelligence (AI), enhancing the reliability and accuracy of trophic status assessments. Our research introduces an improved data-driven methodology specifically tailored for transitional and coastal (TrC) waters, with a focus on Cork Harbour, Ireland, as a case study. Our innovative approach, named the Assessment Trophic Status Index (ATSI) model, comprises three main components: the selection of pertinent water quality indicators, the computation of ATSI scores, and the implementation of a new classification scheme. To optimize input data and minimize redundancy, we employed ML techniques, including advanced deep learning methods. Specifically, we developed a CHL prediction model utilizing ten algorithms, among which XGBoost demonstrated exceptional performance, showcasing minimal errors during both training (RMSE = 0.0, MSE = 0.0, MAE = 0.01) and testing (RMSE = 0.0, MSE = 0.0, MAE = 0.01) phases. Utilizing a novel linear rescaling interpolation function, we calculated ATSI scores and evaluated the model's sensitivity and efficiency across diverse application domains, employing metrics such as R2, the Nash-Sutcliffe efficiency (NSE), and the model efficiency factor (MEF). The results consistently revealed heightened sensitivity and efficiency across all application domains. Additionally, we introduced a brand new classification scheme for ranking the trophic status of transitional and coastal waters. To assess spatial sensitivity, we applied the ATSI model to four distinct waterbodies in Ireland, comparing trophic assessment outcomes with the Assessment of Trophic Status of Estuaries and Bays in Ireland (ATSEBI) System. Remarkably, significant disparities between the ATSI and ATSEBI System were evident in all domains, except for Mulroy Bay. Overall, our research significantly enhances the accuracy of trophic status assessments in marine ecosystems. The ATSI model, combined with cutting-edge ML techniques and our new classification scheme, represents a promising avenue for evaluating and monitoring trophic conditions in TrC waters. The study also demonstrated the effectiveness of ATSI in assessing trophic status across various waterbodies, including lakes, rivers, and more. These findings make substantial contributions to the field of marine ecosystem management and conservation.

Artificial Intelligence-Based Anomaly Detection Technology over Encrypted Traffic: A Systematic Literature Review

As cyber-attacks increase in unencrypted communication environments such as the traditional Internet, protected communication channels based on cryptographic protocols, such as transport layer security (TLS), have been introduced to the Internet. Accordingly, attackers have been carrying out cyber-attacks by hiding themselves in protected communication channels. However, the nature of channels protected by cryptographic protocols makes it difficult to distinguish between normal and malicious network traffic behaviors. This means that traditional anomaly detection models with features from packets extracted a deep packet inspection (DPI) have been neutralized. Recently, studies on anomaly detection using artificial intelligence (AI) and statistical characteristics of traffic have been proposed as an alternative. In this review, we provide a systematic review for AI-based anomaly detection techniques over encrypted traffic. We set several research questions on the review topic and collected research according to eligibility criteria. Through the screening process and quality assessment, 30 research articles were selected with high suitability to be included in the review from the collected literature. We reviewed the selected research in terms of dataset, feature extraction, feature selection, preprocessing, anomaly detection algorithm, and performance indicators. As a result of the literature review, it was confirmed that various techniques used for AI-based anomaly detection over encrypted traffic were used. Some techniques are similar to those used for AI-based anomaly detection over unencrypted traffic, but some technologies are different from those used for unencrypted traffic.

Predictive modeling for acute kidney injury after percutaneous coronary intervention in patients with acute coronary syndrome: a machine learning approach

BACKGROUND

Acute kidney injury (AKI) is one of the preventable complications of percutaneous coronary intervention (PCI). This study aimed to develop machine learning (ML) models to predict AKI after PCI in patients with acute coronary syndrome (ACS).

METHODS

This study was conducted at Tehran Heart Center from 2015 to 2020. Several variables were used to design five ML models: Naïve Bayes (NB), Logistic Regression (LR), CatBoost (CB), Multi-layer Perception (MLP), and Random Forest (RF). Feature importance was evaluated with the RF model, CB model, and LR coefficients while SHAP beeswarm plots based on the CB model were also used for deriving the importance of variables in the population using pre-procedural variables and all variables. Sensitivity, specificity, and the area under the receiver operating characteristics curve (ROC-AUC) were used as the evaluation measures.

