Search

Background and aims: The incidence of colorectal cancer (CRC) is increasing in adults younger than 50, and early screening remains challenging due to cost and under-utilization. To identify individuals aged 35–50 years who may benefit from early screening, we developed a prediction model using machine learning and electronic health record (EHR)-derived factors. Methods: We enrolled 3,116 adults aged 35–50 at average-risk for CRC and underwent colonoscopy between 2017–2020 at a single center. Prediction outcomes were (1) CRC and (2) CRC or high-risk polyps. We derived our predictors from EHRs (e.g., demographics, obesity, laboratory values, medications, and zip code-derived factors). We constructed four machine learning-based models using a training set (random sample of 70% of participants): regularized discriminant analysis, random forest, neural network, and gradient boosting decision tree. In the testing set (remaining 30% of participants), we measured predictive performance by comparing C-statistics to a reference model (logistic regression). Results: The study sample was 55.1% female, 32.8% non-white, and included 16 (0.05%) CRC cases and 478 (15.3%) cases of CRC or high-risk polyps. All machine learning models predicted CRC with higher discriminative ability compared to the reference model [e.g., C-statistics (95%CI); neural network: 0.75 (0.48–1.00) vs. reference: 0.43 (0.18–0.67); P = 0.07] Furthermore, all machine learning approaches, except for gradient boosting, predicted CRC or high-risk polyps significantly better than the reference model [e.g., C-statistics (95%CI); regularized discriminant analysis: 0.64 (0.59–0.69) vs. reference: 0.55 (0.50–0.59); P<0.0015]. The most important predictive variables in the regularized discriminant analysis model for CRC or high-risk polyps were income per zip code, the colonoscopy indication, and body mass index quartiles. Discussion: Machine learning can predict CRC risk in adults aged 35–50 using EHR with improved discrimination. Further development of our model is needed, followed by validation in a primary-care setting, before clinical application. [ABSTRACT FROM AUTHOR]

Background: Mechanical ventilation (MV) is a lifesaving therapy used for patients with respiratory failure. Nevertheless, MV is associated with numerous complications and increased mortality. The aim of this study is to define the effects of MV on gene expression of direct and peripheral human tissues. Methods: Classification models were applied to Genotype-Tissue Expression Project (GTEx) gene expression data of six representative tissues–liver, adipose, skin, nerve-tibial, muscle and lung, for performance comparison and feature analysis. We utilized 18 prediction models using the Random Forest (RF), XGBoost (eXtreme Gradient Boosting) decision tree and ANN (Artificial Neural Network) methods to classify ventilation and non-ventilation samples and to compare their prediction performance for the six tissues. In the model comparison, the AUC (area under receiver operating curve), accuracy, precision, recall, and F1 score were used to evaluate the predictive performance of each model. We then conducted feature analysis per each tissue to detect MV marker genes followed by pathway enrichment analysis for these genes. Results: XGBoost outperformed the other methods and predicted samples had undergone MV with an average accuracy for the six tissues of 0.951 and average AUC of 0.945. The feature analysis detected a combination of MV marker genes per each tested tissue, some common across several tissues. MV marker genes were mainly related to inflammation and fibrosis as well as cell development and movement regulation. The MV marker genes were significantly enriched in inflammatory and viral pathways. Conclusion: The XGBoost method demonstrated clear enhanced performance and feature analysis compared to the other models. XGBoost was helpful in detecting the tissue-specific marker genes for identifying transcriptomic changes related to MV. Our results show that MV is associated with reduced development and movement in the tissues and higher inflammation and injury not only in direct tissues such as the lungs but also in peripheral tissues and thus should be carefully considered before being implemented. [ABSTRACT FROM AUTHOR]

The rising incidence of type 1 diabetes (T1D) among children is an increasing concern globally. A reliable estimate of the age at onset of T1D in children would facilitate intervention plans for medical practitioners to reduce the problems with delayed diagnosis of T1D. This paper has utilised Multiple Linear Regression (MLR), Artificial Neural Network (ANN) and Random Forest (RF) to model and predict the age at onset of T1D in children in Saudi Arabia (S.A.) which is ranked as the 7th for the highest number of T1D and 5th in the world for the incidence rate of T1D. De-identified data between (2010-2020) from three cities in S.A. were used to model and predict the age at onset of T1D. The best subset model selection criteria, coefficient of determination, and diagnostic tests were deployed to select the most significant variables. The efficacy of models for predicting the age at onset was assessed using multi-prediction accuracy measures. The average age at onset of T1D is 6.2 years and the most common age group for onset is (5-9) years. Most of the children in the sample (68%) are from urban areas of S.A., 75% were delivered after a full term pregnancy length and 31% were delivered through a cesarean section. The models of best fit were the MLR and RF models with R2 = (0.85 and 0.95), the root mean square error = (0.25 and 0.15) and mean absolute error = (0.19 and 0.11) respectively for logarithm of age at onset. This study for the first time has utilised MLR, ANN and RF models to predict the age at onset of T1D in children in S.A. These models can effectively aid health care providers to monitor and create intervention strategies to reduce the impact of T1D in children in S.A. [ABSTRACT FROM AUTHOR]

Objectives: Triage is an essential emergency department (ED) process designed to provide timely management depending on acuity and severity; however, the process may be inconsistent with clinical and hospitalization outcomes. Therefore, studies have attempted to augment this process with machine learning models, showing advantages in predicting critical conditions and hospitalization outcomes. The aim of this study was to utilize nationwide registry data to develop a machine learning-based classification model to predict the clinical course of pediatric ED visits. Methods: This cross-sectional observational study used data from the National Emergency Department Information System on emergency visits of children under 15 years of age from January 1, 2016, to December 31, 2017. The primary and secondary outcomes were to identify critically ill children and predict hospitalization from triage data, respectively. We developed and tested a random forest model with the under sampled dataset and validated the model using the entire dataset. We compared the model's performance with that of the conventional triage system. Results: A total of 2,621,710 children were eligible for the analysis and included 12,951 (0.5%) critical outcomes and 303,808 (11.6%) hospitalizations. After validation, the area under the receiver operating characteristic curve was 0.991 (95% confidence interval [CI] 0.991–0.992) for critical outcomes and 0.943 (95% CI 0.943–0.944) for hospitalization, which were higher than those of the conventional triage system. Conclusions: The machine learning-based model using structured triage data from a nationwide database can effectively predict critical illness and hospitalizations among children visiting the ED. [ABSTRACT FROM AUTHOR]

East African highland banana (Musa acuminata genome group AAA-EA; hereafter referred to as banana) is critical for Uganda's food supply, hence our aim to map current distribution and to understand changes in banana production areas over the past five decades. We collected banana presence/absence data through an online survey based on high-resolution satellite images and coupled this data with independent covariates as inputs for ensemble machine learning prediction of current banana distribution. We assessed geographic shifts of production areas using spatially explicit differences between the 1958 and 2016 banana distribution maps. The biophysical factors associated with banana spatial distribution and geographic shift were determined using a logistic regression model and classification and regression tree, respectively. Ensemble models were superior (AUC = 0.895; 0.907) compared to their constituent algorithms trained with 12 and 17 covariates, respectively: random forests (AUC = 0.883; 0.901), gradient boosting machines (AUC = 0.878; 0.903), and neural networks (AUC = 0.870; 0.890). The logistic regression model (AUC = 0.879) performance was similar to that for the ensemble model and its constituent algorithms. In 2016, banana cultivation was concentrated in the western (44%) and central (36%) regions, while only a small proportion was in the eastern (18%) and northern (2%) regions. About 60% of increased cultivation since 1958 was in the western region; 50% of decreased cultivation in the eastern region; and 44% of continued cultivation in the central region. Soil organic carbon, soil pH, annual precipitation, slope gradient, bulk density and blue reflectance were associated with increased banana cultivation while precipitation seasonality and mean annual temperature were associated with decreased banana cultivation over the past 50 years. The maps of spatial distribution and geographic shift of banana can support targeting of context-specific intensification options and policy advocacy to avert agriculture driven environmental degradation. [ABSTRACT FROM AUTHOR]

