Development of an equation to predict delta bilirubin levels using machine learning.

OBJECTIVE: Delta bilirubin (albumin-covalently bound bilirubin) may provide important clinical utility in identifying impaired hepatic excretion of conjugated bilirubin, but it cannot be measured in real-time for diagnostic purposes in clinical laboratories. METHODS: A total of 210 samples were collected, and their delta bilirubin levels were measured four times using high-performance liquid chromatography. Data collected included age, sex, diagnosis code, delta bilirubin, total bilirubin, direct bilirubin, total protein, albumin, globulin, aspartate aminotransferase, alanine transaminase, alkaline phosphatase, gamma-glutamyl transferase, lactate dehydrogenase, hemoglobin, serum hemolysis value, hemolysis index, icterus value (Iv), icterus index (Ii), lipemia value (Lv), and lipemia index. To conduct feature selection and identify the optimal combination of variables, linear regression machine learning was performed 1,000 times. RESULTS: The selected variables were total bilirubin, direct bilirubin, total protein, albumin, hemoglobin, Iv, Ii, and Lv. The best predictive performance for high delta bilirubin concentrations was achieved with the combination of albumin-direct bilirubin-hemoglobin-Iv-Lv. The final equation composed of these variables was as follows: delta bilirubin = 0.35 × Iv + 0.05 × Lv - 0.23 × direct bilirubin - 0.05 × hemoglobin - 0.04 × albumin + 0.10. CONCLUSION: The equation established in this study is practical and can be easily applied in real-time in clinical laboratories.

Insight into the sorption and desorption pattern of pyrrolizidine alkaloids and their N-oxides in acidic tea (Camellia sinensis) plantation soils.

Pyrrolizidine alkaloids (PAs) and their N-oxides (PANOs) are phytotoxins produced by various plant species and have been emerged as environmental pollutants. The sorption/desorption behaviors of PAs/PANOs in soil are crucial due to the horizontal transfer of these natural products from PA-producing plants to soil and subsequently absorbed by plant roots. This study firstly investigated the sorption/desorption behaviors of PAs/PANOs in tea plantation soils with distinct characteristics. Sorption amounts for seneciphylline (Sp) and seneciphylline-N-oxide (SpNO) in three acidic soils ranged from 2.9 to 5.9 µg/g and 1.7 to 2.8 µg/g, respectively. Desorption percentages for Sp and SpNO were from 22.2% to 30.5% and 36.1% to 43.9%. In the mixed PAs/PANOs systems, stronger sorption of PAs over PANOs was occurred in tested soils. Additionally, the Freundlich models more precisely described the sorption/desorption isotherms. Cation exchange capacity, sand content and total nitrogen were identified as major influencing factors by linear regression models. Overall, the soils exhibiting higher sorption capacities for compounds with greater hydrophobicity. PANOs were more likely to migrate within soils and be absorbed by tea plants. It contributes to the understanding of environmental fate of PAs/PANOs in tea plantations and provides basic data and clues for the development of PAs/PANOs reduction technology.

Application of machine learning and deep learning techniques in modeling the associations between air pollution and meteorological parameters in urban areas of tehran metropolis.

Tehran, the most crowded city in Iran, suffers from severe air pollution, particularly during the cold months. This research endeavored to examine the statistical relationships between criteria air pollutants (CO, NO2, SO2, O3, PM10, and PM2.5) and meteorological elements (temperature, rainfall, wind speed, relative humidity, air pressure, sunshine hours, solar radiation, and cloudiness), as well as assess and compare the efficacy of six different algorithms (multiple linear regression (MLR), generalized additive model (GAM), classification and regression trees (CART), random forest (RF), gradient boosting machine (GBM), and deep learning (DL)) in modeling pollutants and climatic factors responsible for variations in Tehran's air pollution levels from 2001 to 2021 using R 4.3.2 software. The results of this study showed that O3 was strongly affected by weather conditions, while other pollutants were mainly influenced by each other than by meteorological parameters and more extensive research is required to pinpoint the precise impact of human activity on these pollutant levels in Tehran. Also based on the predictive model performance evaluation and concerning the principle of parsimony, in half of the cases, the MLR outperformed other models, despite its seeming simplicity and principal assumptions dependence. In other situations, the GAM was a good substitute.

