Dual coordinate descent methods for logistic regression and maximum entropy models

Flood disasters resulting from excessive water in stream beds inflict extensive damage. Floods are caused by the expansion of cities, the erosion of riverbeds, inadequate infrastructure, and increasing precipitation due to climate change. Floods cause great damage to agricultural areas and settlements. Regions that may be affected by floods should be identified, and precautions should be taken in these areas to prevent these damages. Flood susceptibility maps are produced for this reason. The purpose of this study was to construct a flood susceptibility map so that susceptible locations in Mersin may be identified. Firstly, 429 flood events were identified for the flood inventory map. Twelve conditioning factors, namely elevation, slope, distance to river, distance to drainage, drainage density, soil permeability, precipitation, land cover/land use, stream power index (SPI), topographic wetness index (TWI), aspect, and curvature were used to create flood susceptibility maps, applying logistic regression and best-worst methods. The flood inventory data were used to prepare susceptibility maps and test their consistency. The receiver operating characteristic (ROC) curve was used for consistency analysis. In logistic regression, 86% of floods were located within 20% of the study area that was categorized as high and very high susceptibility. According to the value of the area under the ROC curve (AUC), logistic regression had a 0.901 value. Land use, soil permeability, and elevation were the most important factors in the logistic regression method. In the best-worst method, 85% of floods were located within the 14% of the study area categorized as high and very high susceptibility. According to the AUC value, the best-worst method had a 0.898 value. Elevation, distance to river, and precipitation factors had the highest coefficient value in the best-worst method. Based on the AUC values, the flood susceptibility maps had a high prediction capacity.

Aim: The major goal of this study is to compare the effectiveness of the Logistic Regression classifier with the Least Squares Support Vector Machine classifier in detecting plaque in the heart with high accuracy. Materials and Methods: In this work, the Logistic Regression and least squares Support Vector Machine methods are compared. There were a total of 20 samples in the Kaggle dataset on Heart Plaque disease. To calculate sample G power of 0.08 with 95% confidence interval, Clincalc is utilized. There are two groups in the training dataset (n = 489 (70 percent)) and the test dataset (n = 277 (30 percent)). Results: The accuracy of both the Logistic Regression and Least Squares Support Vector Machine algorithms is evaluated. The Least Squares Support Vector Machine approach was only 67.3 % accurate, while the Logistic Regression method was 96 % accurate. Since p(2-tailed) < 0.05, in SPSS statistical analysis, a significant difference exists between the two groups. Conclusion: The Logistic Regression algorithm is significantly better than Least Squares Support Vector Machine algorithm in this study in detecting cardiac plaque disease in the dataset.

BackgroundPredictive models for delayed graft function (DGF) after kidney transplantation are usually developed using logistic regression. We want to evaluate the value of machine learning methods in the prediction of DGF.Methods497 kidney transplantations from deceased donors at the Ghent University Hospital between 2005 and 2011 are included. A feature elimination procedure is applied to determine the optimal number of features, resulting in 20 selected parameters (24 parameters after conversion to indicator parameters) out of 55 retrospectively collected parameters. Subsequently, 9 distinct types of predictive models are fitted using the reduced data set: logistic regression (LR), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), support vector machines (SVMs; using linear, radial basis function and polynomial kernels), decision tree (DT), random forest (RF), and stochastic gradient boosting (SGB). Performance of the models is assessed by computing sensitivity, positive predictive values and area under the receiver operating characteristic curve (AUROC) after 10-fold stratified cross-validation. AUROCs of the models are pairwise compared using Wilcoxon signed-rank test.ResultsThe observed incidence of DGF is 12.5 %. DT is not able to discriminate between recipients with and without DGF (AUROC of 52.5 %) and is inferior to the other methods. SGB, RF and polynomial SVM are mainly able to identify recipients without DGF (AUROC of 77.2, 73.9 and 79.8 %, respectively) and only outperform DT. LDA, QDA, radial SVM and LR also have the ability to identify recipients with DGF, resulting in higher discriminative capacity (AUROC of 82.2, 79.6, 83.3 and 81.7 %, respectively), which outperforms DT and RF. Linear SVM has the highest discriminative capacity (AUROC of 84.3 %), outperforming each method, except for radial SVM, polynomial SVM and LDA. However, it is the only method superior to LR.ConclusionsThe discriminative capacities of LDA, linear SVM, radial SVM and LR are the only ones above 80 %. None of the pairwise AUROC comparisons between these models is statistically significant, except linear SVM outperforming LR. Additionally, the sensitivity of linear SVM to identify recipients with DGF is amongst the three highest of all models. Due to both reasons, the authors believe that linear SVM is most appropriate to predict DGF.

