Develop Machine Learning Algorithms Research Articles

Enhanced Estimate of Chromophoric Dissolved Organic Matter Using Machine Learning Algorithms from Landsat-8 OLI Data in the Pearl River Estuary

Chromophoric Dissolved Organic Matter (CDOM) plays a critical role in the carbon and biogeochemical cycles within aquatic ecosystems. Satellite imagery can be employed to determine aquatic CDOM concentrations, highlighting the need for effective and precise algorithms for this task. In this study, a cruise survey dataset containing CDOM absorption coefficients and water-leaving radiances in the Pearl River estuary (PRE) was utilized to develop machine learning algorithms for CDOM retrieval from Landsat-8 Operational Land Imager (OLI) observations. Based on OLI wavelength bands, five bands and six band-ratios were chosen as input parameters for the machine learning models. Six machine learning models were trained to develop CDOM algorithms, including Support Vector Regression (SVR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN). The results indicated that, among the six machine learning models, the XGBoost algorithm performed best, with the highest R2 value of 0.9 and the lowest CDOM root mean square error (RMSE) of 0.37 m−1, outperforming empirical algorithms. The XGBoost algorithm identified B4/B1 as the most critical input parameter, contributing 71%, followed by B3/B2 with a 16% contribution, where B1, B2, B3, and B4 are the wavelength bands of the OLI. These two band-ratios accounted for most of the contributions, suggesting their significant role in CDOM retrieval from Landsat OLI images. By employing the developed XGBoost algorithm, CDOM spatial patterns at six instances were derived from Landsat-8 OLI image reflectance, illustrating CDOM variations in the PRE influenced by various factors. Further analysis revealed that, in the PRE, tides and winds are the primary driving forces behind the spatial and temporal variability of CDOM. At present, the exploration of employing machine learning algorithms to infer CDOM concentrations in this region remains relatively limited; therefore, with a higher R2 value, the machine learning model we established unveils fresh and novel results.

Barium stars as tracers ofs-process nucleosynthesis in AGB stars

Context.Barium (Ba) stars are characterised by an abundance of heavy elements made by the slow neutron capture process (s-process). This peculiar observed signature is due to the mass transfer from a stellar companion, bound in a binary stellar system, to the Ba star observed today. The signature is created when the stellar companion is an asymptotic giant branch (AGB) star.Aims.We aim to analyse the abundance pattern of 169 Ba stars using machine learning techniques and the AGB final surface abundances predicted by the FRUITYand Monash stellar models.Methods.We developed machine learning algorithms that use the abundance pattern of Ba stars as input to classify the initial mass and metallicity of each Ba star’s companion star using stellar model predictions. We used two algorithms. The first exploits neural networks to recognise patterns, and the second is a nearest-neighbour algorithm that focuses on finding the AGB model that predicts the final surface abundances closest to the observed Ba star values. In the second algorithm, we included the error bars and observational uncertainties in order to find the best-fit model. The classification process was based on the abundances of Fe, Rb, Sr, Zr, Ru, Nd, Ce, Sm, and Eu. We selected these elements by systematically removings-process elements from our AGB model abundance distributions and identifying the elements whose removal had the biggest positive effect on the classification. We excluded Nb, Y, Mo, and La. Our final classification combined the output of both algorithms to identify an initial mass and metallicity range for each Ba star companion.Results.With our analysis tools, we identified the main properties for 166 of the 169 Ba stars in the stellar sample. The classifications based on both stellar sets of AGB final abundances show similar distributions, with an average initial mass ofM= 2.23M⊙and 2.34M⊙and an average [Fe/H] = −0.21 and −0.11, respectively. We investigated why the removal of Nb, Y, Mo, and La improves our classification and identified 43 stars for which the exclusion had the biggest effect. We found that these stars have statistically significant and different abundances for these elements compared to the other Ba stars in our sample. We discuss the possible reasons for these differences in the abundance patterns.