An assessment of the relationship between spring frost indicators and global crop yield losses.

Reports on the influences of spring frost on crop losses are not consistent, which may be because insufficient indicators of spring frost were included in the analysis. To bridge this gap, we analyzed global temperature datasets and production data for the three major crops of maize, winter wheat, and rice from 1981 to 2016. Five indicators of spring frost events: temperature fluctuation (Tv), temperature difference (Td), duration (Thour), occurrence date (Tdate), and frequency (Tnum) were considered to assess their relationship with yield losses. Linear regression was employed to analyze the change trends in five indicators and random forest was utilized to investigate the relationship between yield loss and indicators of spring frost. Our findings reveal that, despite a decline in the number of spring frost events during global warming, not all the five indicators declined over time. Tv is the most important indicator for yield losses in maize and winter wheat, which shows an increasing trend in their growing regions and provides an explanation for the increasing yield losses of maize and winter wheat over time. Td is the most important indicator of rice yield losses but it shows a decreasing trend in rice-growing areas, which explains why rice yield losses from spring frosts in recent years are not significant.

Interaction between the oxidative balance score and serum per- and poly-fluoroalkyl substances (PFASs) on liver health: analysis of the NHANES 2007-2018 dataset.

BACKGROUND: Per- and poly-fluoroalkyl substances (PFASs) are pervasive synthetic compounds, prompting investigations into their intricate interactions with lifestyle factors and health indicators because of their enduring environmental presence and bioaccumulation. This study aimed to explore the effects of the oxidative balance score (OBS) and PFAS on liver-related indices. METHODS: Twenty dietary and lifestyle factors were used to calculate the OBS. The serum concentrations of PFASs were measured, and their sum was calculated for analysis. The levels of liver markers were also evaluated. Linear regression models and interaction analyses were used to assess the associations between OBS, PFAS concentrations, and liver indices. RESULTS: The results revealed an inverse association between high OBS and perfluorooctane sulfonic acid concentration, as well as the sum of PFAS concentrations. OBS was positively associated with liver markers. The PFAS concentrations were positively associated with total bilirubin, alanine aminotransferase (ALT), and aspartate aminotransferase (AST) levels. Interaction analyses revealed significant interactions between OBS and specific PFASs for alkaline phosphatase (interaction P < 0.05). Possible interactions were also found between OBS and specific PFASs for ALT, and AST levels (interaction P < 0.10). CONCLUSIONS: This study clarified the association between total PFAS and OBS. This association was significant mainly for diet-related OBS. PFAS and OBS are associated with liver-related indicators in the blood.

Investigation of Rheological Properties of Molten Materials for Dripping Pills Based on Imaging Monitoring.

INTRODUCTION: Rheological properties, as critical material attributes (CMAs) of solid dispersion drugs such as dripping pills, affect the melting, dispersion, and solidification. Therefore, characterization and assessments of rheological properties in the pharmaceutical process are important in enhancing drug stability and bioavailability. OBJECTIVES: The study aimed to develop a method for analyzing the rheology of molten materials, assessing their consistency and how rheological properties affect the dripping process and pills quality. MATERIALS AND METHODS: The rheological behavior of molten materials composed of Ginkgo biloba leaf extract (GBE) and polyethylene glycol (PEG) 4000 was characterized. Batch consistency of molten materials was evaluated. Image monitoring technology was utilized to capture and process images of the droplet formation process. We established the relationship between the rheological properties of molten materials and various attributes. RESULTS: The quality consistency of molten materials was evaluated, with 12 batches showing similarity above 0.8. The MLR models showed strong correlations (R2 > 0.80) between rheological properties and evaluation attributes. The rheological properties, including consistency coefficient, flow index, and viscosity at 80°C, were identified as critical rheological properties of the molten materials. Rheological property differences of molten materials have an impact on the morphology of droplet and quality performance. CONCLUSION: A rheological method was established, enabling quality consistency evaluation of molten materials in dripping pills. This study revealed the influence of rheological properties on droplet formation process and dripping pills quality, providing a reference for researches on material attributes control of other traditional Chinese medicine dripping pills.