The mining industry production is an important pillar industry in China, while its extensive production activities have led to several ecological and environmental problems. Earth observation technology using high-resolution satellite imagery can help us efficiently obtain information on surface elements, surveying and monitoring various land occupation issues arising from open-pit mining production activities. Conventional pixel-based interpretation methods for high-resolution remote sensing images are restricted by "salt and pepper" noise caused by environmental factors, making it difficult to meet increasing requirements for monitoring accuracy. With the Jingxiang phosphorus mining area in Jingmen Hubei Province as the studied area, this paper uses a multi-scale segmentation algorithm to extract large-scale main characteristic information using a layered mask method based on the hierarchical structure of the image object. The remaining characteristic elements were classified and extracted in combination with the random forest model and characteristic factors to obtain land occupation information related mining industry production, which was compared with the results of the Classification and Regression Tree model. 23 characteristic factors in three aspects were selected, including spectral, geometric and texture characteristics. The methods employed in this study achieved 86% and 0.78 respectively in overall extraction accuracy analysis and the Kappa coefficient analysis, compared to 79% and 0.68 using the conventional method. [ABSTRACT FROM AUTHOR]

To undertake a reliable analysis of injury severity in road traffic accidents, a complete understanding of important attributes is essential. As a result of the shift from traditional statistical parametric procedures to computer-aided methods, machine learning approaches have become an important aspect in predicting the severity of road traffic injuries. The paper presents a hybrid feature selection-based machine learning classification approach for detecting significant attributes and predicting injury severity in single and multiple-vehicle accidents. To begin, we employed a Random Forests (RF) classifier in conjunction with an intrinsic wrapper-based feature selection approach called the Boruta Algorithm (BA) to find the relevant important attributes that determine injury severity. The influential attributes were then fed into a set of four classifiers to accurately predict injury severity (Naive Bayes (NB), K-Nearest Neighbor (K-NN), Binary Logistic Regression (BLR), and Extreme Gradient Boosting (XGBoost)). According to BA's experimental investigation, the vehicle type was the most influential factor, followed by the month of the year, the driver's age, and the alignment of the road segment. The driver's gender, the presence of a median, and the presence of a shoulder were all found to be unimportant. According to classifier performance measures, XGBoost surpasses the other classifiers in terms of prediction performance. Using the specified attributes, the accuracy, Cohen's Kappa, F1-Measure, and AUC-ROC values of the XGBoost were 82.10%, 0.607, 0.776, and 0.880 for single vehicle accidents and 79.52%, 0.569, 0.752, and 0.86 for multiple-vehicle accidents, respectively. [ABSTRACT FROM AUTHOR]

Background: A brief gonadotropin-releasing hormone analogues (GnRHa) stimulation test which solely focused on LH 30-minute post-stimulation was considered to identify girls with central precocious puberty (CPP). However, it was tested using traditional statistical methods. With advanced computer science, we aimed to develop a machine learning-based diagnostic model that processed baseline CPP-related variables and a brief GnRHa stimulation test for CPP diagnosis. Methods: We recruited girls suspected of precocious puberty and underwent a GnRHa stimulation test at Children Hospital 2, Vietnam, and Cathay General Hospital, Taiwan. Clinical data, bone age measurement, and 30-min post-stimulation blood test were used to build up the predictive model. The candidate model was developed by different machine learning algorithms that were mainly evaluated by sensitivity, specificity, the area under the receiver operator characteristic curve (AUC), and F1-score in internal and external validation data to classify girls as CPP and non-CPP at different time-points (0-min, 30-min, 60-min, and 120-min post-stimulation). Results: Among the 614 girls diagnosed with PP, 524 (85.3%) had CPP. The random forest algorithm yielded the highest value of F1-score (0.976), specificity (0.893), positive predicted value (0.987), and relatively high value of AUC (0.972) that contributed to high probability to identify CPP. The performance metrics of the 30-min post-stimulation diagnostic model including sensitivity and specificity surpassed those of the 0-minute model (0-min) and were equivalent to those of the model obtained 60-min and 120-min post-stimulation. Hence, our machine learning-based model helps shorten the stimulation test to 30 minutes after GnRHa injection, in general, it requires 120 minutes for a completed GnRHa stimulation test. Conclusions: We developed a diagnostic model based on clinical features and a single sample 30-minute post-stimulation to identify CPP in girls that can reduce distress for children caused by multiple blood samplings. [ABSTRACT FROM AUTHOR]

In Canadian boreal forests, bryophytes represent an essential component of biodiversity and play a significant role in ecosystem functioning. Despite their ecological importance and sensitivity to disturbances, bryophytes are overlooked in conservation strategies due to knowledge gaps on their distribution, which is known as the Wallacean shortfall. Rare species deserve priority attention in conservation as they are at a high risk of extinction. This study aims to elaborate predictive models of rare bryophyte species in Canadian boreal forests using remote sensing-derived predictors in an Ensemble of Small Models (ESMs) framework. We hypothesize that high ESMs-based prediction accuracy can be achieved for rare bryophyte species despite their low number of occurrences. We also assess if there is a spatial correspondence between rare and overall bryophyte richness patterns. The study area is located in western Quebec and covers 72,292 km2. We selected 52 bryophyte species with <30 occurrences from a presence-only database (214 species, 389 plots in total). ESMs were built from Random Forest and Maxent techniques using remote sensing-derived predictors related to topography and vegetation. Lee's L statistic was used to assess and map the spatial relationship between rare and overall bryophyte richness patterns. ESMs yielded poor to excellent prediction accuracy (AUC > 0.5) for 73% of the modeled species, with AUC values > 0.8 for 19 species, which confirmed our hypothesis. In fact, ESMs provided better predictions for the rarest bryophytes. Likewise, our study revealed a spatial concordance between rare and overall bryophyte richness patterns in different regions of the study area, which have important implications for conservation planning. This study demonstrates the potential of remote sensing for assessing and making predictions on inconspicuous and rare species across the landscape and lays the basis for the eventual inclusion of bryophytes into sustainable development planning. [ABSTRACT FROM AUTHOR]

Objective: To explore the feasibility of using random forest (RF) machine learning algorithm in assessing normal and malignant peripheral pulmonary nodules based on in vivo endobronchial optical coherence tomography (EB-OCT). Methods: A total of 31 patients with pulmonary nodules were admitted to Department of Respiratory Medicine, Zhongda Hospital, Southeast University, and underwent chest CT, EB-OCT and biopsy. Attenuation coefficient and up to 56 different image features were extracted from A-line and B-scan of 1703 EB-OCT images. Attenuation coefficient and 29 image features with significant p-values were used to analyze the differences between normal and malignant samples. A RF classifier was trained using 70% images as training set, while 30% images were included in the testing set. The accuracy of the automated classification was validated by clinically proven pathological results. Results: Attenuation coefficient and 29 image features were found to present different properties with significant p-values between normal and malignant EB-OCT images. The RF algorithm successfully classified the malignant pulmonary nodules with sensitivity, specificity, and accuracy of 90.41%, 77.87% and 83.51% respectively. Conclusion: It is clinically practical to distinguish the nature of pulmonary nodules by integrating EB-OCT imaging with automated machine learning algorithm. Diagnosis of malignant pulmonary nodules by analyzing quantitative features from EB-OCT images could be a potentially powerful way for early detection of lung cancer. [ABSTRACT FROM AUTHOR]

Hand, foot and mouth disease (HFMD) is an increasingly serious public health problem, and it has caused an outbreak in China every year since 2008. Predicting the incidence of HFMD and analyzing its influential factors are of great significance to its prevention. Now, machine learning has shown advantages in infectious disease models, but there are few studies on HFMD incidence based on machine learning that cover all the provinces in mainland China. In this study, we proposed two different machine learning algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost), to perform our analysis and prediction. We first used Random Forest to examine the association between HFMD incidence and potential influential factors for 31 provinces in mainland China. Next, we established Random Forest and XGBoost prediction models using meteorological and social factors as the predictors. Finally, we applied our prediction models in four different regions of mainland China and evaluated the performance of them. Our results show that: 1) Meteorological factors and social factors jointly affect the incidence of HFMD in mainland China. Average temperature and population density are the two most significant influential factors; 2) Population flux has different delayed effect in affecting HFMD incidence in different regions. From a national perspective, the model using population flux data delayed for one month has better prediction performance; 3) The prediction capability of XGBoost model was better than that of Random Forest model from the overall perspective. XGBoost model is more suitable for predicting the incidence of HFMD in mainland China. [ABSTRACT FROM AUTHOR]