A review and comparative study of cancer detection using machine learning: SBERT and SimCSE application

BackgroundUsing visual, biological, and electronic health records data as the sole input source, pretrained convolutional neural networks and conventional machine learning methods have been heavily employed for the identification of various malignancies. Initially, a series of preprocessing steps and image segmentation steps are performed to extract region of interest features from noisy features. Then, the extracted features are applied to several machine learning and deep learning methods for the detection of cancer.MethodsIn this work, a review of all the methods that have been applied to develop machine learning algorithms that detect cancer is provided. With more than 100 types of cancer, this study only examines research on the four most common and prevalent cancers worldwide: lung, breast, prostate, and colorectal cancer. Next, by using state-of-the-art sentence transformers namely: SBERT (2019) and the unsupervised SimCSE (2021), this study proposes a new methodology for detecting cancer. This method requires raw DNA sequences of matched tumor/normal pair as the only input. The learnt DNA representations retrieved from SBERT and SimCSE will then be sent to machine learning algorithms (XGBoost, Random Forest, LightGBM, and CNNs) for classification. As far as we are aware, SBERT and SimCSE transformers have not been applied to represent DNA sequences in cancer detection settings.ResultsThe XGBoost model, which had the highest overall accuracy of 73 ± 0.13 % using SBERT embeddings and 75 ± 0.12 % using SimCSE embeddings, was the best performing classifier. In light of these findings, it can be concluded that incorporating sentence representations from SimCSE’s sentence transformer only marginally improved the performance of machine learning models.

Machine learning to predict major bleeding during anticoagulation for venous thromboembolism: possibilities and limitations.

Predictive tools for major bleeding (MB) using machine learning (ML) might be advantageous over traditional methods. We used data from the Registro Informatizado de Enfermedad TromboEmbólica (RIETE) to develop ML algorithms to identify patients with venous thromboembolism (VTE) at increased risk of MB during the first 3 months of anticoagulation. A total of 55 baseline variables were used as predictors. New data prospectively collected from the RIETE were used for further validation. The RIETE and VTE-BLEED scores were used for comparisons. External validation was performed with the COMMAND-VTE database. Learning was carried out with data from 49 587 patients, of whom 873 (1.8%) had MB. The best performing ML method was XGBoost. In the prospective validation cohort the sensitivity, specificity, positive predictive value and F1 score were: 33.2%, 93%, 10%, and 15.4% respectively. F1 value for the RIETE and VTE-BLEED scores were 8.6% and 6.4% respectively. In the external validation cohort the metrics were 10.3%, 87.6%, 3.5% and 5.2% respectively. In that cohort, the F1 value for the RIETE score was 17.3% and for the VTE-BLEED score 9.75%. The performance of the XGBoost algorithm was better than that from the RIETE and VTE-BLEED scores only in the prospective validation cohort, but not in the external validation cohort.

Meta-analysis of engineered nanoparticles dynamic aggregation in freshwater-like systems using machine learning techniques

Predictive algorithms for exposure characterization of engineered nanoparticles (ENPs) in the ecosystems are essential to improve the development of robust nano-safety frameworks. Here, machine learning (ML) techniques were utilised for data mining and prediction of the dynamic aggregation transformation process in aqueous environments using case studies of nZnO and nTiO2. Supervised ML models using input variables of natural organic matter, ionic strength, size, and ENPs concentration showed poor prediction performance based on statistical metric values of root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and Nash-Sutcliffe efficiency (NSE) for both types of ENP. On the contrary, algorithms developed using model input parameters of zeta potential, pH, and time had good generalisation and high prediction accuracy. Among the five developed ML algorithms, random forest regression, support vector regression, and artificial neural network generated good prediction accuracy for both data sets. Therefore, the use of ML can be valuable in the development of robust nano-safety frameworks to optimise societal benefits, and for proactive long-term ecological protection.