Leveraging External Aggregated Information for the Marginal Accelerated Failure Time Model.

It is becoming increasingly common for researchers to consider leveraging information from external sources to enhance the analysis of small-scale studies. While much attention has focused on univariate survival data, correlated survival data are prevalent in epidemiological investigations. In this article, we propose a unified framework to improve the estimation of the marginal accelerated failure time model with correlated survival data by integrating additional information given in the form of covariate effects evaluated in a reduced accelerated failure time model. Such auxiliary information can be summarized by using valid estimating equations and hence can then be combined with the internal linear rank-estimating equations via the generalized method of moments. We investigate the asymptotic properties of the proposed estimator and show that it is more efficient than the conventional estimator using internal data only. When population heterogeneity exists, we revise the proposed estimation procedure and present a shrinkage estimator to protect against bias and loss of efficiency. Moreover, the proposed estimation procedure can be further refined to accommodate the non-negligible uncertainty in the auxiliary information, leading to more trustable inference conclusions. Simulation results demonstrate the finite sample performance of the proposed methods, and empirical application on the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial substantiates its practical relevance.

Study of SME employees' awareness level on lean manufacturing and ergonomics implementation in Malaysian and Indonesian production environments.

SMEs are small to medium-sized businesses with relatively fewer workers and lower revenues than large companies. However, SMEs also contribute to the local economic growth of a region, so the smooth production process needs to be considered to increase productivity. Applying lean manufacturing (LM) and Ergonomics concepts in the production process is critical because it can overcome smooth production and maintain the health and safety of SMEs workers. LM focuses on minimizing waste, while ergonomics focuses on humans as a source of energy in the smooth running of production activities. So, this study aims to measure the level of understanding of Malaysian and Indonesian SMEs workers on applying LM and Ergonomics concepts on the production floor and determine the effect of these two concepts using the SPSS and SmartPLS4 applications. SPSS serves to measure the validity, reliability and mean for the category of workers' understanding of LM and Ergonomics. SmartPLS4 helps us understand the influence of the two concepts. Based on the calculation of the mean for each variable of LM and ergonomics, it is found that Malaysian workers understand enough compared to Indonesian SMEs workers. As for the effect, Ergonomics has a significant influence on LM.

Association of household chemicals use with cognitive function among Chinese older adults.

Background: The paucity of empirical evidence supporting a correlation between the utilization of household chemicals and cognitive decline in Chinese older adults. Methods: The data utilized for this study originated from the Chinese Longitudinal Healthy Longevity Survey (CLHLS 2018). Using regression models to investigate the relationship between exposure to household chemicals and cognitive decline, and evaluate the impact of different fields on cognitive function. Results: The use of household chemicals was associated with a decline in cognitive function (anti-caries agent, OR = 1.68, P = 0.040; air freshener, OR = 2.48, P = 0.002; disinfectant, OR = 1.40, P = 0.033). The more frequent the use of household chemicals, the worse the cognitive function (Model1: OR = 2.54, P = 0.024; Model2: OR = 3.23, P = 0.006; Model3: OR = 3.59, P = 0.003). Conclusion: The study has uncovered a correlation between the utilization of household chemicals and cognitive decline in individuals aged 65 years and over in China.