Successive orchard plantings of almond and other Prunus species exhibit reduced growth and yield in many California soils. This phenomenon, known as Prunus replant disease (PRD), can be prevented by preplant soil fumigation or anaerobic soil disinfestation, but its etiology is poorly understood and its incidence and severity are hard to predict. We report here on relationships among physicochemical variables, microbial community structure, and PRD induction in 25 diverse replant soils from California. In a greenhouse bioassay, soil was considered to be "PRD-inducing" when growth of peach seedlings in it was significantly increased by preplant fumigation and pasteurization, compared to an untreated control. PRD was induced in 18 of the 25 soils, and PRD severity correlated positively with soil exchangeable-K, pH, %clay, total %N, and electrical conductivity. The structure of bacterial, fungal, and oomycete communities differed significantly between the PRD-inducing and non-inducing soils, based on PERMANOVA of Bray Curtis dissimilarities. Bacterial class MB-A2-108 of phylum Actinobacteria had high relative abundances among PRD-inducing soils, while Bacteroidia were relatively abundant among non-inducing soils. Among fungi, many ASVs classified only to kingdom level were relatively abundant among PRD-inducing soils whereas ASVs of Trichoderma were relatively abundant among non-inducing soils. Random forest classification effectively discriminated between PRD-inducing and non-inducing soils, revealing many bacterial ASVs with high explanatory values. Random forest regression effectively accounted for PRD severity, with soil exchangeable-K and pH having high predictive value. Our work revealed several biotic and abiotic variables worthy of further examination in PRD etiology. [ABSTRACT FROM AUTHOR]

Aims: Noncompaction cardiomyopathy (NCC) is considered a genetic cardiomyopathy with unknown pathophysiological mechanisms. We propose to evaluate echocardiographic predictors for rigid body rotation (RBR) in NCC using a machine learning (ML) based model. Methods and results: Forty-nine outpatients with NCC diagnosis by echocardiography and magnetic resonance imaging (21 men, 42.8±14.8 years) were included. A comprehensive echocardiogram was performed. The layer-specific strain was analyzed from the apical two-, three, four-chamber views, short axis, and focused right ventricle views using 2D echocardiography (2DE) software. RBR was present in 44.9% of patients, and this group presented increased LV mass indexed (118±43.4 vs. 94.1±27.1g/m2, P = 0.034), LV end-diastolic and end-systolic volumes (P< 0.001), E/e' (12.2±8.68 vs. 7.69±3.13, P = 0.034), and decreased LV ejection fraction (40.7±8.71 vs. 58.9±8.76%, P < 0.001) when compared to patients without RBR. Also, patients with RBR presented a significant decrease of global longitudinal, radial, and circumferential strain. When ML model based on a random forest algorithm and a neural network model was applied, it found that twist, NC/C, torsion, LV ejection fraction, and diastolic dysfunction are the strongest predictors to RBR with accuracy, sensitivity, specificity, area under the curve of 0.93, 0.99, 0.80, and 0.88, respectively. Conclusion: In this study, a random forest algorithm was capable of selecting the best echocardiographic predictors to RBR pattern in NCC patients, which was consistent with worse systolic, diastolic, and myocardium deformation indices. Prospective studies are warranted to evaluate the role of this tool for NCC risk stratification. [ABSTRACT FROM AUTHOR]

Recent technological advances have facilitated the collection of large-scale administrative data and the online surveying of the Indian population. Building on these we propose a strategy for more robust, frequent and transparent projections of the Indian vote during the campaign. We execute a modified MrP model of Indian vote preferences that proposes innovations to each of its three core components: stratification frame, training data, and a learner. For the post-stratification frame we propose a novel Data Integration approach that allows the simultaneous estimation of counts from multiple complementary sources, such as census tables and auxiliary surveys. For the training data we assemble panels of respondents from two unorthodox online populations: Amazon Mechanical Turks workers and Facebook users. And as a modeling tool, we replace the Bayesian multilevel regression learner with Random Forests. Our 2019 pre-election forecasts for the two largest Lok Sahba coalitions were very close to actual outcomes: we predicted 41.8% for the NDA, against an observed value of 45.0% and 30.8% for the UPA against an observed vote share of just under 31.3%. Our uniform-swing seat projection outperforms other pollsters—we had the lowest absolute error of 89 seats (along with a poll from 'Jan Ki Baat'); the lowest error on the NDA-UPA lead (a mere 8 seats), and we are the only pollster that can capture real-time preference shifts due to salient campaign events. [ABSTRACT FROM AUTHOR]

White abalone (Haliotis sorenseni) was once commonly found in coastal waters of the Southern California Bight (SCB) and south to Punta Abreojos, Baja California, Mexico. During the 1970s, white abalone supported a commercial fishery, which reduced the population and resulted in the closure of the fishery in 1996. When population levels continued to decline, National Marine Fisheries Service (NMFS) listed the species as endangered under the Endangered Species Act. The California Department of Fish and Wildlife and NMFS began surveying the wild populations, propagating specimens in captivity, and protecting its seabed habitat. We modeled coarse-scale (17 x 17 km) historical (using fishery-dependent data [1955–1996]) and contemporary (using fishery-independent data [1996–2017]) distributions of white abalone throughout its historical domain using random forests and maximum entropy (MaxEnt), respectively, and its fine-scale (10 x 10 m) contemporary distribution (fishery-independent data) using MaxEnt. We also investigated potential outplanting habitat farther north under two scenarios of future climate conditions. The coarse-scale models identified potential regions to focus outplanting efforts within SCB while fine-scale models can inform population monitoring and outplanting activities in these particular areas. These models predict that areas north of Point Conception may become candidate outplant sites as seawater temperatures continue to rise in the future due to climate change. Collectively, these results provide guidance on the design and potential locations for experimental outplanting at such locations to ultimately improve methods and success of recovery efforts. [ABSTRACT FROM AUTHOR]

Maps of bottom type are essential to the management of marine resources and biodiversity because of their foundational role in characterizing species' habitats. They are also urgently needed as countries work to define marine protected areas. Current approaches are time consuming, focus largely on grain size, and tend to overlook shallow waters. Our random forest classification of almost 200,000 observations of bottom type is a timely alternative, providing maps of coastal substrate at a combination of resolution and extents not previously achieved. We correlated the observations with depth, depth-derivatives, and estimates of energy to predict marine substrate at 100 m resolution for Canada's Pacific shelf, a study area of over 135,000 km2. We built five regional models with the same data at 20 m resolution. In addition to standard tests of model fit, we used three independent data sets to test model predictions. We also tested for regional, depth, and resolution effects. We guided our analysis by asking: 1) does weighting for prevalence improve model predictions? 2) does model resolution influence model performance? And 3) is model performance influenced by depth? All our models fit the build data well with true skill statistic (TSS) scores ranging from 0.56 to 0.64. Weighting models with class prevalence improved fit and the correspondence with known spatial features. Class-based metrics showed differences across both resolutions and spatial regions, indicating non-stationarity across these spatial categories. Predictive power was lower (TSS from 0.10 to 0.36) based on independent data evaluation. Model performance was also a function of depth and resolution, illustrating the challenge of accurately representing heterogeneity. Our work shows the value of regional analyses to assessing model stationarity and how independent data evaluation and the use of error metrics can improve understanding of model performance and sampling bias. [ABSTRACT FROM AUTHOR]

Psoriasis is a chronic inflammatory skin disease that affects approximately 125 million people worldwide. It has significant impacts on both physical and emotional health-related quality of life comparable to other major illnesses. Accurately prediction of psoriasis using biomarkers from routine laboratory tests has important practical values. Our goal is to derive a powerful predictive model for psoriasis disease based on only routine hospital tests. We collected a data set including 466 psoriasis patients and 520 healthy controls with 81 variables from only laboratory routine tests, such as age, total cholesterol, HDL cholesterol, blood pressure, albumin, and platelet distribution width. In this study, Boruta feature selection method was applied to select the most relevant features, with which a Random Forest model was constructed. The model was tested with 30 repetitions of 10-fold cross-validation. Our classification model yielded an average accuracy of 86.9%. 26 notable features were selected by Boruta, among which 15 features are confirmed from previous studies, and the rest are worth further investigations. The experimental results demonstrate that the machine learning approach has good potential in predictive modeling for the psoriasis disease given the information only from routine hospital tests. [ABSTRACT FROM AUTHOR]

Gene expression data has the characteristics of high dimensionality and a small sample size and contains a large number of redundant genes unrelated to a disease. The direct application of machine learning to classify this type of data will not only incur a great time cost but will also sometimes fail to improved classification performance. To counter this problem, this paper proposes a dimension-reduction algorithm based on weighted kernel principal component analysis (WKPCA), constructs kernel function weights according to kernel matrix eigenvalues, and combines multiple kernel functions to reduce the feature dimensions. To further improve the dimensional reduction efficiency of WKPCA, t-class kernel functions are constructed, and corresponding theoretical proofs are given. Moreover, the cumulative optimal performance rate is constructed to measure the overall performance of WKPCA combined with machine learning algorithms. Naive Bayes, K-nearest neighbour, random forest, iterative random forest and support vector machine approaches are used in classifiers to analyse 6 real gene expression dataset. Compared with the all-variable model, linear principal component dimension reduction and single kernel function dimension reduction, the results show that the classification performance of the 5 machine learning methods mentioned above can be improved effectively by WKPCA dimension reduction. [ABSTRACT FROM AUTHOR]

