A Random Forest Approach for Bounded Outcome Variables.
Ontology highlight
ABSTRACT:
SUBMITTER: Weinhold L
PROVIDER: S-EPMC8193767 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Missing data are a common issue in statistical analyses. Multiple imputation is a technique that has been applied in countless research studies and has a strong theoretical basis. Most of the statistical literature on multiple imputation has focused on unbounded continuous variables, with mostly ad hoc remedies for variables with bounded support. These approaches can be unsatisfactory when applied to bounded variables as they can produce misleading inferences. In this paper, we propose a flexible quantile-based imputation model suitable for distributions defined over singly or doubly bounded intervals. Proper support of the imputed values is ensured by applying a family of transformations with singly or doubly bounded range. Simulation studies demonstrate that our method is able to deal with skewness, bimodality, and heteroscedasticity and has superior properties as compared to competing approaches, such as log-normal imputation and predictive mean matching. We demonstrate the application of the proposed imputation procedure by analysing data on mathematical development scores in children from the Millennium Cohort Study, UK. We also show a specific advantage of our methods using a small psychiatric dataset. Our methods are relevant in a number of fields, including education and psychology.
| S-EPMC6662738 | biostudies-literature
Project description:BACKGROUND:Sudden unexpected death in epilepsy (SUDEP) is second only to stroke in neurological events resulting in years of potential life lost. Postictal generalized electroencephalogram (EEG) suppression (PGES) is a period of suppressed brain activity often occurring after generalized tonic-clonic seizure, a most significant risk factor for SUDEP. Therefore, PGES has been considered as a potential biomarker for SUDEP risk. Automatic PGES detection tools can address the limitations of labor-intensive, and sometimes inconsistent, visual analysis. A successful approach to automatic PGES detection must overcome computational challenges involved in the detection of subtle amplitude changes in EEG recordings, which may contain physiological and acquisition artifacts. OBJECTIVE:This study aimed to present a random forest approach for automatic PGES detection using multichannel human EEG recordings acquired in epilepsy monitoring units. METHODS:We used a combination of temporal, frequency, wavelet, and interchannel correlation features derived from EEG signals to train a random forest classifier. We also constructed and applied confidence-based correction rules based on PGES state changes. Motivated by practical utility, we introduced a new, time distance-based evaluation method for assessing the performance of PGES detection algorithms. RESULTS:The time distance-based evaluation showed that our approach achieved a 5-second tolerance-based positive prediction rate of 0.95 for artifact-free signals. For signals with different artifact levels, our prediction rates varied from 0.68 to 0.81. CONCLUSIONS:We introduced a feature-based, random forest approach for automatic PGES detection using multichannel EEG recordings. Our approach achieved increasingly better time distance-based performance with reduced signal artifact levels. Further study is needed for PGES detection algorithms to perform well irrespective of the levels of signal artifacts.
| S-EPMC7055778 | biostudies-literature
Project description:Random forest and similar Machine Learning techniques are already used to generate spatial predictions, but spatial location of points (geography) is often ignored in the modeling process. Spatial auto-correlation, especially if still existent in the cross-validation residuals, indicates that the predictions are maybe biased, and this is suboptimal. This paper presents a random forest for spatial predictions framework (RFsp) where buffer distances from observation points are used as explanatory variables, thus incorporating geographical proximity effects into the prediction process. The RFsp framework is illustrated with examples that use textbook datasets and apply spatial and spatio-temporal prediction to numeric, binary, categorical, multivariate and spatiotemporal variables. Performance of the RFsp framework is compared with the state-of-the-art kriging techniques using fivefold cross-validation with refitting. The results show that RFsp can obtain equally accurate and unbiased predictions as different versions of kriging. Advantages of using RFsp over kriging are that it needs no rigid statistical assumptions about the distribution and stationarity of the target variable, it is more flexible towards incorporating, combining and extending covariates of different types, and it possibly yields more informative maps characterizing the prediction error. RFsp appears to be especially attractive for building multivariate spatial prediction models that can be used as "knowledge engines" in various geoscience fields. Some disadvantages of RFsp are the exponentially growing computational intensity with increase of calibration data and covariates and the high sensitivity of predictions to input data quality. The key to the success of the RFsp framework might be the training data quality-especially quality of spatial sampling (to minimize extrapolation problems and any type of bias in data), and quality of model validation (to ensure that accuracy is not effected by overfitting). For many data sets, especially those with lower number of points and covariates and close-to-linear relationships, model-based geostatistics can still lead to more accurate predictions than RFsp.