A novel mathematical model for modeling viscosity and temperature relationship for dead oils.

Viscosity is crucial in subsurface and surface transport, used in engineering domains like heat transfer and pipeline design. However, measurements are limited, necessitating predictive viscosity relationships. Existing models lack precision or pertain to limited fluids, and accurately forecasting dead oil viscosity remains challenging due to errors. The study presents a mathematical algorithm to accurately estimate viscosity values in hydrocarbon fluids. It uses a robust non-linear regression technique to establish a reliable relationship between fluid viscosity and temperature within a specific temperature range. The algorithm is applied to extra-heavy to light crude oil samples from Iranian oilfields, revealing viscosity values ranging from 0.29 cp to 5328.74 cp within a dataset of 243 viscosity data points. After modeling each of these five fluids, the highest values obtained for the maximum absolute error and relative error are related to the fluid with an API gravity of 12.92. The maximum absolute error and relative error for this fluid sample are 1.25 cp and 6.04%, respectively. The algorithm offers acceptable precision in outcome models, even with limited training data, demonstrating its effectiveness in training models with less than 30% of available data. Moreover, these models end up with a near-unity coefficient of determination in testing data, reaffirming their proficiency at reflecting empirical data with remarkable accuracy.

Improving analysis of cognitive outcomes in cardiovascular trials using different statistical approaches.

BACKGROUND: The Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA) questionnaires are commonly used to measure global cognition in clinical trials. Because these scales are discrete and bounded with ceiling and floor effects and highly skewed, their analysis as continuous outcomes presents challenges. Normality assumptions of linear regression models are usually violated, which may result in failure to detect associations with variables of interest. METHODS: Alternative approaches to analyzing the results of these cognitive batteries include transformations (standardization, square root, or log transformation) of the scores in the multivariate linear regression (MLR) model, the use of nonlinear beta-binomial regression (which is not dependent on the assumption of normality), or Tobit regression, which adds a latent variable to account for bounded data. We aim to empirically compare the model performance of all proposed approaches using four large randomized controlled trials (ORIGIN, TRANSCEND, COMPASS, and NAVIGATE-ESUS), and using as metrics the Akaike information criterion (AIC). We also compared the treatment effects for the methods that have the same unit of measure (i.e., untransformed MLR, beta-binomial, and Tobit). RESULTS: The beta-binomial consistently demonstrated superior model performance, with the lowest AIC values among nearly all the approaches considered, followed by the MLR with square root and log transformations across all four studies. Notably, in ORIGIN, a substantial AIC reduction was observed when comparing the untransformed MLR to the beta-binomial, whereas other studies had relatively small AIC reductions. The beta-binomial model also resulted in a significant treatment effect in ORIGIN, while the untransformed MLR and Tobit regression showed no significance. The other three studies had similar and insignificant treatment effects among the three approaches. CONCLUSION: When analyzing discrete and bounded outcomes, such as cognitive scores, as continuous variables, a beta-binomial regression model improves model performance, avoids spurious significance, and allows for a direct interpretation of the actual cognitive measure. TRIALS REGISTRATION: ORIGIN (NCT00069784). Registered on October 1, 2003; TRANSCEND (NCT00153101). Registered on September 9, 2005; COMPASS (NCT01776424). Registered on January 24, 2013; NAVIGATE-ESUS (NCT02313909). Registered on December 8, 2014.

A Novel Modeling Optimization Approach for a Seven-Channel Titania Ceramic Membrane in an Oily Wastewater Filtration System Based on Experimentation, Full Factorial Design, and Machine Learning.