Advanced analysis of internal quantum efficiency measurements using machine learning

AbstractThe internal quantum efficiency (IQE) is given as the ratio between the externally collected electron current and the photon current absorbed by the device. Spectral analysis of IQE measurements is a powerful method to identify performance‐limiting mechanisms in solar cells. It also enables the extraction of key electrical and optical parameters. However, the potential of IQE measurements is only rarely fully utilized, presumably due to the significant complexity associated with the fitting process and its sensitivity to noise. In this study, machine learning is proposed as an efficient method to extract quantitative information from IQE measurements. The extraction method is automated and easy to use, providing an array of specific device parameters. By simplifying the analytical process, the developed machine learning algorithms also extract the parasitic absorption of the antireflection coating, a key parameter that is difficult to obtain by traditional methods. Although the method has been developed for and tested on silicon solar cells, it can be adapted and applied to other types of solar cells.

Paper 19: Evidence-Based Machine Learning Algorithm to Predict Failure Following Cartilage Preservation Procedures in the Knee

Objectives: To develop machine learning algorithms to predict failure of surgical procedures that address cartilage defects of the knee and detect the most valuable variables associated with failure. Methods: A single institution prospectively collected database of cartilage procedures was queried for procedures performed between 2000 and 2018. Failure was defined as revision cartilage surgery and/or knee arthroplasty. One hundred and one preoperative and intraoperative features were evaluated as potential predictors. The dataset was randomly divided into training (70%) and independent testing (30%) sets. Four machine learning algorithms were trained and internally validated. Algorithm performance was assessed using area under curve (AUC) and the Brier score. Local Interpretable Model-agnostic Explanations (LIME) was utilized to assess the optimized algorithm fidelity. Results: A total of 1091 patients who underwent surgical procedures addressing cartilage defects in the knee with a minimum of 2-years of follow-up were included. The mean follow-up was 3.5 ± 2.8 years. The mean age was 40.5 ± 15 years. There were 205 (18.8%) patients who failed at final follow-up. The Random Forest algorithm was found to be the best performing algorithm, with an AUC of 0.765 and a Brier score of 0.135. The 10 most important features for predicting failure following surgical procedures addressing cartilage defects of the knee were: symptom duration, age, body mass index (BMI), lesion grade, total lesion area (sum of all lesion areas), number of previous surgeries, number of lesions in the knee, gender, athletic level, and traumatic etiology. LIME analysis allowed for assessment of the optimized algorithm fidelity, as well as provided a patient-specific comparison for the risk of failure of an individual patient being assigned various types of cartilage procedures. Conclusions: Machine learning algorithms were accurate in predicting the risk of failure following cartilage procedures of the knee, with the most important features being symptom duration, age, BMI, lesion grade, and total lesion area. Machine learning algorithms may be used to compare the risk of failure of specific patient-procedure combinations in the treatment of cartilage defects of the knee. Integrated human and machine learning decision-making may improve patient selection and bring about the new era of patient-tailored evidence-based clinical care. [Table: see text][Table: see text][Figure: see text][Figure: see text]

Predicting gene knockout effects from expression data

BackgroundThe study of gene essentiality, which measures the importance of a gene for cell division and survival, is used for the identification of cancer drug targets and understanding of tissue-specific manifestation of genetic conditions. In this work, we analyze essentiality and gene expression data from over 900 cancer lines from the DepMap project to create predictive models of gene essentiality.MethodsWe developed machine learning algorithms to identify those genes whose essentiality levels are explained by the expression of a small set of “modifier genes”. To identify these gene sets, we developed an ensemble of statistical tests capturing linear and non-linear dependencies. We trained several regression models predicting the essentiality of each target gene, and used an automated model selection procedure to identify the optimal model and hyperparameters. Overall, we examined linear models, gradient boosted trees, Gaussian process regression models, and deep learning networks.ResultsWe identified nearly 3000 genes for which we accurately predict essentiality using gene expression data of a small set of modifier genes. We show that both in the number of genes we successfully make predictions for, as well as in the prediction accuracy, our model outperforms current state-of-the-art works.ConclusionsOur modeling framework avoids overfitting by identifying the small set of modifier genes, which are of clinical and genetic importance, and ignores the expression of noisy and irrelevant genes. Doing so improves the accuracy of essentiality prediction in various conditions and provides interpretable models. Overall, we present an accurate computational approach, as well as interpretable modeling of essentiality in a wide range of cellular conditions, thus contributing to a better understanding of the molecular mechanisms that govern tissue-specific effects of genetic disease and cancer.