RESULTS

A total of 4592 patients were included, and 646 (14.1%) experienced AKI. The train data consisted of 3672 and the test data included 920 cases. The patient population had a mean age of 65.6 ± 11.2 years and 73.1% male predominance. Notably, left ventricular ejection fraction (LVEF) and fasting plasma glucose (FPG) had the highest feature importance when training the RF model on only pre-procedural features. SHAP plots for all features demonstrated LVEF and age as the top features. With pre-procedural variables only, CB had the highest AUC for the prediction of AKI (AUC 0.755, 95% CI 0.713 to 0.797), while RF had the highest sensitivity (75.9%) and MLP had the highest specificity (64.35%). However, when considering pre-procedural, procedural, and post-procedural features, RF outperformed other models (AUC: 0.775). In this analysis, CB achieved the highest sensitivity (82.95%) and NB had the highest specificity (82.93%).

CONCLUSION

Our analyses showed that ML models can predict AKI with acceptable performance. This has potential clinical utility for assessing the individualized risk of AKI in ACS patients undergoing PCI. Additionally, the identified features in the models may aid in mitigating these risk factors.

CT-based radiomics signature for differentiating pyelocaliceal upper urinary tract urothelial carcinoma from infiltrative renal cell carcinoma

Objectives

To develop a CT-based radiomics model and a combined model for preoperatively discriminating infiltrative renal cell carcinoma (RCC) and pyelocaliceal upper urinary tract urothelial carcinoma (UTUC), which invades the renal parenchyma.

Materials and methods

Eighty patients (37 pathologically proven infiltrative RCCs and 43 pathologically proven pyelocaliceal UTUCs) were retrospectively enrolled and randomly divided into a training set (n = 56) and a testing set (n = 24) at a ratio of 7:3. Traditional CT imaging characteristics in the portal venous phase were collected by two radiologists (SPH and ZXL, who have 4 and 30 years of experience in abdominal radiology, respectively). Patient demographics and traditional CT imaging characteristics were used to construct the clinical model. The radiomics score was calculated based on the radiomics features extracted from the portal venous CT images and the random forest (RF) algorithm to construct the radiomics model. The combined model was constructed using the radiomics score and significant clinical factors according to the multivariate logistic regression. The diagnostic efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC).

Results

The RF score based on the eight validated features extracted from the portal venous CT images was used to build the radiomics model. Painless hematuria as an independent risk factor was used to build the clinical model. The combined model was constructed using the RF score and the selected clinical factor. Both the radiomics model and combined model showed higher efficacy in differentiating infiltrative RCC and pyelocaliceal UTUC in the training and testing cohorts with AUC values of 0.95 and 0.90, respectively, for the radiomics model and 0.99 and 0.90, respectively, for the combined model. The decision curves of the combined model as well as the radiomics model indicated an overall net benefit over the clinical model. Both the radiomics model and the combined model achieved a notable reduction in false-positive and false-negativerates, resulting in significantly higher accuracy compared to the visual assessments in both the training and testing cohorts.

Conclusion

The radiomics model and combined model had the potential to accurately differentiate infiltrative RCC and pyelocaliceal UTUC, which invades the renal parenchyma, and provide a new potentially non-invasive method to guide surgery strategies.

Dimensions management of traffic big data for short-term traffic prediction on suburban roadways

Since intelligent systems were developed to collect traffic data, this data can be collected at high volume, velocity, and variety, resulting in big traffic data. In previous studies, dealing with the large volume of big traffic data has always been discussed. In this study, big traffic data were used to predict traffic state on a section of suburban road from Karaj to Chalous located in the north of Iran. Due to the many and various extracted features, data dimensions management is necessary. This management was accomplished using principal component analysis to reduce the number of features, genetic algorithms to select features influencing traffic states, and cyclic features to change the nature of features. The data set obtained from each method is used as input to the models. The models used include long short-term memory, support vector machine, and random forest. The results show that using cyclic features can increase traffic state prediction's accuracy than the model, including all the initial features (base model). Long short-term memory model with 71 cyclic features offers the highest accuracy, equivalent to 88.09%. Additionally, this model's reduced number of features led to a shorter modelling execution time, from 456 s (base model) to 201 s.