This comprehensive study looks at how operational conditions affect the performance of a novel seven-channel titania ceramic ultrafiltration membrane for the treatment of produced water. A full factorial design experiment (23) was conducted to study the effect of the cross-flow operating factors on the membrane permeate flux decline and the overall permeate volume. Eleven experimental runs were performed for three important process operating variables: transmembrane pressure (TMP), crossflow velocity (CFV), and filtration time (FT). Steady final membrane fluxes and permeate volumes were recorded for each experimental run. Under the optimized conditions (1.5 bar, 1 m/s, and 2 h), the membrane performance index demonstrated an oil rejection rate of 99%, a flux of 297 L/m2·h (LMH), a 38% overall initial flux decline, and a total permeate volume of 8.14 L. The regression models used for the steady-state membrane permeate flux decline and overall permeate volume led to the highest goodness of fit to the experimental data with a correlation coefficient of 0.999. A Multiple Linear Regression method and an Artificial Neural Network approach were also employed to model the experimental membrane permeate flux decline and analyze the impact of the operating conditions on membrane performance. The predictions of the Gaussian regression and the Levenberg-Marquardt backpropagation method were validated with a determination coefficient of 99% and a Mean Square Error of 0.07.

Based on the improved fuzzy analytic hierarchy and the TSE-MLR model energy consumption prediction of university: A case study.

The accurate prediction of building energy consumption on university campuses is a significant research area. Current studies often focus on predicting the energy consumption of specific building areas or individual equipment, and typically consider only one factor, limiting the accuracy and applicability of the predictions. This study introduces the Time Segmented Energy-Multiple Linear Regression (TSE-MLR) prediction model, which integrates the improved fuzzy analytic hierarchy and the multiple linear regression algorithm. The model is compared with traditional (MLR, BP) and advanced (RNN) models, and their various indexes are discussed and analyzed. By collecting meteorological and energy consumption data from the study site over the past 12 years, the key factors affecting energy consumption on the university campus were identified using the improved fuzzy analytic hierarchy. Subsequently, the TSE-MLR model was trained using energy consumption data from 2010 to 2016 and validated using data from 2017 to 2019. The prediction results of the TSE-MLR model were compared with those obtained through Multiple linear regression, BP neural networks, and RNN. The results demonstrated that the TSE-MLR model significantly reduced the prediction error by 13.8 % and exhibited higher accuracy compared to the other models. Therefore, the TSE-MLR model introduced in this study offers a new and effective approach to predicting university energy consumption and supporting energy management using existing data from university building operations across different periods.

Testing for a treatment effect in a selected subgroup.

There is a growing interest in clinical trials that investigate how patients may respond differently to an experimental treatment depending on the basis of some biomarker measured on a continuous scale, and in particular to identify some threshold value for the biomarker above which a positive treatment effect can be considered to have been demonstrated. This can be statistically challenging when the same data are used both to select the threshold and to test the treatment effect in the subpopulation that it defines. This paper describes a hierarchical testing framework to give familywise type I error rate control in this setting and proposes two specific tests that can be used within this framework. One, a simple test based on the estimated value from a linear regression model with treatment by biomarker interaction, is powerful but can lead to type I error rate inflation if the assumptions of the linear model are not met. The other is more robust to these assumptions, but can be slightly less powerful when the assumptions hold.

Prediction techniques of movie box office using neural networks and emotional mining.

Box office prediction is of great significance for understanding investment risks, class construction, promotion and distribution, and theater scheduling. However, due to the insufficient selection of influencing factors of movie box office, the currently existing prediction model restricts the prediction accuracy. A total of 34 influencing factors in 11 categories, such as heat index, movie types, release date, creators, first-day box office, were selected to study the prediction technology of movie box office. The Word2vec algorithm is used to construct a feature thesaurus for nouns in movie domain; adjectives and verbs with emotional coloring are used to construct an emotional dictionary based on the movie domain; and the TF-IDF algorithm is integrated to calculate the emotional scores of movie comments. A prediction method based on comments and Multivariate Linear Regression (MLR) is designed to analyze the relationship between the influencing factors and the movie box office, which provides an important basis for the prediction of the total box office, and also provides a decision-making reference for the movie industry and the related management departments. Incorporating comments as feature values to improve the accuracy, a prediction model based on comments and Convolutional Neural Network (CNN) is constructed. The results show that the average prediction accuracy of the MLR without comments, Back-Propagation Neural Network (BPNN), and CNN is 63.4%, 68.3%, and 71.9%, respectively, and after integrating the comments, the average prediction accuracy of the MLR and CNN is improved by 16.1% and 11.8%, respectively, and the prediction accuracy is significantly improved.