Ecological Niche Modeling is a process by which spatiotemporal, climatic, and environmental data are analyzed to predict the distribution of an organism. Using this process, an ensemble ecological niche model for West Nile virus habitat prediction in the state of Florida was developed. This model was created through the weighted averaging of three separate machine learning models—boosted regression tree, random forest, and maximum entropy—developed for this study using sentinel chicken surveillance and remote sensing data. Variable importance differed among the models. The highest variable permutation value included mean dewpoint temperature for the boosted regression tree model, mean temperature for the random forest model, and wetlands focal statistics for the maximum entropy mode. Model validation resulted in area under the receiver curve predictive values ranging from good [0.8728 (95% CI 0.8422–0.8986)] for the maximum entropy model to excellent [0.9996 (95% CI 0.9988–1.0000)] for random forest model, with the ensemble model predictive value also in the excellent range [0.9939 (95% CI 0.9800–0.9979]. This model should allow mosquito control districts to optimize West Nile virus surveillance, improving detection and allowing for a faster, targeted response to reduce West Nile virus transmission potential. [ABSTRACT FROM AUTHOR]

With the advent of high-throughput technologies, life sciences are generating a huge amount of varied biomolecular data. Global gene expression profiles provide a snapshot of all the genes that are transcribed in a cell or in a tissue under a particular condition. The high-dimensionality of such gene expression data (i.e., very large number of features/genes analyzed with relatively much less number of samples) makes it difficult to identify the key genes (biomarkers) that are truly attributing to a particular phenotype or condition, (such as cancer), de novo. For identifying the key genes from gene expression data, among the existing literature, mutual information (MI) is one of the most successful criteria. However, the correction of MI for finite sample is not taken into account in this regard. It is also important to incorporate dynamic discretization of genes for more relevant gene selection, although this is not considered in the available methods. Besides, it is usually suggested in current studies to remove redundant genes which is particularly inappropriate for biological data, as a group of genes may connect to each other for downstreaming proteins. Thus, despite being redundant, it is needed to add the genes which provide additional useful information for the disease. Addressing these issues, we proposed Mutual information based Gene Selection method (MGS) for selecting informative genes. Moreover, to rank these selected genes, we extended MGS and propose two ranking methods on the selected genes, such as MGSf—based on frequency and MGSrf—based on Random Forest. The proposed method not only obtained better classification rates on gene expression datasets derived from different gene expression studies compared to recently reported methods but also detected the key genes relevant to pathways with a causal relationship to the disease, which indicate that it will also able to find the responsible genes for an unknown disease data. [ABSTRACT FROM AUTHOR]

The evolution of malware is causing mobile devices to crash with increasing frequency. Therefore, adequate security evaluations that detect Android malware are crucial. Two techniques can be used in this regard: Static analysis, which meticulously examines the full codes of applications, and dynamic analysis, which monitors malware behaviour. While both perform security evaluations successfully, there is still room for improvement. The goal of this research is to examine the effectiveness of static analysis to detect Android malware by using permission-based features. This study proposes machine learning with different sets of classifiers was used to evaluate Android malware detection. The feature selection method in this study was applied to determine which features were most capable of distinguishing malware. A total of 5,000 Drebin malware samples and 5,000 Androzoo benign samples were utilised. The performances of the different sets of classifiers were then compared. The results indicated that with a TPR value of 91.6%, the Random Forest algorithm achieved the highest level of accuracy in malware detection. [ABSTRACT FROM AUTHOR]

Background: Girls and women need effective, safe, and affordable menstrual products. Single-use menstrual pads and tampons are regularly provided by agencies among resource-poor populations. Reusable menstrual pads (RMPs: fabric layers sewn together by an enterprise for manufacture of menstrual products) may be an effective alternative. Methods: For this review (PROSPERO CRD42020179545) we searched databases (inception to November 1, 2020) for quantitative and qualitative studies that reported on leakage, acceptability, or safety of RMPs. Findings were summarised or combined using forest plots (random-effects meta-analysis). Potential costs and environmental savings associated with RMPs were estimated. Results: A total of 44 studies were eligible (~14,800 participants). Most were conducted in low- and middle-income countries (LMIC, 78%), and 20% in refugee settings. The overall quality of studies was low. RMP uptake in cohort studies ranged from 22–100% (12 studies). One Ugandan trial among schoolgirls found leakage with RMPs was lower (44.4%, n = 72) compared to cloths (78%, n = 111, p<0.001). Self-reported skin-irritation was 23.8% after 3 months among RMP-users in a Ugandan cohort in a refugee setting (n = 267), compared to 72.8% at baseline with disposable pad use. There were no objective reports on infection. Challenges with washing and changing RMP were reported in LMIC studies, due to lack of water, privacy, soap, buckets, and sanitation/drying facilities. Among 69 brands, the average price for an RMP was $8.95 (standard deviation [sd] $5.08; LMIC $2.06, n = 10, high-income countries [HIC] $10.11), with a mean estimated lifetime of 4.3 years (sd 2.3; LMIC 2.9, n = 11; HIC 4.9 years, n = 23). In 5-year cost-estimates, in LMICs, 4–25 RMPs per period would be cheaper (170–417 US$) than 9–25 single-use pads, with waste-savings of ~600–1600 single-use pads. In HICs, 4–25 RMPs would be cheaper (33–245 US$) compared to 20 single-use tampons per period, with waste-savings of ~1300 tampons. Conclusion: RMPs are used internationally and are an effective, safe, cheaper, and environmentally friendly option for menstrual product provision by programmes. Good quality studies in this field are needed. [ABSTRACT FROM AUTHOR]

Anthropogenic activities are changing the state of ecosystems worldwide, affecting community composition and often resulting in loss of biodiversity. Rivers are among the most impacted ecosystems. Recording their current state with regular biomonitoring is important to assess the future trajectory of biodiversity. Traditional monitoring methods for ecological assessments are costly and time-intensive. Here, we compared monitoring of macroinvertebrates based on environmental DNA (eDNA) sampling with monitoring based on traditional kick-net sampling to assess biodiversity patterns at 92 river sites covering all major Swiss river catchments. From the kick-net community data, a biotic index (IBCH) based on 145 indicator taxa had been established. The index was matched by the taxonomically annotated eDNA data by using a machine learning approach. Our comparison of diversity patterns only uses the zero-radius Operational Taxonomic Units assigned to the indicator taxa. Overall, we found a strong congruence between both methods for the assessment of the total indicator community composition (gamma diversity). However, when assessing biodiversity at the site level (alpha diversity), the methods were less consistent and gave complementary data on composition. Specifically, environmental DNA retrieved significantly fewer indicator taxa per site than the kick-net approach. Importantly, however, the subsequent ecological classification of rivers based on the detected indicators resulted in similar biotic index scores for the kick-net and the eDNA data that was classified using a random forest approach. The majority of the predictions (72%) from the random forest classification resulted in the same river status categories as the kick-net approach. Thus, environmental DNA validly detected indicator communities and, combined with machine learning, provided reliable classifications of the ecological state of rivers. Overall, while environmental DNA gives complementary data on the macroinvertebrate community composition compared to the kick-net approach, the subsequently calculated indices for the ecological classification of river sites are nevertheless directly comparable and consistent. [ABSTRACT FROM AUTHOR]

As the Internet retail industry continues to rise, more and more consumers choose to shop online, especially Chinese consumers. Using consumer behavior data left on the Internet to predict repurchase behavior is of great significance for companies to achieve precision marketing. This paper proposes an improved deep forest model, and the interactive behavior characteristics of users and goods are added into the original feature model to predict the repurchase behavior of e-commerce consumers. Based on the Alibaba mobile e-commerce platform data set, first construct a feature engineering that includes user characteristics, product characteristics, and interactive behavior characteristics. And then use our proposed model to make predictions. Experiments show that the model's overall performance with increased interactive behavior features is better and has higher accuracy. Compared with the existing prediction models, the improved deep forest model has certain advantages, which not only improves the prediction accuracy but also reduces the cost of training time. [ABSTRACT FROM AUTHOR]