Risk Prediction Tool for Aggressive Tumors in Clinical T1 Stage Clear Cell Renal Cell Carcinoma Using Molecular Biomarkers

One of the key performance indicators for the logistics industry, especially freight forwarder company (cargo), is the delivery time. This is still a challenge in this industry in terms of ensuring the customer service level and reducing transportation costs. On the other hand, the development of information technology now allows an organization or company to collect large amounts of data automatically. A decent method that can be used to analyze the data for prediction purposes is machine learning, which is a method of extracting data into a certain pattern of information. This research aims to apply three machine learning methods to estimate the status of shipping goods. The method used in this study follows the machine learning process published by the Cross Industry Standard Process for Data Mining (CRISP-DM), namely; business processes understanding, data understanding, data preparation, model development, evaluation, and implementation. Based on the results of the study, the random forest method produces better accuracy than the logistic regression and artificial neural network (ANN) methods, which is 76.6%, while the results of ANN and logistic regression methods are 73.81% and 72.84% respectively.

Anemia Before Coronary Artery Bypass Surgery as Additional Risk Factor Increases the Perioperative Risk

The accurate diagnosis of cardiac disease is vital in managing patients' health. Data mining and machine learning techniques play an important role in the diagnosis of heart disease. We aimed to examine the diagnostic performances of an adaptive neuro-fuzzy inference system (ANFIS) for predicting coronary artery disease and compare this with two statistical methods: flexible discriminant analysis (FDA) and logistic regression (LR). The data of this study is the result of descriptive-analytical research from the study of Mashhad. We used ANFIS, LR, and FDA to predict coronary artery disease. A total of 7385 subjects were recruited as part of the Mashhad Stroke and Heart Atherosclerotic Disorders (MASHAD) cohort study. The data set contained demographic, serum biochemical parameters, anthropometric, and many other variables. To evaluate the ability of trained ANFIS, LR, and FDA models to diagnose coronary artery disease, we used the Hold-Out method.For analyzing data, we used SPSS v25, R 4.0.4, and MATLAB 2018 software. The accuracy, sensitivity, specificity, Mean squared error (MSE) , and area under the roc curve (AUC) for ANFIS were 83.4%, 80%, 86%, 0.166 and 83.4%. The corresponding values based on the LR method were 72.4%, 74%, 70% , 0.175 and 81.5% and for the FDA method, these measurements were 77.7%, 74%, 81%, 0.223, and 77.6%, respectively. There was a significant difference between the accuracy of these three methods. The present findings showed that ANFIS was the most accurate method for diagnosing coronary artery disease compared with LR and FDA methods. Thus, it could be a helpful tool to aid medical decision-making for the diagnosis of coronary artery disease.

Prediction of Recurrence using a Stacked Denoising Autoencoder and Multifaceted Feature Analysis of Pretreatment MRI in Patients with Nasopharyngeal Carcinoma.