Performance enhancement of classifiers through Bio inspired feature selection methods for early detection of lung cancer from microarray genes.

Gene expression in the microarray is assimilated with redundant and high-dimensional information. Moreover, the information in the microarray genes mostly correlates with background noise. This paper uses dimensionality reduction and feature selection methods to employ a classification methodology for high-dimensional lung cancer microarray data. The approach is enforced in two phases; initially, the genes are dimensionally reduced through Hilbert Transform, Detrend Fluctuation Analysis and Least Square Linear Regression methods. The dimensionally reduced data is further optimized in the next phase using Elephant Herd optimization (EHO) and Cuckoo Search Feature selection methods. The classifiers used here are Bayesian Linear Discriminant, Naive Bayes, Random Forest, Decision Tree, SVM (Linear), SVM (Polynomial), and SVM (RBF). The classifier's performances are analysed with and without feature selection methods. The SVM (Linear) classifier with the DFA Dimensionality Reduction method and EHO feature selection achieved the highest accuracy of 92.26 % compared to other classifiers.

A novel DRL-guided sparse voxel decoding model for reconstructing perceived images from brain activity.

BACKGROUND: Due to the sparse encoding character of the human visual cortex and the scarcity of paired training samples for {images, fMRIs}, voxel selection is an effective means of reconstructing perceived images from fMRI. However, the existing data-driven voxel selection methods have not achieved satisfactory results. NEW METHOD: Here, a novel deep reinforcement learning-guided sparse voxel (DRL-SV) decoding model is proposed to reconstruct perceived images from fMRI. We innovatively describe voxel selection as a Markov decision process (MDP), training agents to select voxels that are highly involved in specific visual encoding. RESULTS: Experimental results on two public datasets verify the effectiveness of the proposed DRL-SV, which can accurately select voxels highly involved in neural encoding, thereby improving the quality of visual image reconstruction. COMPARISON WITH EXISTING METHODS: We qualitatively and quantitatively compared our results with the state-of-the-art (SOTA) methods, getting better reconstruction results. We compared the proposed DRL-SV with traditional data-driven baseline methods, obtaining sparser voxel selection results, but better reconstruction performance. CONCLUSIONS: DRL-SV can accurately select voxels involved in visual encoding on few-shot, compared to data-driven voxel selection methods. The proposed decoding model provides a new avenue to improving the image reconstruction quality of the primary visual cortex.

Dominant role of soil iron and organic matters in arsenic transfer from soil to plant in a mine area in Hunan Province, Central China.

The transfer of arsenic (As) from soil to plant could be significantly influenced by soil parameters through regulating soil As bioavailability. To distinguish the bioavailable As provided by soil and the As uptaken by plants, herein two different soil bioavailable were defined, namely potential soil bioavailable As (evaluated through the bioavailable fraction of As) and actual soil bioavailable As (assessed through plant bioaccumulation factor, BF, and BFavailable). To identify the dominant soil parameters for the two soil bioavailable As forms, soil and plant samples were collected from a former As mine site. The results showed that the potential bioavailable As only accounted for 1.77 to 11.43% in the sampled soils, while the BF and BFavailable in the sampled vegetables ranged from 0.00 to 1.01 and 0.01 to 17.87, respectively. Despite a similar proportion of As in the residual fraction, soil with higher pH and organic matter (OM) content and lower iron (Fe) content showed a higher potential soil bioavailable As. Correlation analysis indicated a relationship between the soil pH and potential soil bioavailable As (r = 0.543, p < 0.01) and between the soil Fe and actual soil bioavailable As (r = - 0.644, p < 0.05, r = - 0.594, p < 0.05). Stepwise multiple linear regression (SMLR) analysis was employed to identify the dominant soil parameters and showed that soil pH and phosphorus (P) content could be used to predict the potential soil bioavailable As (R2 = 0.69, p < 0.001). On the other hand, soil Fe and OM could be used to predict the actual soil bioavailable As (R2 = 0.18-0.86, p < 0.001-0.015, in different vegetables). These results suggest that different soil parameters affect potential and actual soil bioavailable As. Hence, soil Fe and OM are the most important parameters controlling As transfer from soil to plant in the investigated area.