Background: Cardiac dysrhythmias (CD) affect millions of Americans in the United States (US), and are associated with considerable morbidity and mortality. New strategies to combat this growing problem are urgently needed. Objectives: Predicting CD using electronic health record (EHR) data would allow for earlier diagnosis and treatment of the condition, thus improving overall cardiovascular outcomes. The Guideline Advantage (TGA) is an American Heart Association ambulatory quality clinical data registry of EHR data representing 70 clinics distributed throughout the US, and has been used to monitor outpatient prevention and disease management outcome measures across populations and for longitudinal research on the impact of preventative care. Methods: For this study, we represented all time-series cardiovascular health (CVH) measures and the corresponding data collection time points for each patient by numerical embedding vectors. We then employed a deep learning technique–long-short term memory (LSTM) model–to predict CD from the vector of time-series CVH measures by 5-fold cross validation and compared the performance of this model to the results of deep neural networks, logistic regression, random forest, and Naïve Bayes models. Results: We demonstrated that the LSTM model outperformed other traditional machine learning models and achieved the best prediction performance as measured by the average area under the receiver operator curve (AUROC): 0.76 for LSTM, 0.71 for deep neural networks, 0.66 for logistic regression, 0.67 for random forest, and 0.59 for Naïve Bayes. The most influential feature from the LSTM model were blood pressure. Conclusions: These findings may be used to prevent CD in the outpatient setting by encouraging appropriate surveillance and management of CVH. [ABSTRACT FROM AUTHOR]

The current pandemic outbreak clearly indicated the urgent need for tools allowing fast predictions of bioactivity of a large number of compounds, either available or at least synthesizable. In the computational chemistry toolbox, several such tools are available, with the main ones being docking and structure-activity relationship modeling either by classical linear QSAR or Machine Learning techniques. In this contribution, we focus on the comparison of the results obtained using different docking protocols on the example of the search for bioactivity of compounds containing N-N-C(S)-N scaffold at the S-protein of SARS-CoV-2 virus with ACE2 human receptor interface. Based on over 1800 structures in the training set we have predicted binding properties of the complete set of nearly 600000 structures from the same class using the Machine Learning Random Forest Regressor approach. [ABSTRACT FROM AUTHOR]

Advances in remote sensing and machine learning enable increasingly accurate, inexpensive, and timely estimation of poverty and malnutrition indicators to guide development and humanitarian agencies' programming. However, state of the art models often rely on proprietary data and/or deep or transfer learning methods whose underlying mechanics may be challenging to interpret. We demonstrate how interpretable random forest models can produce estimates of a set of (potentially correlated) malnutrition and poverty prevalence measures using free, open access, regularly updated, georeferenced data. We demonstrate two use cases: contemporaneous prediction, which might be used for poverty mapping, geographic targeting, or monitoring and evaluation tasks, and a sequential nowcasting task that can inform early warning systems. Applied to data from 11 low and lower-middle income countries, we find predictive accuracy broadly comparable for both tasks to prior studies that use proprietary data and/or deep or transfer learning methods. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a complex neurodegenerative disorder that affects thinking, memory, and behavior. Limbic-predominant age-related TDP-43 encephalopathy (LATE) is a recently identified common neurodegenerative disease that mimics the clinical symptoms of AD. The development of drugs to prevent or treat these neurodegenerative diseases has been slow, partly because the genes associated with these diseases are incompletely understood. A notable hindrance from data analysis perspective is that, usually, the clinical samples for patients and controls are highly imbalanced, thus rendering it challenging to apply most existing machine learning algorithms to directly analyze such datasets. Meeting this data analysis challenge is critical, as more specific disease-associated gene identification may enable new insights into underlying disease-driving mechanisms and help find biomarkers and, in turn, improve prospects for effective treatment strategies. In order to detect disease-associated genes based on imbalanced transcriptome-wide data, we proposed an integrated multiple random forests (IMRF) algorithm. IMRF is effective in differentiating putative genes associated with subjects having LATE and/or AD from controls based on transcriptome-wide data, thereby enabling effective discrimination between these samples. Various forms of validations, such as cross-domain verification of our method over other datasets, improved and competitive classification performance by using identified genes, effectiveness of testing data with a classifier that is completely independent from decision trees and random forests, and relationships with prior AD and LATE studies on the genes linked to neurodegeneration, all testify to the effectiveness of IMRF in identifying genes with altered expression in LATE and/or AD. We conclude that IMRF, as an effective feature selection algorithm for imbalanced data, is promising to facilitate the development of new gene biomarkers as well as targets for effective strategies of disease prevention and treatment. [ABSTRACT FROM AUTHOR]

Louisiana Waterthrush (Parkesia motacilla) is a familiar singer in the Western Hemisphere family Parulidae, yet apparent geographic variations in its song and potentially related causal mechanisms have not received detailed examination in previously published studies. Here, we analyzed song pattern variations of 651 Louisiana Waterthrush singers in audio spectrogram recordings obtained from our field work and publicly accessible bioacoustics archives. Visual and auditory assessment of the introductory note sequence of each song identified three distinct song types (A, B, and C) and most of the songs were assigned to one of these types. Linear Discriminant Analysis and Random Forest methods were used to verify the assignments and showed strong agreement for Type A with slightly less agreement on Types B and C. User error rates (proportion of the Linear Discriminant Analysis classifications that were incorrect) were low for Types A and B, and somewhat higher for Type C, while producer error rates (proportion of the song type for which the Linear Discriminant Analysis was incorrect) were somewhat higher for Types A and C than the minimal levels achieved for Type B. Our findings confirmed that most between-individual variation was in the number of notes and note sequence duration while most within-individual variation resulted from the percent of downstrokes. The location of each singer was plotted on a map of the breeding range and results suggested the song types have large-scale discrete geographic distributions that co-occur in some regions but not range-wide. Evaluation of the distributions provided tentative support for a hypothesis that two of the song types may independently exhibit congruence with the geographic extent of Pleistocene glacial boundaries and the third song type may be distinguished by a lack of congruence, but further investigation is needed to elucidate whether the song variations represent subpopulations with three separate evolutionary histories. [ABSTRACT FROM AUTHOR]

Gadolinium-enhancing lesions reflect active disease and are critical for in-patient monitoring in multiple sclerosis (MS). In this work, we have developed the first fully automated method to segment and count the gadolinium-enhancing lesions from routine clinical MRI of MS patients. The proposed method first segments the potential lesions using 2D-UNet from multi-channel scans (T1 post-contrast, T1 pre-contrast, FLAIR, T2, and proton-density) and classifies the lesions using a random forest classifier. The algorithm was trained and validated on 600 MRIs with manual segmentation. We compared the effect of loss functions (Dice, cross entropy, and bootstrapping cross entropy) and number of input contrasts. We compared the lesion counts with those by radiologists using 2,846 images. Dice, lesion-wise sensitivity, and false discovery rate with full 5 contrasts were 0.698, 0.844, and 0.307, which improved to 0.767, 0.969, and 0.00 in large lesions (>100 voxels). The model using bootstrapping loss function provided a statistically significant increase of 7.1% in sensitivity and of 2.3% in Dice compared with the model using cross entropy loss. T1 post/pre-contrast and FLAIR were the most important contrasts. For large lesions, the 2D-UNet model trained using T1 pre-contrast, FLAIR, T2, PD had a lesion-wise sensitivity of 0.688 and false discovery rate 0.083, even without T1 post-contrast. For counting lesions in 2846 routine MRI images, the model with 2D-UNet and random forest, which was trained with bootstrapping cross entropy, achieved accuracy of 87.7% using T1 pre-contrast, T1 post-contrast, and FLAIR when lesion counts were categorized as 0, 1, and 2 or more. The model performs well in routine non-standardized MRI datasets, allows large-scale analysis of clinical datasets, and may have clinical applications. [ABSTRACT FROM AUTHOR]

Identifying people with Parkinson disease during the prodromal period, including via algorithms in administrative claims data, is an important research and clinical priority. We sought to improve upon an existing penalized logistic regression model, based on diagnosis and procedure codes, by adding prescription medication data or using machine learning. Using Medicare Part D beneficiaries age 66–90 from a population-based case-control study of incident Parkinson disease, we fit a penalized logistic regression both with and without Part D data. We also built a predictive algorithm using a random forest classifier for comparison. In a combined approach, we introduced the probability of Parkinson disease from the random forest, as a predictor in the penalized regression model. We calculated the receiver operator characteristic area under the curve (AUC) for each model. All models performed well, with AUCs ranging from 0.824 (simplest model) to 0.835 (combined approach). We conclude that medication data and random forests improve Parkinson disease prediction, but are not essential. [ABSTRACT FROM AUTHOR]