The time score for 50% cell viability (50% effective time; ET50) is used as the index of skin irritation evaluated by a three-dimensional human skin model, such as TESTSKIN and Vitrolife-Skin. ET50 is conventionally estimated by linear interpolation of measurements at two time points, which yields cell viabilities above and below 50%. This simple method is problematic in that biased estimates are occasionally obtained and confidence intervals cannot be appropriately constructed. We compared four estimation methods including a logistic regression method, a log-time regression method, a linear regression method and a newly proposed two-stage method through a Monte-Carlo simulation study in small sample sizes due to the experimental restrictions. The logistic regression method provides almost unbiased estimates, although the confidence interval for ET50 is occasionally not obtained. The log-time regression method and the linear regression method provide positive biased estimates, although the confidence interval for ET50 is obtained in any case. The two-stage method is reasonable, in which the log-time regression method is adopted only if the logistic regression method cannot construct a confidence interval for ET50.

Background and aimsThe birth weight of a newborn is a crucial factor that affects their overall health and future well-being. Low birth weight (LBW) is a widespread global issue, which the World Health Organization defines as weighing less than 2,500 g. LBW can have severe negative consequences on an individual’s health, including neonatal mortality and various health concerns throughout their life. To address this problem, this study has been conducted using BDHS 2017–2018 data to uncover important aspects of LBW using a variety of machine learning (ML) approaches and to determine the best feature selection technique and best predictive ML model.MethodsTo pick out the key features, the Boruta algorithm and wrapper method were used. Logistic Regression (LR) used as traditional method and several machine learning classifiers were then used, including, DT (Decision Tree), SVM (Support Vector Machine), NB (Naïve Bayes), RF (Random Forest), XGBoost (eXtreme Gradient Boosting), and AdaBoost (Adaptive Boosting), to determine the best model for predicting LBW. The model’s performance was evaluated based on the specificity, sensitivity, accuracy, F1 score and AUC value.ResultsResult shows, Boruta algorithm identifies eleven significant features including respondent’s age, highest education level, educational attainment, wealth index, age at first birth, weight, height, BMI, age at first sexual intercourse, birth order number, and whether the child is a twin. Incorporating Boruta algorithm’s significant features, the performance of traditional LR and ML methods including DT, SVM, NB, RF, XGBoost, and AB were evaluated where LR, had a specificity, sensitivity, accuracy and F1 score of 0.85, 0.5, 85.15% and 0.915. While the ML methods DT, SVM, NB, RF, XGBoost, and AB model’s respective accuracy values were 85.35%, 85.15%, 84.54%, 81.18%, and 84.41%. Based on the specificity, sensitivity, accuracy, F1 score and AUC, RF (specificity = 0.99, sensitivity = 0.58, accuracy = 85.86%, F1 score = 0.9243, AUC = 0.549) outperformed the other methods. Both the classical (LR) and machine learning (ML) models’ performance has improved dramatically when important characteristics are extracted using the wrapper method. The LR method identified five significant features with a specificity, sensitivity, accuracy and F1 score of 0.87, 0.33, 87.12% and 0.9309. The region, whether the infant is a twin, and cesarean delivery were the three key features discovered by the DT and RF models, which were implemented using the wrapper technique. All three models had the identical F1 score of 0.9318. However, “child is twin” was recognized as a significant feature by the SVM, NB, and AB models, with an F1 score of 0.9315. Ultimately, with an F1 score of 0.9315, the XGBoost model recognized “child is twin” and “age at first sex” as relevant features. Random Forest again beat the other approaches in this instance.ConclusionsThe study reveals Wrapper method as the optimal feature selection technique. The ML method outperforms traditional methods, with Random Forest (RF) being the most effective predictive model for Low-Birth-Weight prediction. The study suggests that policymakers in Bangladesh can mitigate low birth weight newborns by considering identified risk factors.