Synergizing Machine Learning Algorithm with Triboelectric Nanogenerators for Advanced Self-Powered Sensing Systems

The advancement of the Internet of Things (IoT) has increased the demand for large-scale intelligent sensing systems. The periodic replacement of power sources for ubiquitous sensing systems leads to significant resource waste and environmental pollution. Human staffing costs associated with replacement also increase the economic burden. The triboelectric nanogenerators (TENGs) provide both an energy harvesting scheme and the possibility of self-powered sensing. Based on contact electrification from different materials, TENGs provide a rich material selection to collect complex and diverse data. As the data collected by TENGs become increasingly numerous and complex, different approaches to machine learning (ML) and deep learning (DL) algorithms have been proposed to efficiently process output signals. In this paper, the latest advances in ML algorithms assisting solid-solid TENG and liquid-solid TENG sensors are reviewed based on the sample size and complexity of the data. The pros and cons of various algorithms are analyzed and application scenarios of various TENG sensing systems are presented. The prospects of synergizing hardware (TENG sensors) with software (ML algorithms) in a complex environment and their main challenges for future developments are discussed.

Modeling based on machine learning to investigate flue gas desulfurization performance by calcium silicate absorbent in a sand bed reactor

Flue gas desulfurization (FGD) is a critical process for reducing sulfur dioxide (SO2) emissions from industrial sources, particularly power plants. This research uses calcium silicate absorbent in combination with machine learning (ML) to predict SO2 concentration within an FGD process. The collected dataset encompasses four input parameters, specifically relative humidity, absorbent weight, temperature, and time, and incorporates one output parameter, which pertains to the concentration of SO2. Six ML models were developed to estimate the output parameters. Statistical metrics such as the coefficient of determination (R2) and mean squared error (MSE) were employed to identify the most suitable model and assess its fitting effectiveness. The random forest (RF) model emerged as the top-performing model, boasting an R2 of 0.9902 and an MSE of 0.0008. The model's predictions aligned closely with experimental results, confirming its high accuracy. The most suitable hyperparameter values for RF model were found to be 74 for n_estimators, 41 for max_depth, false for bootstrap, sqrt for max_features, 1 for min_samples_leaf, absolute_error for criterion, and 3 for min_samples_split. Three-dimensional surface plots were generated to explore the impact of input variables on SO2 concentration. Global sensitivity analysis (GSA) revealed absorbent weight and time significantly influence SO2 concentration. The integration of ML into FGD modeling offers a novel approach to optimizing the efficiency and effectiveness of this environmentally crucial process.

An AI-based novel system for predicting respiratory support in COVID-19 patients through CT imaging analysis

The proposed AI-based diagnostic system aims to predict the respiratory support required for COVID-19 patients by analyzing the correlation between COVID-19 lesions and the level of respiratory support provided to the patients. Computed tomography (CT) imaging will be used to analyze the three levels of respiratory support received by the patient: Level 0 (minimum support), Level 1 (non-invasive support such as soft oxygen), and Level 2 (invasive support such as mechanical ventilation). The system will begin by segmenting the COVID-19 lesions from the CT images and creating an appearance model for each lesion using a 2D, rotation-invariant, Markov-Gibbs random field (MGRF) model. Three MGRF-based models will be created, one for each level of respiratory support. This suggests that the system will be able to differentiate between different levels of severity in COVID-19 patients. The system will decide for each patient using a neural network-based fusion system, which combines the estimates of the Gibbs energy from the three MGRF-based models. The proposed system were assessed using 307 COVID-19-infected patients, achieving an accuracy of [Formula: see text], a sensitivity of [Formula: see text], and a specificity of [Formula: see text], indicating a high level of prediction accuracy.

Precise prediction of metabolites patterns using machine learning approaches in distinguishing honey and sugar diets fed to mice

As a natural sweetener produced by honey bees, honey was recognized as being healthier for consumption than table sugar. Our previous study also indicated thatmetaboliteprofiles in mice fed honey and mixedsugardiets aredifferent. However, it is still noteworthy about the batch-to-batch consistency of the metabolic differences between two diet types. Here, the machine learning (ML) algorithms were applied to complement and calibrate HPLC-QTOF/MS-based untargeted metabolomics data. Data were generated from three batches of mice that had the same treatment, which can further mine the metabolite biomarkers. Random Forest and Extra-Trees models could better discriminate between honey and mixed sugar dietary patterns under five-fold cross-validation. Finally, SHapley Additive exPlanations tool identified phosphatidylethanolamine and phosphatidylcholine as reliable metabolic biomarkers to discriminate the honey diet from the mixed sugar diet. This study provides us new ideas for metabolomic analysis of larger data sets.

