Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement.
Ontology highlight
ABSTRACT:
SUBMITTER: Bartol K
PROVIDER: S-EPMC8914647 | biostudies-literature | 2022 Feb
REPOSITORIES: biostudies-literature
Publications
Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement.
Bartol Kristijan K Bojanić David D Petković Tomislav T Peharec Stanislav S Pribanić Tomislav T
Sensors (Basel, Switzerland) 20220228 5
We propose a linear regression model for the estimation of human body measurements. The input to the model only consists of the information that a person can self-estimate, such as height and weight. We evaluate our model against the state-of-the-art approaches for body measurement from point clouds and images, demonstrate the comparable performance with the best methods, and even outperform several deep learning models on public datasets. The simplicity of the proposed regression model makes it ...[more]
Similar Datasets
Project description: Not available
| S-EPMC11346807 | biostudies-literature
Project description:Deep learning methods have recently gained success in detecting left ventricular systolic dysfunction (LVSD) from electrocardiogram (ECG) waveforms. Despite their high level of accuracy, they are difficult to interpret and deploy broadly in the clinical setting. In this study, we set out to determine whether simpler models based on standard ECG measurements could detect LVSD with similar accuracy to that of deep learning models. Using an observational data set of 40 994 matched 12-lead ECGs and transthoracic echocardiograms, we trained a range of models with increasing complexity to detect LVSD based on ECG waveforms and derived measurements. The training data were acquired from the Stanford University Medical Center. External validation data were acquired from the Columbia Medical Center and the UK Biobank. The Stanford data set consisted of 40 994 matched ECGs and echocardiograms, of which 9.72% had LVSD. A random forest model using 555 discrete, automated measurements achieved an area under the receiver operator characteristic curve (AUC) of 0.92 (0.91-0.93), similar to a deep learning waveform model with an AUC of 0.94 (0.93-0.94). A logistic regression model based on five measurements achieved high performance [AUC of 0.86 (0.85-0.87)], close to a deep learning model and better than N-terminal prohormone brain natriuretic peptide (NT-proBNP). Finally, we found that simpler models were more portable across sites, with experiments at two independent, external sites. Our study demonstrates the value of simple electrocardiographic models that perform nearly as well as deep learning models, while being much easier to implement and interpret.
| S-EPMC11284011 | biostudies-literature
Project description:The ordinary linear regression method is limited to bivariate data because it is based on the Cartesian representation y = f(x). Using the chain rule, we transform the method to the parametric representation (x(t), y(t)) and obtain a linear regression framework in which the weighted average is used as a parameter for a multivariate linear relation for a set of linearly related variable vectors (LRVVs). We confirm the proposed approach by a Monte Carlo simulation, where the minimum coefficient of variation for error (CVE) provides the optimal weights when forming a weighted average of LRVVs. Then, we describe a parametric linear regression (PLR) algorithm in which the Moore-Penrose pseudoinverse is used to estimate measurement error regression (MER) parameters individually for the given variable vectors. We demonstrate that MER parameters from the PLR and nonlinear ODRPACK methods are quite similar for a wide range of reliability ratios, but ODRPACK is formulated only for bivariate data. We identify scale invariant quantities for the PLR and weighted orthogonal regression (WOR) methods and their correspondences with the partitioned residual effects between the variable vectors. Thus, the specification of an error model for the data is essential for MER and we discuss the use of Monte Carlo methods for estimating the distributions and confidence intervals for MER slope and correlation coefficient. We distinguish between elementary covariance for the y = f(x) representation and covariance vector for the (x(t), y(t)) representation. We also discuss the multivariate generalization of the Pearson correlation as the contraction between Cartesian polyad alignment tensors for the LRVVs and weighted average. Finally, we demonstrate the use of multidimensional PLR in estimating the MER parameters for replicate RNA-Seq data and quadratic regression for estimating the parameters of the conical dispersion of read count data about the MER line.
| S-EPMC8782541 | biostudies-literature
Project description:The problem tackled is the determination of sample size for a given level and power in the context of a simple linear regression model. The standard approach deals with planned experiments in which the predictor X is observed for a number n of times and the corresponding observations on the response variable Y are to be drawn. The statistic that is used is built on the least squares' estimator of the slope parameter. Its conditional distribution given the data on the predictor X is utilized for sample size calculations. This is problematic. The sample size n is already presaged and the data on X is fixed. In unplanned experiments, in which both X and Y are to be sampled simultaneously, we do not have data on the predictor X yet. This conundrum has been discussed in several papers and books with no solution proposed. We overcome the problem by determining the exact unconditional distribution of the test statistic in the unplanned case. We have provided tables of critical values for given levels of significance following the exact distribution. In addition, we show that the distribution of the test statistic depends only on the effect size, which is defined precisely in the paper.