A multi-objective evolutionary algorithm with decomposition and the information feedback for high-dimensional medical data

High-dimensional medical data often leads to a phenomenon known as the ”curse of dimensionality,” which causes additional memory and high training costs, as well as degrading the generalization capacity of learning algorithms. To address this issue, a multi-objective evolutionary algorithm that integrates decomposition and the information feedback model (IFMMOEAD) is proposed for high-dimensional medical data. This algorithm not only considers the number of selected features, but also classification accuracy and correlation measures of features when feature dimensionality reduction is executed. The property of IFMMOEAD is first verified by standard benchmarks DTLZ1–DTLZ7. Then, it is used to develop machine learning algorithms for thirty-five high-dimensional cancer gene expression data sets, showing excellent potential for high-dimensional medical machine learning. Finally, the IFMMOEAD is applied to empirical clinical data of multiple myeloma, significantly outperforming existing algorithms in terms of normalized mutual information and adjusted rand index metrics. We suggest that this algorithm could be implemented in medical information systems as a promising technique for high-dimensional medical problems.

A Neural Network Model Using Pain Score Patterns to Predict the Need for Outpatient Opioid Refills Following Ambulatory Surgery: Algorithm Development and Validation.

Expansion of clinical guidance tools is crucial to identify patients at risk of requiring an opioid refill after outpatient surgery. The objective of this study was to develop machine learning algorithms incorporating pain and opioid features to predict the need for outpatient opioid refills following ambulatory surgery. Neural networks, regression, random forest, and a support vector machine were used to evaluate the data set. For each model, oversampling and undersampling techniques were implemented to balance the data set. Hyperparameter tuning based on k-fold cross-validation was performed, and feature importance was ranked based on a Shapley Additive Explanations (SHAP) explainer model. To assess performance, we calculated the average area under the receiver operating characteristics curve (AUC), F1-score, sensitivity, and specificity for each model. There were 1333 patients, of whom 144 (10.8%) refilled their opioid prescription within 2 weeks after outpatient surgery. The average AUC calculated from k-fold cross-validation was 0.71 for the neural network model. When the model was validated on the test set, the AUC was 0.75. The features with the highest impact on model output were performance of a regional nerve block, postanesthesia care unit maximum pain score, postanesthesia care unit median pain score, active smoking history, and total perioperative opioid consumption. Applying machine learning algorithms allows providers to better predict outcomes that require specialized health care resources such as transitional pain clinics. This model can aid as a clinical decision support for early identification of at-risk patients who may benefit from transitional pain clinic care perioperatively in ambulatory surgery.

Machine learning for longitudinal mortality risk prediction in patients with malignant neoplasm in São Paulo, Brazil

Artificial intelligence is becoming an important diagnostic and prognostic tool in recent years, as machine learning algorithms have been shown to improve clinical decision-making. These algorithms will have some of their most important applications in developing regions with restricted data collection, but their performance under this condition is still widely unknown. We analyzed longitudinal data from São Paulo, Brazil, to develop machine learning algorithms to predict the risk of death in patients with cancer. We tested different algorithms using nine separate model structures. Considering the area under the ROC curve (AUC-ROC), we obtained values of 0.946 for the general model, 0.945 for the model with the five main cancers, 0.899 for bronchial and lung cancer, 0.947 for breast cancer, 0.866 for stomach cancer, 0.872 for colon cancer, 0.923 for rectum cancer, 0.955 for prostate cancer, and 0.917 for uterine cervix cancer. Our results indicate the potential of building models for predicting mortality risk in cancer patients in developing regions using only routinely-collected data.

An automatic sleep-scoring system in elderly women with osteoporosis fractures using frequency localized finite orthogonal quadrature Fejer Korovkin kernels.