Exploration of the pathophysiology of high myopia via proteomic profiling of human corneal stromal lenticules

This study aimed to investigate the underlying pathophysiology of high myopia by analyzing the proteome of human corneal stromal lenticule samples obtained through small incision lenticule extraction (SMILE). A total of thirty-two patients who underwent SMILE were included in the study. Label-free quantitative proteomic analysis was performed on corneal stromal lenticule samples, equally representing high myopia (n = 10) and low myopia (n = 10) groups. The identified and profiled lenticule proteomes were analyzed using in silico tools to explore biological characteristics of differentially expressed proteins (DEPs). Additionally, LASSO regression and random forest model were employed to identify key proteins associated with the pathophysiology of high myopia. The DEPs were found to be closely linked to immune activation, extracellular matrix, and cell adhesion-related pathways according to gene ontology analysis. Specifically, decreased expression of COL1A1 and increased expression of CDH11 were associated with the pathogenesis of high myopia and validated by western blotting (n = 6) and quantitative real time polymerase chain reaction (n = 6). Overall, this study provides evidence that COL1A1 and CDH11 may contribute to the pathophysiology of high myopia based on comparative proteomic profiling of human corneal stromal lenticules obtained through SMILE.

Instantaneous CO2 emission modelling for a Euro 6 start-stop vehicle based on portable emission measurement system data and artificial intelligence methods

One of the increasingly common methods to counteract the increased fuel consumption of vehicles is start-stop technology. This paper introduces a methodology which presents the process of measuring and creating a computational model of CO2 emissions using artificial intelligence techniques for a vehicle equipped with start-stop technology. The method requires only measurement data of velocity, acceleration of vehicle, and gradient of road to predict the emission of CO2. In this paper, three methods of machine learning techniques were analyzed, while the best prediction results are shown by the gradient boosting method. For the developed models, the results were validated using the coefficient of determination, the mean squared error, and based on visual evaluation of residual and instantaneous emission plots and CO2 emission maps. The developed models present a novel methodology and can be used for microscale environmental analysis.

Nitrogen regulates the synthesis of hydrophobic amino acids to improve protein structural and gel properties in common buckwheat

Nitrogen (N) fertilizer impacts the grain quality of common buckwheat, but the effects and regulatory mechanisms of N on various protein parameters of buckwheat are not fully understood. The purpose of this study was to investigate the particle morphology, structural and gel properties, and regulation mechanism of buckwheat protein under four N levels. The bulk density, surface hydrophobicity, particle size, and thermal properties of the buckwheat protein were maximized through the optimal N application (180 kg N/ha), further enhancing the thermal stability of the protein. N application increased the β-sheet content and reduced the random coil content. Appropriate N fertilizer input enhanced the tertiary structure stability and gel elasticity of buckwheat protein by promoting hydrophobic interactions, disulfide bonds, ionic bonds, storage modulus and loss modulus. The differentially expressed proteins induced by N are primarily enriched in small ribosomal subunit and ribosome, improving protein quality mainly by promoting the synthesis of hydrophobic amino acids. Future agriculture should pay attention to the hydrophobic amino acid content of buckwheat to effectively improve protein quality. This study further advances the application of buckwheat protein in the field of food processing and provides a theoretical basis for the extensive development and utilization of buckwheat protein.

Nitrate prediction in groundwater of data scarce regions: The futuristic fresh-water management outlook