| S-EPMC10137477 | biostudies-literature
Project description:The vertebral compression is a significant factor for determining the prognosis of osteoporotic vertebral compression fractures and is generally measured manually by specialists. The consequent misdiagnosis or delayed diagnosis can be fatal for patients. In this study, we trained and evaluated the performance of a vertebral body segmentation model and a vertebral compression measurement model based on convolutional neural networks. For vertebral body segmentation, we used a recurrent residual U-Net model, with an average sensitivity of 0.934 (± 0.086), an average specificity of 0.997 (± 0.002), an average accuracy of 0.987 (± 0.005), and an average dice similarity coefficient of 0.923 (± 0.073). We then generated 1134 data points on the images of three vertebral bodies by labeling each segment of the segmented vertebral body. These were used in the vertebral compression measurement model based on linear regression and multi-scale residual dilated blocks. The model yielded an average mean absolute error of 2.637 (± 1.872) (%), an average mean square error of 13.985 (± 24.107) (%), and an average root mean square error of 3.739 (± 2.187) (%) in fractured vertebral body data. The proposed algorithm has significant potential for aiding the diagnosis of vertebral compression fractures.
| S-EPMC8253748 | biostudies-literature
Project description:Biomarker estimation methods from medical images have traditionally followed a segment-and-measure strategy. Deep-learning regression networks have changed such a paradigm, enabling the direct estimation of biomarkers in databases where segmentation masks are not present. While such methods achieve high performance, they operate as a black-box. In this work, we present a novel deep learning network structure that, when trained with only the value of the biomarker, can perform biomarker regression and the generation of an accurate localization mask simultaneously, thus enabling a qualitative assessment of the image locus that relates to the quantitative result. We showcase the proposed method with three different network structures and compare their performance against direct regression networks in four different problems: pectoralis muscle area (PMA), subcutaneous fat area (SFA), liver mass area in single slice computed tomography (CT), and Agatston score estimated from non-contrast thoracic CT images (CAC). Our results show that the proposed method improves the performance with respect to direct biomarker regression methods (correlation coefficient of 0.978, 0.998, and 0.950 for the proposed method in comparison to 0.971, 0.982, and 0.936 for the reference regression methods on PMA, SFA and CAC respectively) while achieving good localization (DICE coefficients of 0.875, 0.914 for PMA and SFA respectively, p < 0.05 for all pairs). We observe the same improvement in regression results comparing the proposed method with those obtained by quantify the outputs using an U-Net segmentation network (0.989 and 0.951 respectively). We, therefore, conclude that it is possible to obtain simultaneously good biomarker regression and localization when training biomarker regression networks using only the biomarker value.
| S-EPMC7307703 | biostudies-literature
Project description:DNA methylation change has been useful for cancer biomarker discovery, classification, and potential treatment development. So far, existing methods use either differentially methylated CpG sites or combined CpG sites, namely differentially methylated regions, that can be mapped to genes. However, such methylation signal mapping has limitations. To address these limitations, in this study, we introduced a combinatorial framework using linear regression, differential expression, deep learning method for accurate biological interpretation of DNA methylation through integrating DNA methylation data and corresponding TCGA gene expression data. We demonstrated it for uterine cervical cancer. First, we pre-filtered outliers from the data set and then determined the predicted gene expression value from the pre-filtered methylation data through linear regression. We identified differentially expressed genes (DEGs) by Empirical Bayes test using Limma. Then we applied a deep learning method, "nnet" to classify the cervical cancer label of those DEGs to determine all classification metrics including accuracy and area under curve (AUC) through 10-fold cross validation. We applied our approach to uterine cervical cancer DNA methylation dataset (NCBI accession ID: GSE30760, 27,578 features covering 63 tumor and 152 matched normal samples). After linear regression and differential expression analysis, we obtained 6287 DEGs with false discovery rate (FDR) <0.001. After performing deep learning analysis, we obtained average classification accuracy 90.69% (±1.97%) of the uterine cervical cancerous labels. This performance is better than that of other peer methods. We performed in-degree and out-degree hub gene network analysis using Cytoscape. We reported five top in-degree genes (PAIP2, GRWD1, VPS4B, CRADD and LLPH) and five top out-degree genes (MRPL35, FAM177A1, STAT4, ASPSCR1 and FABP7). After that, we performed KEGG pathway and Gene Ontology enrichment analysis of DEGs using tool WebGestalt(WEB-based Gene SeT AnaLysis Toolkit). In summary, our proposed framework that integrated linear regression, differential expression, deep learning provides a robust approach to better interpret DNA methylation analysis and gene expression data in disease study.