Vessel-based sonar systems that focus on the water column provide valuable information on the distribution of underwater marine organisms, but such data are expensive to collect and limited in their spatiotemporal coverage. Satellite data, however, are widely available across large regions and provide information on surface ocean conditions. If satellite data can be linked to subsurface sonar measurements, it may be possible to predict marine life over broader spatial regions with higher frequency using satellite observations. Here, we use random forest models to evaluate the potential for predicting a sonar-derived proxy for subsurface biomass as a function of satellite imagery in the California Current Ecosystem. We find that satellite data may be useful for prediction under some circumstances, but across a range of sonar frequencies and depths, overall model performance was low. Performance in spatial interpolation tasks exceeded performance in spatial and temporal extrapolation, suggesting that this approach is not yet reliable for forecasting or spatial extrapolation. We conclude with some potential limitations and extensions of this work. [ABSTRACT FROM AUTHOR]

Monitoring variables such as dissolved oxygen, pH, and pond temperature is a key aspect of high-quality fish farming. Machine learning (ML) techniques have been proposed to model the dynamics of such variables to improve the fish farmer's decision-making. Most of the research on ML in aquaculture has focused on scenarios where devices for real-time data acquisition, storage, and remote monitoring are available, making it easy to develop accurate ML techniques. However, fish farmers do not necessarily have access to such devices. Many of them prefer to use equipment to manually measure these variables limiting the amount of available data to process. In this work, we study the use of random forests, multivariate linear regression, and artificial neural networks in scenarios with limited amount of measurements to analyze data from water-quality variables that are commonly measured in fish farming. We propose a methodology to build models in two scenarios: i) estimation of unobserved variables based on the observed ones, and ii) forecasting when a low amount of data is available for training. We show that random forests can be used to forecast dissolved oxygen, pond temperature, pH, ammonia, and ammonium when the water pond variables are measured only twice per day. Moreover, we showed that these prediction models can be implemented on a mobile-based information system and run in an average smartphone that fish farmers can afford. [ABSTRACT FROM AUTHOR]

The bandgap of two-dimensional (2D) materials plays an important role in their applications to various devices. For instance, the gapless nature of graphene limits the use of this material to semiconductor device applications, whereas the indirect bandgap of molybdenum disulfide is suitable for electrical and photo-device applications. Therefore, predicting the bandgap rapidly and accurately for a given 2D material structure has great scientific significance in the manufacturing of semiconductor devices. Compared to the extremely high computation cost of conventional first-principles calculations, machine learning (ML) based on statistics may be a promising alternative to predicting bandgaps. Although ML algorithms have been used to predict the properties of materials, they have rarely been used to predict the properties of 2D materials. In this study, we apply four ML algorithms to predict the bandgaps of 2D materials based on the computational 2D materials database (C2DB). Gradient boosted decision trees and random forests are more effective in predicting bandgaps of 2D materials with an R2 >90% and root-mean-square error (RMSE) of ~0.24 eV and 0.27 eV, respectively. By contrast, support vector regression and multi-layer perceptron show that R2 is >70% with RMSE of ~0.41 eV and 0.43 eV, respectively. Finally, when the bandgap calculated without spin-orbit coupling (SOC) is used as a feature, the RMSEs of the four ML models decrease greatly to 0.09 eV, 0.10 eV, 0.17 eV, and 0.12 eV, respectively. The R2 of all the models is >94%. These results show that the properties of 2D materials can be rapidly obtained by ML prediction with high precision. [ABSTRACT FROM AUTHOR]

Soil pH effects a wide range of critical biogeochemical processes that dictate plant growth and diversity. Previous literature has established the capacity of classification and regression trees (CARTs) to predict soil pH, but limitations of CARTs in this context have not been fully explored. The current study collected soil pH, climatic, and topographic data from 100 locations across New York's Temperate Deciduous Forests (in the United States of America) to investigate the extrapolative capacity of a previously developed CART model as compared to novel CART and random forest (RF) models. Results showed that the previously developed CART underperformed in terms of predictive accuracy (RRMSE = 14.52%) when compared to a novel tree (RRMSE = 9.33%), and that a novel random forest outperformed both models (RRMSE = 8.88%), though its predictions did not differ significantly from the novel tree (p = 0.26). The most important predictors for model construction were climatic factors. These findings confirm existing reports that CART models are constrained by the spatial autocorrelation of geographic data and encourage the restricted application of relevant machine learning models to regions from which training data was collected. They also contradict previous literature implying that random forests should meaningfully boost the predictive accuracy of CARTs in the context of soil pH. [ABSTRACT FROM AUTHOR]

Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users—pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups—for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists. [ABSTRACT FROM AUTHOR]

Background: Alcohol use disorder (AUD) is a chronic disease with a higher recurrence rate than that of other mental illnesses. Moreover, it requires continuous outpatient treatment for the patient to maintain abstinence. However, with a low probability of these patients to continue outpatient treatment, predicting and managing patients who might discontinue treatment becomes necessary. Accordingly, we developed a machine learning (ML) algorithm to predict which the risk of patients dropping out of outpatient treatment schemes. Methods: A total of 839 patients were selected out of 2,206 patients admitted for AUD in three hospitals under the Catholic Central Medical Center in Korea. We implemented six ML models—logistic regression, support vector machine, k-nearest neighbor, random forest, neural network, and AdaBoost—and compared the prediction performances thereof. Results: Among the six models, AdaBoost was selected as the final model for recommended use owing to its area under the receiver operating characteristic curve (AUROC) of 0.72. The four variables affecting the prediction based on feature importance were the length of hospitalization, age, residential area, and diabetes. Conclusion: An ML algorithm was developed herein to predict the risk of patients with AUD in Korea discontinuing outpatient treatment. By testing and validating various machine learning models, we determined the best performing model, AdaBoost, as the final model for recommended use. Using this model, clinicians can manage patients with high risks of discontinuing treatment and establish patient-specific treatment strategies. Therefore, our model can potentially enable patients with AUD to successfully complete their treatments by identifying them before they can drop out. [ABSTRACT FROM AUTHOR]

In the context of the current global pandemic and the limitations of the RT-PCR test, we propose a novel deep learning architecture, DFCN (Denoising Fully Connected Network). Since medical facilities around the world differ enormously in what laboratory tests or chest imaging may be available, DFCN is designed to be robust to missing input data. An ablation study extensively evaluates the performance benefits of the DFCN as well as its robustness to missing inputs. Data from 1088 patients with confirmed RT-PCR results are obtained from two independent medical facilities. The data includes results from 27 laboratory tests and a chest x-ray scored by a deep learning model. Training and test datasets are taken from different medical facilities. Data is made publicly available. The performance of DFCN in predicting the RT-PCR result is compared with 3 related architectures as well as a Random Forest baseline. All models are trained with varying levels of masked input data to encourage robustness to missing inputs. Missing data is simulated at test time by masking inputs randomly. DFCN outperforms all other models with statistical significance using random subsets of input data with 2-27 available inputs. When all 28 inputs are available DFCN obtains an AUC of 0.924, higher than any other model. Furthermore, with clinically meaningful subsets of parameters consisting of just 6 and 7 inputs respectively, DFCN achieves higher AUCs than any other model, with values of 0.909 and 0.919. [ABSTRACT FROM AUTHOR]

Identifying the factors controlling the spatial variability of soil metal elements could be a challenge task due to the interaction of environmental attributes and human activities. This study aimed to investigate the critical explanatory variables controlling total Ca, Cd, Cr, Cu, Zn, Fe, Mn, Mg, Pb, and Zn variations in the arable topsoil using classical statistics, principal component analysis, and random forest techniques. The work was conducted in the core region of the Three Gorges Reservoir of China. The explanatory variables included soil, topography, climate, vegetation, land use type, and distance-related parameters. Average concentrations of the metal elements were in order of Fe > Mg > Ca > Mn > Zn > Cr > Ni > Pb > Cu > Cd. Soil Cr, Fe, and Pb showed low variability while others presented medium variability. Average concentrations of Cr, Fe, Cd, and Mg exceeded their corresponding background values. There were highly positive correlations between all metal elements except Pb, Cd and Cr. The principal component analysis further demonstrated that the sources of Pb, Cd, and Cr differed with other elements. The results of random forest suggested that soil properties followed by topography were critical parameters affecting the variations of Ca, Mg, Mn, Fe, Ni, Zn, and Cu. Agricultural activities and soil properties were major factors controlling the variations of Pb, Cr, and Cd. Further study should be conducted to understand the relations between the metal elements and soil properties. [ABSTRACT FROM AUTHOR]