Healthy sleep signifies a good physical and mental state of the body. However, factors such as inappropriate work schedules, medical complications, and others can make it difficult to get enough sleep, leading to various sleep disorders. The identification of these disorders requires sleep stage classification. Visual evaluation of sleep stages is time intensive, placing a significant strain on sleep experts and prone to human errors. As a result, it is crucial to develop machine learning algorithms to score sleep stages to acquire an accurate diagnosis. Hence, a new methodology for automated sleep stage classification is suggested using machine learning and filtering electroencephalogram (EEG) signals. The national sleep research resource's (NSRR) study of osteoporotic fractures (SOF) dataset comprising 453 subjects' polysomnograph (PSG) data is used in this study. Only two unipolar EEG derivations C4-A1 and C3-A2 are employed individually and jointly in this work. The EEG signals are decomposed into sub-bands using a frequency-localized finite orthogonal quadrature Fejer Korovkin wavelet filter bank. The wavelet-based entropy features are extracted from sub-bands. Subsequently, extracted features are classified using machine learning techniques. Our developed model obtained the highest classification accuracy of 81.3%, using an ensembled bagged trees classifier with a 10-fold cross-validation method and Cohen's Kappa coefficient of 0.72. The proposed model is accurate, dependable, and easy to implement and can be employed as an alternative to a PSG-based system at home with minimal resources. It is also ready to be tested on other EEG data to evaluate the sleep stages of healthy and unhealthy subjects.

A Machine Learning-Based Online Prediction Tool for Predicting Short-Term Postoperative Outcomes Following Spinal Tumor Resections.

Background: Preoperative prediction of short-term postoperative outcomes in spinal tumor patients can lead to more precise patient care plans that reduce the likelihood of negative outcomes. With this study, we aimed to develop machine learning algorithms for predicting short-term postoperative outcomes and implement these models in an open-source web application. Methods: Patients who underwent surgical resection of spinal tumors were identified using the American College of Surgeons, National Surgical Quality Improvement Program. Three outcomes were predicted: prolonged length of stay (LOS), nonhome discharges, and major complications. Four machine learning algorithms were developed and integrated into an open access web application to predict these outcomes. Results: A total of 3073 patients that underwent spinal tumor resection were included in the analysis. The most accurately predicted outcomes in terms of the area under the receiver operating characteristic curve (AUROC) was the prolonged LOS with a mean AUROC of 0.745 The most accurately predicting algorithm in terms of AUROC was random forest, with a mean AUROC of 0.743. An open access web application was developed for getting predictions for individual patients based on their characteristics and this web application can be accessed here: huggingface.co/spaces/MSHS-Neurosurgery-Research/NSQIP-ST. Conclusion: Machine learning approaches carry significant potential for the purpose of predicting postoperative outcomes following spinal tumor resections. Development of predictive models as clinically useful decision-making tools may considerably enhance risk assessment and prognosis as the amount of data in spinal tumor surgery continues to rise.

Predicting the buckling behaviour of thin-walled structural elements using machine learning methods

The design process of thin-walled structural members is highly complex due to the possible occurrence of multiple instabilities. This research therefore aimed to develop machine learning algorithms to predict the buckling behaviour of thin-walled channel elements subjected to axial compression or bending. Feed-forward multi-layer Artificial Neural Networks (ANNs) were trained, in which the input variables comprised the cross-sectional dimensions and thickness, the presence/location of intermediate stiffeners, and the element length. The output data consisted of the elastic critical buckling load or moment, while also providing an immediate modal decomposition of the buckled shape into the traditionally defined ‘pure’ buckling mode categories (i.e. local, distortional and global buckling). The sample output for training was prepared using a combination of the Finite Strip Method (FSM) and the Equivalent Nodal Force Method (ENFM). The ANN models were subjected to a K-fold cross-validation technique and the hyperparameters were tuned using a grid search technique. The results indicated that the trained algorithms were capable of predicting the elastic critical buckling loads and carrying out the modal decomposition of the critical buckled shapes with an average accuracy (R2-value) of 98%. The influence of the various channel parameters on the output was assessed using the SHapley Additive exPlanations (SHAP) method.

Revealing the sources of arsenic in private well water using Random Forest Classification and Regression.