| S-EPMC7465138 | biostudies-literature
Project description:In the context of legged robotics, many criteria based on the control of the Center of Mass (CoM) have been developed to ensure a stable and safe robot locomotion. Defining a whole-body framework with the control of the CoM requires a planning strategy, often based on a specific type of gait and a reliable state-estimation. In a whole-body control approach, if the CoM task is not specified, the consequent redundancy can still be resolved by specifying a postural task that set references for all the joints. Therefore, the postural task can be exploited to keep a well-behaved, stable kinematic configuration. In this work, we propose a generic locomotion framework which is able to generate different kind of gaits, ranging from very dynamic gaits, such as the trot, to more static gaits like the crawl, without the need to plan the CoM trajectory. Consequently, the whole-body controller becomes planner-free and it does not require the estimation of the floating base state, which is often prone to drift. The framework is composed of a priority-based whole-body controller that works in synergy with a walking pattern generator. We show the effectiveness of the framework by presenting simulations on different types of simulated terrains, including rough terrain, using different quadruped platforms.
| S-EPMC7805836 | biostudies-literature
Project description:Identifying coordinate transformations that make strongly nonlinear dynamics approximately linear has the potential to enable nonlinear prediction, estimation, and control using linear theory. The Koopman operator is a leading data-driven embedding, and its eigenfunctions provide intrinsic coordinates that globally linearize the dynamics. However, identifying and representing these eigenfunctions has proven challenging. This work leverages deep learning to discover representations of Koopman eigenfunctions from data. Our network is parsimonious and interpretable by construction, embedding the dynamics on a low-dimensional manifold. We identify nonlinear coordinates on which the dynamics are globally linear using a modified auto-encoder. We also generalize Koopman representations to include a ubiquitous class of systems with continuous spectra. Our framework parametrizes the continuous frequency using an auxiliary network, enabling a compact and efficient embedding, while connecting our models to decades of asymptotics. Thus, we benefit from the power of deep learning, while retaining the physical interpretability of Koopman embeddings.
| S-EPMC6251871 | biostudies-literature
Project description:BackgroundB-cell epitopes play important roles in vaccine design, clinical diagnosis, and antibody production. Although some models have been developed to predict linear or conformational B-cell epitopes, their performance is still unsatisfactory. Hundreds of thousands of linear B-cell epitope data have accumulated in the Immune Epitope Database (IEDB). These data can be explored using the deep learning methods, in order to create better predictive models for linear B-cell epitopes.ResultsAfter data cleaning, we obtained 240,563 peptide samples with experimental evidence from the IEDB database, including 25,884 linear B-cell epitopes and 214,679 non-epitopes. Based on the peptide center, we adapted each peptide to the same length by trimming or extending. A random portion of the data, with the same amount of epitopes and non-epitopes, were set aside as test dataset. Then a same number of epitopes and non-epitopes were randomly selected from the remaining data to build a classifier with the feedforward deep neural network. We built eleven classifiers to form an ensemble prediction model. The model will report a peptide as an epitope if it was classified as epitope by all eleven classifiers. Then we used the test data set to evaluate the performance of the model using the area value under the receiver operating characteristic (ROC) curve (AUC) as an indicator. We established 40 models to predict linear B-cell epitopes of length from 11 to 50 separately, and found that the AUC value increased with the length and tended to be stable when the length was 38. Repeated results showed that the models constructed by this method were robust. Tested on our and two public test datasets, our models outperformed current major models available.ConclusionsWe applied the feedforward deep neural network to the large amount of linear B-cell epitope data with experimental evidence in the IEDB database, and constructed ensemble prediction models with better performance than the current major models available. We named the models as DLBEpitope and provided web services using the models at http://ccb1.bmi.ac.cn:81/dlbepitope/.
| S-EPMC7371472 | biostudies-literature