Universal penalized regression (Elastic-net) model with differentially methylated promoters for oral cancer prediction.

BACKGROUND: DNA methylation showed notable potential to act as a diagnostic marker in many cancers. Many studies proposed DNA methylation biomarker in OSCC detection, while most of these studies are limited to specific cohorts or geographical location. However, the generalizability of DNA methylation as a diagnostic marker in oral cancer across different geographical locations is yet to be investigated. METHODS: We used genome-wide methylation data from 384 oral cavity cancer and normal tissues from TCGA HNSCC and eastern India. The common differentially methylated CpGs in these two cohorts were used to develop an Elastic-net model that can be used for the diagnosis of OSCC. The model was validated using 812 HNSCC and normal samples from different anatomical sites of oral cavity from seven countries. Droplet Digital PCR of methyl-sensitive restriction enzyme digested DNA (ddMSRE) was used for quantification of methylation and validation of the model with 22 OSCC and 22 contralateral normal samples. Additionally, pyrosequencing was used to validate the model using 46 OSCC and 25 adjacent normal and 21 contralateral normal tissue samples. RESULTS: With ddMSRE, our model showed 91% sensitivity, 100% specificity, and 95% accuracy in classifying OSCC from the contralateral normal tissues. Validation of the model with pyrosequencing also showed 96% sensitivity, 91% specificity, and 93% accuracy for classifying the OSCC from contralateral normal samples, while in case of adjacent normal samples we found similar sensitivity but with 20% specificity, suggesting the presence of early disease methylation signature at the adjacent normal samples. Methylation array data of HNSCC and normal tissues from different geographical locations and different anatomical sites showed comparable sensitivity, specificity, and accuracy in detecting oral cavity cancer with across. Similar results were also observed for different stages of oral cavity cancer. CONCLUSIONS: Our model identified crucial genomic regions affected by DNA methylation in OSCC and showed similar accuracy in detecting oral cancer across different geographical locations. The high specificity of this model in classifying contralateral normal samples from the oral cancer compared to the adjacent normal samples suggested applicability of the model in early detection.

Are Latent Factor Regression and Sparse Regression Adequate?

We propose the Factor Augmented (sparse linear) Regression Model (FARM) that not only admits both the latent factor regression and sparse linear regression as special cases but also bridges dimension reduction and sparse regression together. We provide theoretical guarantees for the estimation of our model under the existence of sub-Gaussian and heavy-tailed noises (with bounded (1 + ϑ) -th moment, for all ϑ > 0) respectively. In addition, the existing works on supervised learning often assume the latent factor regression or sparse linear regression is the true underlying model without justifying its adequacy. To fill in such an important gap on high-dimensional inference, we also leverage our model as the alternative model to test the sufficiency of the latent factor regression and the sparse linear regression models. To accomplish these goals, we propose the Factor-Adjusted deBiased Test (FabTest) and a two-stage ANOVA type test respectively. We also conduct large-scale numerical experiments including both synthetic and FRED macroeconomics data to corroborate the theoretical properties of our methods. Numerical results illustrate the robustness and effectiveness of our model against latent factor regression and sparse linear regression models.