Exposure to arsenic through private drinking water wells causes serious human health risks throughout the globe. Water testing data indicates there is arsenic contamination in private drinking water wells across New Jersey. To reduce the adverse health risk due to exposure to arsenic in drinking water, it is necessary to identify arsenic sources affecting private wells. Private wells are not regulated by any federal or state agencies through the Safe Drinking Water Act and therefore information is often lacking. To this end, we have developed machine learning algorithms including Random Forest Classification and Regression to decipher the factors contributing to higher arsenic concentration in private drinking water wells in west-central New Jersey. Arsenic concentration in private drinking water wells served as a response variable while explanatory variables were geological bedrock type, soil type, drainage class, land use/cover, and presence of orchards, contaminated sites, and abandoned mines within the 152.4-meter (500 ft) radius of each well. Random Forest Classification and Regression achieved 66 % and 55 % prediction accuracies for arsenic concentration in private drinking water wells, respectively. Overall, both models identify that bedrock, soil, land use/cover, and drainage type (in descending order) are the most important variables contributing to higher arsenic concentration in well water. These models further identify bedrock subgroups at a finer scale including Passaic Formation, Lockatong Formation, Stockton Formation contributing significantly to arsenic concentration in well water. Identification of sources of arsenic contamination in private drinking water wells at such a fine scale facilitates development of more targeted outreach as well as mitigation strategies to improve water quality and safeguard human health.

A machine learning approach in the estimation of a radioactive source position using a coded aperture device

Coded Aperture γ-cameras have been used for more than three decades for imaging radioactive source distributions encountered in astrophysics, in decommissioning of nuclear facilities, and in nuclear medicine. These devices enable the identification of the coordinates of γ-emitters located within their Field of View (FOV) with the use of the coded-aperture shadow projected on pixelated detectors. In this work we have developed machine learning algorithms based on Gradient Boosted Decision Trees (BDTG) and Deep Neural Networks (DNN). The algorithms have been trained using 21000 shadowgrams created with simulation. A custom fast simulation tool was used to produce the shadowgrams due to sources placed randomly at different positions within the FOV at distances from 20 cm up to 20 m from the detector plane. The performance of the algorithms has been evaluated with the aid of a different independent simulation sample of shadowgrams and verified with real data.

A Novel Light-Weight DCNN Model for Classifying Plant Diseases on Internet of Things Edge Devices

One of the essential aspects of smart farming and precision agriculture is quickly and accurately identifying diseases. Utilizing plant imaging and recently developed machine learning algorithms, the timely detection of diseases provides many benefits to farmers regarding crop and product quality. Specifically, for farmers in remote areas, disease diagnostics on edge devices is the most effective and optimal method to handle crop damage as quickly as possible. However, the limitations posed by the equipment’s limited resources have reduced the accuracy of disease detection. Consequently, adopting an efficient machine-learning model and decreasing the model size to fit the edge device is an exciting problem that receives significant attention from researchers and developers. This work takes advantage of previous research on deep learning model performance evaluation to present a model that applies to both the Plant-Village laboratory dataset and the Plant-Doc natural-type dataset. The evaluation results indicate that the proposed model is as effective as the current state-of-the-art model. Moreover, due to the quantization technique, the system performance stays the same when the model size is reduced to accommodate the edge device.

Predicting Antigenic Distance from Genetic Data for PRRSV-Type 1: Applications of Machine Learning.