The aim of the current study was to investigate the relation between reticulorumen contractions and monitored cow behaviors. A purpose-built pressure measuring device was used and shown to be capable of detecting the known contraction patterns in the reticulorumen of four rumen-fistulated cows. Reticular pressure data was used to build a random forest algorithm, a learning algorithm based on a combination of decision trees, to detect rumination and other cow behaviors. In addition, we developed a peak-detection algorithm for rumination based on visual inspection of patterns in reticular pressure. Cow behaviors, differentiated in ruminating, eating, drinking, sleeping and 'other', as scored from video observation, were used to develop and test the algorithms. The results demonstrated that rumination of a cow can be detected by measuring pressure differences in the reticulum using either the random forest algorithm or the peak-detection algorithm. The random forest algorithm showed very robust performances for detecting rumination with an accuracy of 0.98, a sensitivity of 0.95 and a specificity of 0.99. The peak-detection algorithm could detect rumination robustly, with an accuracy of 0.92, a sensitivity of 0.97 and a specificity of 0.90. In addition, we provide proof of principle that a random forest algorithm can also detect eating, drinking and sleeping behavior from the same data with performances above 0.90 for all measures. The measurement device used in this study needed rumen-fistulated cows, but the results indicate that behavior detection using algorithms based on only measurements in the reticulum is feasible. This is promising as it may allow future wireless sensor techniques in the reticulum to continuously monitor a range of important behaviors of cows. [ABSTRACT FROM AUTHOR]

Aim: The aim was to predict and understand variations in swimmer performance between individual and relay events, and develop a predictive model for the 4x200-m swimming freestyle relay event to help inform team selection and strategy. Data and methods: Race data for 716 relay finals (4 x 200-m freestyle) from 14 international competitions between 2010–2018 were analysed. Individual 200-m freestyle season best time for the same year was located for each swimmer. Linear regression and machine learning was applied to 4 x 200-m swimming freestyle relay events. Results: Compared to the individual event, the lowest ranked swimmer in the team (-0.62 s, CI = [−0.94, −0.30]) and American swimmers (−0.48 s [−0.89, −0.08]) typically swam faster 200-m times in relay events. Random forest models predicted gold, silver, bronze and non-medal with 100%, up to 41%, up to 63%, and 93% sensitivity, respectively. Discussion: Team finishing position was strongly associated with the differential time to the fastest team (mean decrease in Gini (MDG) when this variable was omitted = 31.3), world rankings of team members (average ranking MDG of 18.9), and the order of swimmers (MDG = 6.9). Differential times are based on the sum of individual swimmer's season's best times, and along with world rankings, reflect team strength. In contrast, the order of swimmers reflects strategy. This type of analysis could assist coaches and support staff in selecting swimmers and team orders for relay events to enhance the likelihood of success. [ABSTRACT FROM AUTHOR]

Due to difficulty in early diagnosis of Alzheimer's disease (AD) related to cost and differentiated capability, it is necessary to identify low-cost, accessible, and reliable tools for identifying AD risk in the preclinical stage. We hypothesized that cognitive ability, as expressed in the vocal features in daily conversation, is associated with AD progression. Thus, we have developed a novel machine learning prediction model to identify AD risk by using the rich voice data collected from daily conversations, and evaluated its predictive performance in comparison with a classification method based on the Japanese version of the Telephone Interview for Cognitive Status (TICS-J). We used 1,465 audio data files from 99 Healthy controls (HC) and 151 audio data files recorded from 24 AD patients derived from a dementia prevention program conducted by Hachioji City, Tokyo, between March and May 2020. After extracting vocal features from each audio file, we developed machine-learning models based on extreme gradient boosting (XGBoost), random forest (RF), and logistic regression (LR), using each audio file as one observation. We evaluated the predictive performance of the developed models by describing the receiver operating characteristic (ROC) curve, calculating the areas under the curve (AUCs), sensitivity, and specificity. Further, we conducted classifications by considering each participant as one observation, computing the average of their audio files' predictive value, and making comparisons with the predictive performance of the TICS-J based questionnaire. Of 1,616 audio files in total, 1,308 (81.0%) were randomly allocated to the training data and 308 (19.1%) to the validation data. For audio file-based prediction, the AUCs for XGboost, RF, and LR were 0.863 (95% confidence interval [CI]: 0.794–0.931), 0.882 (95% CI: 0.840–0.924), and 0.893 (95%CI: 0.832–0.954), respectively. For participant-based prediction, the AUC for XGboost, RF, LR, and TICS-J were 1.000 (95%CI: 1.000–1.000), 1.000 (95%CI: 1.000–1.000), 0.972 (95%CI: 0.918–1.000) and 0.917 (95%CI: 0.918–1.000), respectively. There was difference in predictive accuracy of XGBoost and TICS-J with almost approached significance (p = 0.065). Our novel prediction model using the vocal features of daily conversations demonstrated the potential to be useful for the AD risk assessment. [ABSTRACT FROM AUTHOR]

While it is generally accepted that language and speech have genetic foundations, and that the widespread inter-individual variation observed in many of their aspects is partly driven by variation in genes, it is much less clear if differences between languages may also be partly rooted in our genes. One such proposal is that the population frequencies of the so-called "derived" alleles of two genes involved in brain growth and development, ASPM and Microcephalin, are related to the probability of speaking a tone language or not. The original study introducing this proposal used a cross-linguistic statistical approach, showing that these associations are "special" when compared with many other possible relationships between genetic variants and linguistic features. Recent experimental evidence supports strongly a negative effect of the "derived" allele of ASPM on tone perception and/or processing within individuals, but failed to find any effect for Microcephalin. Motivated by these experimental findings, I conduct here a cross-linguistic statistical test, using a larger and updated dataset of 175 samples from 129 unique (meta)populations, and a battery of methods including mixed-effects regression (Bayesian and maximum-likelihood), mediation and path analysis, decision trees and random forests, using permutations and restricted sampling to control for the confounding effects of genealogy (language families) and contact (macroareas). Overall, the results support a negative weak effect of ASPM-D against the presence of tone above and beyond the strong confounding influences of genealogy and contact, but they suggest that the original association between tone and MCPH1 might have been a false positive, explained by differences between populations and languages within and outside Africa. Thus, these cross-linguistic population-scale statistical results are fully consonant with the inter-individual-level experimental results, and suggest that the observed linguistic diversity may be, at least in some cases, partly driven by genetic diversity. [ABSTRACT FROM AUTHOR]

Background: Deep neural networks learn from former experiences on a large scale and can be used to predict future disease activity as potential clinical decision support. AdaptiveNet is a novel adaptive recurrent neural network optimized to deal with heterogeneous and missing clinical data. Objective: We investigate AdaptiveNet for the prediction of individual disease activity in patients from a rheumatoid arthritis (RA) registry. Methods: Demographic and disease characteristics from over 9500 patients and 65.000 visits from the Swiss Quality Management (SCQM) database were used to train and evaluate the network. Patient characteristics, clinical and patient reported outcomes, laboratory values and medication were used as input features. DAS28-BSR served as a target to predict active RA and future numeric individual disease activity by classification and regression. Results: AdaptiveNet predicted active disease defined as DAS28-BSR >2.6 at the next visit with an overall accuracy of 75.6% (SD +- 0.7%) and a sensitivity and specificity of 84.2% (SD +- 1.6%) and 61.5% (SD +- 3.6%), respectively. Prediction performance was significantly higher in patients with a disease duration >3 years and positive rheumatoid factor. Regression allowed forecasting individual DAS28-BSR values with a mean squared error (MSE) of 0.9 (SD +- 0.05). This corresponds to a 8% deviation between estimated and real DAS28-BSR values. Compared to linear regression, random forest and support vector machines, AdaptiveNet showed an increased performance of over 7% in MSE. Medication played a minor role in the prediction of RA disease activity. Conclusion: AdaptiveNet has a superior capacity to predict numeric RA disease activity compared to classical machine learning architectures. All investigated models had limitations in low specificity. [ABSTRACT FROM AUTHOR]