| S-EPMC6119462 | biostudies-literature
Project description:Notational analysis is a popular tool for understanding what constitutes optimal performance in traditional sports. However, this approach has been seldom used in esports. The popular esport "Rocket League" is an ideal candidate for notational analysis due to the availability of an online repository containing data from millions of matches. The purpose of this study was to use Random Forest models to identify in-match metrics that predicted match outcome (performance indicators or "PIs") and/or in-game player rank (rank indicators or "RIs"). We evaluated match data from 21,588 Rocket League matches involving players from four different ranks. Upon identifying goal difference (GD) as a suitable outcome measure for Rocket League match performance, Random Forest models were used alongside accompanying variable importance methods to identify metrics that were PIs or RIs. We found shots taken, shots conceded, saves made, and time spent goalside of the ball to be the most important PIs, and time spent at supersonic speed, time spent on the ground, shots conceded and time spent goalside of the ball to be the most important RIs. This work is the first to use Random Forest learning algorithms to highlight the most critical PIs and RIs in a prominent esport.
| S-EPMC8481284 | biostudies-literature
Project description:BACKGROUND:Random forest (RF) is a machine-learning method that generally works well with high-dimensional problems and allows for nonlinear relationships between predictors; however, the presence of correlated predictors has been shown to impact its ability to identify strong predictors. The Random Forest-Recursive Feature Elimination algorithm (RF-RFE) mitigates this problem in smaller data sets, but this approach has not been tested in high-dimensional omics data sets. RESULTS:We integrated 202,919 genotypes and 153,422 methylation sites in 680 individuals, and compared the abilities of RF and RF-RFE to detect simulated causal associations, which included simulated genotype-methylation interactions, between these variables and triglyceride levels. Results show that RF was able to identify strong causal variables with a few highly correlated variables, but it did not detect other causal variables. CONCLUSIONS:Although RF-RFE decreased the importance of correlated variables, in the presence of many correlated variables, it also decreased the importance of causal variables, making both hard to detect. These findings suggest that RF-RFE may not scale to high-dimensional data.
| S-EPMC6157185 | biostudies-literature
Project description:BackgroundToll-like receptor 9 is a key innate immune receptor involved in detecting infectious diseases and cancer. TLR9 activates the innate immune system following the recognition of single-stranded DNA oligonucleotides (ODN) containing unmethylated cytosine-guanine (CpG) motifs. Due to the considerable number of rotatable bonds in ODNs, high-throughput in silico screening for potential TLR9 activity via traditional structure-based virtual screening approaches of CpG ODNs is challenging. In the current study, we present a machine learning based method for predicting novel mouse TLR9 (mTLR9) agonists based on features including count and position of motifs, the distance between the motifs and graphically derived features such as the radius of gyration and moment of Inertia. We employed an in-house experimentally validated dataset of 396 single-stranded synthetic ODNs, to compare the results of five machine learning algorithms. Since the dataset was highly imbalanced, we used an ensemble learning approach based on repeated random down-sampling.ResultsUsing in-house experimental TLR9 activity data we found that random forest algorithm outperformed other algorithms for our dataset for TLR9 activity prediction. Therefore, we developed a cross-validated ensemble classifier of 20 random forest models. The average Matthews correlation coefficient and balanced accuracy of our ensemble classifier in test samples was 0.61 and 80.0%, respectively, with the maximum balanced accuracy and Matthews correlation coefficient of 87.0% and 0.75, respectively. We confirmed common sequence motifs including 'CC', 'GG','AG', 'CCCG' and 'CGGC' were overrepresented in mTLR9 agonists. Predictions on 6000 randomly generated ODNs were ranked and the top 100 ODNs were synthesized and experimentally tested for activity in a mTLR9 reporter cell assay, with 91 of the 100 selected ODNs showing high activity, confirming the accuracy of the model in predicting mTLR9 activity.ConclusionWe combined repeated random down-sampling with random forest to overcome the class imbalance problem and achieved promising results. Overall, we showed that the random forest algorithm outperformed other machine learning algorithms including support vector machines, shrinkage discriminant analysis, gradient boosting machine and neural networks. Due to its predictive performance and simplicity, the random forest technique is a useful method for prediction of mTLR9 ODN agonists.
| S-EPMC6924143 | biostudies-literature
Project description:BackgroundPlant innate immunity relies on a broad repertoire of receptor proteins that can detect pathogens and trigger an effective defense response. Bioinformatic tools based on conserved domain and sequence similarity are within the most popular strategies for protein identification and characterization. However, the multi-domain nature, high sequence diversity and complex evolutionary history of disease resistance (DR) proteins make their prediction a real challenge. Here we present RFPDR, which pioneers the application of Random Forest (RF) for Plant DR protein prediction.MethodsA recently published collection of experimentally validated DR proteins was used as a positive dataset, while 10x10 nested datasets, ranging from 400-4,000 non-DR proteins, were used as negative datasets. A total of 9,631 features were extracted from each protein sequence, and included in a full dimension (FD) RFPDR model. Sequence selection was performed, to generate a reduced-dimension (RD) RFPDR model. Model performances were evaluated using an 80/20 (training/testing) partition, with 10-cross fold validation, and compared to baseline, sequence-based and state-of-the-art strategies. To gain some insights into the underlying biology, the most discriminatory sequence-based features in the RF classifier were identified.Results and discussionRD-RFPDR showed to be sensitive (86.4 ± 4.0%) and specific (96.9 ± 1.5%) for identifying DR proteins, while robust to data imbalance. Its high performance and robustness, added to the fact that RD-RFPDR provides valuable information related to DR proteins underlying properties, make RD-RFPDR an interesting approach for DR protein prediction, complementing the state-of-the-art strategies.