Nitrate contamination in groundwater poses a significant threat to water quality and public health, especially in regions with limited data availability. This study addresses this challenge by employing machine learning (ML) techniques to predict nitrate (NO3--N) concentrations in Mexico's groundwater. Four ML algorithms-Extreme Gradient Boosting (XGB), Boosted Regression Trees (BRT), Random Forest (RF), and Support Vector Machines (SVM)-were executed to model NO3--N concentrations across the country. Despite data limitations, the ML models achieved robust predictive performances. XGB and BRT algorithms demonstrated superior accuracy (0.80 and 0.78, respectively). Notably, this was achieved using ∼10 times less information than previous large-scale assessments. The novelty lies in the first-ever implementation of the 'Support Points-based Split Approach' during data pre-processing. The models considered initially 68 covariates and identified 13-19 significant predictors of NO3--N concentration spanning from climate, geomorphology, soil, hydrogeology, and human factors. Rainfall, elevation, and slope emerged as key predictors. A validation incorporated nationwide waste disposal sites, yielding an encouraging correlation. Spatial risk mapping unveiled significant pollution hotspots across Mexico. Regions with elevated NO3--N concentrations (>10 mg/L) were identified, particularly in the north-central and northeast parts of the country, associated with agricultural and industrial activities. Approximately 21 million people, accounting for 10 % of Mexico's population, are potentially exposed to elevated NO3--N levels in groundwater. Moreover, the NO3--N hotspots align with reported NO3--N health implications such as gastric and colorectal cancer. This study not only demonstrates the potential of ML in data-scarce regions but also offers actionable insights for policy and management strategies. Our research underscores the urgency of implementing sustainable agricultural practices and comprehensive domestic waste management measures to mitigate NO3--N contamination. Moreover, it advocates for the establishment of effective policies based on real-time monitoring and collaboration among stakeholders.

Untangling fuel, weather and management effects on fire severity: Insights from large-sample LiDAR remote sensing analysis of conditions preceding the 2019-20 Australian wildfires

Evaluation of fire severity reduction strategies requires the quantification of intervention outcomes and, more broadly, the extent to which fuel characteristics affect fire severity. However, investigations are currently limited by the availability of accurate data on fire severity predictors, particularly relating to fuel. Here, we used airborne LiDAR data collected before the 2019-20 Australian Black Summer fires to investigate the contribution of fuel structure to fire severity under a range of weather conditions. Fire severity was estimated using the Relative Burn Ratio calculated from Sentinel-2 optical remote sensing imagery. We modelled the effects of various fuel structure estimates and other environmental predictors using Random Forest models. In addition to variables estimated at each observation point, we investigated the influence of surrounding landscape characteristics using an innovative method to estimate fireline progression direction. Our models explained 63-76% of fire severity variance using parsimonious predictor sets. Fuel cover in the understorey and canopy, and vertical vegetation heterogeneity, were positively associated with fire severity. Up-fire burnt area and recent planned and unplanned fire reduced fire severity, whereby unplanned fire provided a longer-lasting reduction of fire severity (up to 15 years) than planned fire (up to 10 years). Although fuel structure and land management effects were important predictors, weather and canopy height effects were dominant. By mapping continuous interactions between weather and fuel-related variables, we found strong evidence of diminishing fuel effects below 20-40% relative air humidity. While our findings suggest that land management interventions can provide meaningful fire severity reduction, they also highlight the risk of warmer and drier future climates constraining these advantages.

Automated machine learning-based model for predicting benign anastomotic strictures in patients with rectal cancer who have received anterior resection

BACKGROUND

Benign anastomotic strictures (BAS) significantly impact patients' quality of life and long-term prognosis. However, the current clinical practice lacks accurate tools for predicting BAS. This study aimed to develop a machine-learning model to predict BAS in patients with rectal cancer who have undergone anterior resection.

METHODS

Data from 1973 patients who underwent anterior resection for rectal cancer were collected. Multiple machine learning classification models were integrated to analyze the data and identify the optimal model. Model performance was evaluated using receiver operator characteristic (ROC) curves, decision curve analysis (DCA), and calibration curves. The Shapley Additive exPlanation (SHAP) algorithm was utilized to assess the impact of various clinical characteristics on the optimal model to enhance the interpretability of the model results.

RESULTS

A total of 10 clinical features were considered in constructing the machine learning model. The model evaluation results indicated that the random forest (RF)model was optimal, with the area under the test set curve (AUC: 0.888, 95% CI: 0.810-0.965), accuracy: 0.792, sensitivity: 0.846, specificity: 0.791. The SHAP algorithm analysis identified prophylactic ileostomy, operative time, and anastomotic leakage as significant contributing factors influencing the predictions of the RF model.

CONCLUSION

We developed a robust machine-learning model and user-friendly online prediction tool for predicting BAS following anterior resection of rectal cancer. This tool offers a potential foundation for BAS prevention and aids clinical practice by enabling more efficient disease management and precise medical interventions.