Aims: Malnutrition is a major health issue among Bangladeshi under-five (U5) children. Children are malnourished if the calories and proteins they take through their diet are not sufficient for their growth and maintenance. The goal of the research was to use machine learning (ML) algorithms to detect the risk factors of malnutrition (stunted, wasted, and underweight) as well as their prediction. Methods: This work utilized malnutrition data that was derived from Bangladesh Demographic and Health Survey which was conducted in 2014. The selected dataset consisted of 7079 children with 13 factors. The potential risks of malnutrition have been identified by logistic regression (LR). Moreover, 3 ML classifiers (support vector machine (SVM), random forest (RF), and LR) have been implemented for predicting malnutrition and the performance of these ML algorithms were assessed on the basis of accuracy. Results: The average prevalence of stunted, wasted, and underweight was 35.4%, 15.4%, and 32.8%, respectively. It was noted that LR identified five risk factors for stunting and underweight, as well as four factors for wasting. Results illustrated that RF can be accurately classified as stunted, wasted, and underweight children and obtained the highest accuracy of 88.3% for stunted, 87.7% for wasted, and 85.7% for underweight. Conclusion: This research focused on the identification and prediction of major risk factors for stunting, wasting, and underweight using ML algorithms which will aid policymakers in reducing malnutrition among Bangladesh's U5 children. [ABSTRACT FROM AUTHOR]

Sarcasm is the main reason behind the faulty classification of tweets. It brings a challenge in natural language processing (NLP) as it hampers the method of finding people's actual sentiment. Various feature engineering techniques are being investigated for the automatic detection of sarcasm. However, most related techniques have always concentrated only on the content-based features in sarcastic expression, leaving the contextual information in isolation. This leads to a loss of the semantics of words in the sarcastic expression. Another drawback is the sparsity of the training data. Due to the word limit of microblog, the feature vector's values for each sample constructed by BoW produces null features. To address the above-named problems, a Multi-feature Fusion Framework is proposed using two classification stages. The first stage classification is constructed with the lexical feature only, extracted using the BoW technique, and trained using five standard classifiers, including SVM, DT, KNN, LR, and RF, to predict the sarcastic tendency. In stage two, the constructed lexical sarcastic tendency feature is fused with eight other proposed features for modelling a context to obtain a final prediction. The effectiveness of the developed framework is tested with various experimental analysis to obtain classifiers' performance. The evaluation shows that our constructed classification models based on the developed novel feature fusion obtained results with a precision of 0.947 using a Random Forest classifier. Finally, the obtained results were compared with the results of three baseline approaches. The comparison outcome shows the significance of the proposed framework. [ABSTRACT FROM AUTHOR]

Quantification of endogenous biomarkers in clinical studies requires careful evaluation of a number of assay performance parameters. Comparisons of absolute values from several clinical studies can enable retrospective analyses further elucidating the biology of a given biomarker across various study populations. We characterized the performance of a highly multiplex bioanalytical method for quantification of phosphatidylinositols (PI). Hydrophilic interaction chromatography (HILIC) and multiple reaction monitoring (MRM) were employed for targeted multiplex quantification. Odd-chain PI species that are not normally present in human plasma were utilized as surrogate analytes (SA) to assess various assay performance parameters and establish a definitive dynamic linear range for PI lipids. To correct for batch effects, Systematic Error Removal using Random Forest (SERRF) normalization algorithm was employed and used to bridge raw values between two clinical studies, enabling quantitative comparison of their absolute values. A high throughput method was developed, qualified, transferred to an automation platform and applied to sample testing in two clinical trials in healthy volunteers (NCT03001297) and stable Coronary Artery Disease (CAD, NCT03351738) subjects. The method demonstrated acceptable precision and accuracy (±30%) over linear range of 1–1000 nM for SA and 8-fold dilutional linearity for endogenous PI. We determined that mean-adjusted average QC performed best for normalization using SERRF. The comparison of two studies revealed that healthy subject levels of PI are consistently higher across PI species compared to CAD subjects identifying a potential lipid biomarker to be explored in future studies. [ABSTRACT FROM AUTHOR]

China became the country with the largest global carbon emissions in 2007. Cities are regional population and economic centers and are the main sources of carbon emissions. However, factors influencing carbon emissions from cities can vary with geographic location and the development history of the cities, rendering it difficult to explicitly quantify the influence of individual factors on carbon emissions. In this study, random forest (RF) machine learning algorithms were applied to analyze the relationships between factors and carbon emissions in cities using real-world data from Chinese cities. Seventy-three cities in three urban agglomerations within the Yangtze River Economic Belt were evaluated with respect to urban carbon emissions using data from regional energy balance tables for the years 2000, 2007, 2012, and 2017. The RF algorithm was then used to select 16 prototypical cities based on 10 influencing factors that affect urban carbon emissions while considering five primary factors: population, industry, technology levels, consumption, and openness to the outside world. Subsequently, 18 consecutive years of data from 2000 to 2017 were used to construct RFs to investigate the temporal predictability of carbon emission variation in the 16 cities based on regional differences. Results indicated that the RF approach is a practical tool to study the connection between various influencing factors and carbon emissions in the Yangtze River Economic Belt from different perspectives. Furthermore, regional differences among the primary carbon emission influencing factors for each city were clearly observed and were related to urban population characteristics, urbanization level, industrial structures, and degree of openness to the outside world. These factors variably affected different cities, but the results indicate that regional emission reductions have achieved positive results, with overall simulation trends shifting from underestimation to overestimation of emissions. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to develop and validate a claims-based, machine learning algorithm to predict clinical outcomes across both medical and surgical patient populations. Methods: This retrospective, observational cohort study, used a random 5% sample of 770,777 fee-for-service Medicare beneficiaries with an inpatient hospitalization between 2009–2011. The machine learning algorithms tested included: support vector machine, random forest, multilayer perceptron, extreme gradient boosted tree, and logistic regression. The extreme gradient boosted tree algorithm outperformed the alternatives and was the machine learning method used for the final risk model. Primary outcome was 30-day mortality. Secondary outcomes were: rehospitalization, and any of 23 adverse clinical events occurring within 30 days of the index admission date. Results: The machine learning algorithm performance was evaluated by both the area under the receiver operating curve (AUROC) and Brier Score. The risk model demonstrated high performance for prediction of: 30-day mortality (AUROC = 0.88; Brier Score = 0.06), and 17 of the 23 adverse events (AUROC range: 0.80–0.86; Brier Score range: 0.01–0.05). The risk model demonstrated moderate performance for prediction of: rehospitalization within 30 days (AUROC = 0.73; Brier Score: = 0.07) and six of the 23 adverse events (AUROC range: 0.74–0.79; Brier Score range: 0.01–0.02). The machine learning risk model performed comparably on a second, independent validation dataset, confirming that the risk model was not overfit. Conclusions and relevance: We have developed and validated a robust, claims-based, machine learning risk model that is applicable to both medical and surgical patient populations and demonstrates comparable predictive accuracy to existing risk models. [ABSTRACT FROM AUTHOR]

Biological pest control (i.e. 'biocontrol') agents can have direct and indirect non-target impacts, and predicting these effects (especially indirect impacts) remains a central challenge in biocontrol risk assessment. The analysis of ecological networks offers a promising approach to understanding the community-wide impacts of biocontrol agents (via direct and indirect interactions). Independently, species traits and phylogenies have been shown to successfully predict species interactions and network structure (alleviating the need to collect quantitative interaction data), but whether these approaches can be combined to predict indirect impacts of natural enemies remains untested. Whether predictions of interactions (i.e. direct effects) can be made equally well for generalists vs. specialists, abundant vs. less abundant species, and across different habitat types is also untested for consumer-prey interactions. Here, we used two machine-learning techniques (random forest and k-nearest neighbour; KNN) to test whether we could accurately predict empirically-observed quantitative host-parasitoid networks using trait and phylogenetic information. Then, we tested whether the accuracy of machine-learning-predicted interactions depended on the generality or abundance of the interacting partners, or on the source (habitat type) of the training data. Finally, we used these predicted networks to generate predictions of indirect effects via shared natural enemies (i.e. apparent competition), and tested these predictions against empirically observed indirect effects between hosts. We found that random-forest models predicted host-parasitoid pairwise interactions (which could be used to predict attack of non-target host species) more successfully than KNN. This predictive ability depended on the generality of the interacting partners for KNN models, and depended on species' abundances for both random-forest and KNN models, but did not depend on the source (habitat type) of data used to train the models. Further, although our machine-learning informed methods could significantly predict indirect effects, the explanatory power of our machine-learning models for indirect interactions was reasonably low. Combining machine-learning and network approaches provides a starting point for reducing risk in biocontrol introductions, and could be applied more generally to predicting species interactions such as impacts of invasive species. [ABSTRACT FROM AUTHOR]