| S-EPMC9037127 | biostudies-literature
Project description:The Tropical Andes region includes biodiversity hotspots of high conservation priority whose management strategies depend on the analysis of forest dynamics drivers (FDDs). These depend on complex social and ecological interactions that manifest on different space-time scales and are commonly evaluated through regression analysis of multivariate datasets. However, processing such datasets is challenging, especially when time series are used and inconsistencies in data collection complicate their integration. Moreover, regression analysis in FDD characterization has been criticized for failing to capture spatial variability; therefore, alternatives such as geographically weighted regression (GWR) have been proposed, but their sensitivity to multicollinearity has not yet been solved. In this scenario, we present an innovative methodology that combines techniques to: 1) derive remote sensing time series products; 2) improve census processing with dasymetric mapping; 3) combine GWR and random forest (RF) to derive local variables importance; and 4) report results based in a clustering and hypothesis testing. We applied this methodology in the northwestern Ecuadorian Amazon, a highly heterogeneous region characterized by different active fronts of deforestation and reforestation, within the time period 2000-2010. Our objective was to identify linkages between these processes and validate the potential of the proposed methodology. Our findings indicate that land-use intensity proxies can be extracted from remote sensing time series, while intercensal analysis can be facilitated by calculating population density maps. Moreover, our implementation of GWR with RF achieved accurate predictions above the 74% using the out-of-bag samples, demonstrating that derived RF features can be used to construct hypothesis and discuss forest change drivers with more detailed information. In the other hand, our analysis revealed contrasting effects between deforestation and reforestation for variables related to suitability to agriculture and accessibility to its facilities, which is also reflected according patch size, land cover and population dynamics patterns. This approach demonstrates the benefits of integrating remote sensing-derived products and socioeconomic data to understand coupled socioecological systems more from a local than a global scale.
| S-EPMC6927660 | biostudies-literature
Project description:BackgroundThe outbreak of coronavirus disease 2019 (COVID-19) that occurred in Wuhan, China, has become a global public health threat. It is necessary to identify indicators that can be used as optimal predictors for clinical outcomes of COVID-19 patients.MethodsThe clinical information from 126 patients diagnosed with COVID-19 were collected from Wuhan Fourth Hospital. Specific clinical characteristics, laboratory findings, treatments and clinical outcomes were analyzed from patients hospitalized for treatment from 1 February to 15 March 2020, and subsequently died or were discharged. A random forest (RF) algorithm was used to predict the prognoses of COVID-19 patients and identify the optimal diagnostic predictors for patients' clinical prognoses.ResultsSeven of the 126 patients were excluded for losing endpoints, 103 of the remaining 119 patients were discharged (alive) and 16 died in the hospital. A synthetic minority over-sampling technique (SMOTE) was used to correct the imbalanced distribution of clinical patients. Recursive feature elimination (RFE) was used to select the optimal subset for analysis. Eleven clinical parameters, Myo, CD8, age, LDH, LMR, CD45, Th/Ts, dyspnea, NLR, D-Dimer and CK were chosen with AUC approximately 0.9905. The RF algorithm was built to predict the prognoses of COVID-19 patients based on the best subset, and the area under the ROC curve (AUC) of the test data was 100%. Moreover, two optimal clinical risk predictors, lactate dehydrogenase (LDH) and Myoglobin (Myo), were selected based on the Gini index. The univariable logistic analysis revealed a substantial increase in the risk for in-hospital mortality when Myo was higher than 80 ng/ml (OR = 7.54, 95% CI [3.42-16.63]) and LDH was higher than 500 U/L (OR = 4.90, 95% CI [2.13-11.25]).ConclusionWe applied an RF algorithm to predict the mortality of COVID-19 patients with high accuracy and identified LDH higher than 500 U/L and Myo higher than 80 ng/ml to be potential risk factors for the prognoses of COVID-19 patients in the early stage of the disease.
| S-EPMC7486830 | biostudies-literature
Project description:Instrumental variables (IVs) are widely used for estimating causal effects in the presence of unmeasured confounding. Under the standard IV model, however, the average treatment effect (ATE) is only partially identifiable. To address this, we propose novel assumptions that allow for identification of the ATE. Our identification assumptions are clearly separated from model assumptions needed for estimation, so that researchers are not required to commit to a specific observed data model in establishing identification. We then construct multiple estimators that are consistent under three different observed data models, and multiply robust estimators that are consistent in the union of these observed data models. We pay special attention to the case of binary outcomes, for which we obtain bounded estimators of the ATE that are guaranteed to lie between -1 and 1. Our approaches are illustrated with simulations and a data analysis evaluating the causal effect of education on earnings.
| S-EPMC6051728 | biostudies-literature