The control of porcine reproductive and respiratory syndrome (PRRS) remains a significant challenge due to the genetic and antigenic variability of the causative virus (PRRSV). Predominantly, PRRSV management includes using vaccines and live virus inoculations to confer immunity against PRRSV on farms. While understanding cross-protection among strains is crucial for the continued success of these interventions, understanding how genetic diversity translates to antigenic diversity remains elusive. We developed machine learning algorithms to estimate antigenic distance in silico, based on genetic sequence data, and identify differences in specific amino acid sites associated with antigenic differences between viruses. First, we obtained antigenic distance estimates derived from serum neutralization assays cross-reacting PRRSV monospecific antisera with virus isolates from 27 PRRSV1 viruses circulating in Europe. Antigenic distances were weakly to moderately associated with ectodomain amino acid distance for open reading frames (ORFs) 2 to 4 (ρ < 0.2) and ORF5 (ρ = 0.3), respectively. Dividing the antigenic distance values at the median, we then categorized the sera-virus pairs into two levels: low and high antigenic distance (dissimilarity). In the machine learning models, we used amino acid distances in the ectodomains of ORFs 2 to 5 and site-wise amino acid differences between the viruses as potential predictors of antigenic dissimilarity. Using mixed-effect gradient boosting models, we estimated the antigenic distance (high versus low) between serum-virus pairs with an accuracy of 81% (95% confidence interval, 76 to 85%); sensitivity and specificity were 86% and 75%, respectively. We demonstrate that using sequence data we can estimate antigenic distance and potential cross-protection between PRRSV1 strains. IMPORTANCE Understanding cross-protection between cocirculating PRRSV1 strains is crucial to reducing losses associated with PRRS outbreaks on farms. While experimental studies to determine cross-protection are instrumental, these in vivo studies are not always practical or timely for the many cocirculating and emerging PRRSV strains. In this study, we demonstrate the ability to rapidly estimate potential immunologic cross-reaction between different PRRSV1 strains in silico using sequence data routinely collected by production systems. These models can provide fast turn-around information crucial for improving PRRS management decisions such as selecting vaccines/live virus inoculation to be used on farms and assessing the risk of outbreaks by emerging strains on farms previously exposed to certain PRRSV strains and vaccine development among others.

Quantification and machine learning based N2O–N and CO2–C emissions predictions from a decomposing rye cover crop

AbstractCover crops improve soil health and reduce the risk of soil erosion. However, their impact on the carbon dioxide equivalence (CO2e) is unknown. Therefore, the objective of this 2‐yr study was to quantify the effect of cover crop‐induced differences in soil moisture, temperature, organic C, and microorganisms on CO2e, and to develop machine learning algorithms that predict daily N2O–N and CO2–C emissions. The prediction models tested were multiple linear regression, partial least square regression, support vector machine, random forest (RF), and artificial neural network. Models’ performance was accessed using R2, RMSE and mean of absolute value of error. Rye (Secale cereale L.) was dormant seeded in mid‐October, and in the following spring it was terminated at corn's (Zea mays L.) V4 growth stage. Soil temperature, moisture, and N2O–N and CO2–C emissions were measured near continuously from soil thaw to harvest in 2019 and 2020. Prior to termination, the cover crop decreased N2O–N emissions by 34% (p = .05), and over the entire season, N2O–N emissions from cover crop and no cover crop treatments were similar (p = .71). Based on N2O–N and CO2–C emissions over the entire season and the estimated fixed cover crop‐C remaining in the soil, the partial CO2e were −1,061 and 496 kg CO2e ha–1 in the cover crop and no cover crop treatments, respectively. The RF algorithm explained more of the daily N2O–N (73%) and CO2–C (85%) emissions variability during validation than the other models. Across models, the most important variables were temperature and the amount of cover crop‐C added to the soil.

A correlation-based feature analysis of physical examination indicators can help predict the overall underlying health status using machine learning

As a systematic investigation of the correlations between physical examination indicators (PEIs) is lacking, most PEIs are currently independently used for disease warning. This results in the general physical examination having limited diagnostic values. Here, we systematically analyzed the correlations in 221 PEIs between healthy and 34 unhealthy statuses in 803,614 individuals in China. Specifically, the study population included 711,928 healthy participants, 51,341 patients with hypertension, 12,878 patients with diabetes, and 34,997 patients with other unhealthy statuses. We found rich relevance between PEIs in the healthy physical status (7662 significant correlations, 31.5%). However, in the disease conditions, the PEI correlations changed. We focused on the difference in PEIs between healthy and 35 unhealthy physical statuses and found 1239 significant PEI differences, suggesting that they could be candidate disease markers. Finally, we established machine learning algorithms to predict health status using 15–16% of the PEIs through feature extraction, reaching a 66–99% accurate prediction, depending on the physical status. This new reference of the PEI correlation provides rich information for chronic disease diagnosis. The developed machine learning algorithms can fundamentally affect the practice of general physical examinations.