This study aimed to validate the accuracy and prediction performance of machine learning (ML), deep learning (DL), and logistic regression methods in the treatment of medial meniscus posterior root tears (MMPRT). From July 2003 to May 2018, 640 patients diagnosed with MMPRT were included. First, the affecting factors for the surgery were evaluated using statistical analysis. Second, AI technology was introduced using X-ray and MRI. Finally, the accuracy and prediction performance were compared between ML&DL and logistic regression methods. Affecting factors of the logistic regression method corresponded well with the feature importance of the six top-ranked factors in the ML&DL method. There was no significant difference when comparing the accuracy, F1-score, and error rate between ML&DL and logistic regression methods (accuracy = 0.89 and 0.91, F1 score = 0.89 and 0.90, error rate = 0.11 and 0.09; p = 0.114, 0.422, and 0.119, respectively). The area under the curve (AUC) values showed excellent test quality for both ML&DL and logistic regression methods (AUC = 0.97 and 0.94, respectively) in the evaluation of prediction performance (p = 0.289). The affecting factors of the logistic regression method and the influence of the ML&DL method were not significantly different. The accuracy and performance of the ML&DL method in predicting the fate of MMPRT were comparable to those of the logistic regression method. Therefore, this ML&DL algorithm could potentially predict the outcome of the MMRPT in various fields and situations. Furthermore, our method could be efficiently implemented in current clinical practice.

Entropy methods enable a convenient general approach to providing a probability distribution with partial information. The minimum cross-entropy principle selects the distribution that minimizes the Kullback–Leibler divergence subject to the given constraints. This general principle encompasses a wide variety of distributions, and generalizes other methods that have been proposed independently. There remains, however, some confusion about the breadth of entropy methods in the literature. In particular, the asymmetry of the Kullback–Leibler divergence provides two important special cases when the target distribution is uniform: the maximum entropy method and the maximum log-probability method. This paper compares the performance of both methods under a variety of conditions. We also examine a generalized maximum log-probability method as a further demonstration of the generality of the entropy approach.

BackgroundPenalised regression methods are a useful atheoretical approach for both developing predictive models and selecting key indicators within an often substantially larger pool of available indicators. In comparison to traditional methods, penalised regression models improve prediction in new data by shrinking the size of coefficients and retaining those with coefficients greater than zero. However, the performance and selection of indicators depends on the specific algorithm implemented. The purpose of this study was to examine the predictive performance and feature (i.e., indicator) selection capability of common penalised logistic regression methods (LASSO, adaptive LASSO, and elastic-net), compared with traditional logistic regression and forward selection methods.DesignData were drawn from the Australian Temperament Project, a multigenerational longitudinal study established in 1983. The analytic sample consisted of 1,292 (707 women) participants. A total of 102 adolescent psychosocial and contextual indicators were available to predict young adult daily smoking.FindingsPenalised logistic regression methods showed small improvements in predictive performance over logistic regression and forward selection. However, no single penalised logistic regression model outperformed the others. Elastic-net models selected more indicators than either LASSO or adaptive LASSO. Additionally, more regularised models included fewer indicators, yet had comparable predictive performance. Forward selection methods dismissed many indicators identified as important in the penalised logistic regression models.ConclusionsAlthough overall predictive accuracy was only marginally better with penalised logistic regression methods, benefits were most clear in their capacity to select a manageable subset of indicators. Preference to competing penalised logistic regression methods may therefore be guided by feature selection capability, and thus interpretative considerations, rather than predictive performance alone.

TheMs7.0 Lushan earthquake triggered a huge number of landslides. Landslide susceptibility mapping is of great importance. Weight of Evidence (WoE) and Logistic Regression (LR) methods have been widely used for LSM (Landslide Susceptibility Mapping). However, limitations still exist. WoE is capable of assessing the influence of different classes of each factor, but neglects the correlation between factors. LR is able to analyze the relationship among the factors while it is not capable of evaluating the influence of different classes. This paper proposes a combined method of LR and WoE for LSM, taking advantage of their individual merits and overcoming their limitations. An inventory of 1289 landslides was used: 70% were random‐selected for training and the remaining for validation. 11 landslide condition factors were employed in the model and the result was validated using Receiver Operating Characteristic (ROC) curve. The results showed that the LR‐WoE model had a better accuracy than the LR model, producing an area below the curve with values of 0.802 success and 0.791 predictive, higher than that of the LR model (0.715 success and 0.722 predictive). It is therefore concluded that the combined method of WoE and LR can provide a promising level of accuracy for earthquake‐induced landslide susceptibility mapping.

Comparing the performance of different multiple imputation strategies for missing binary outcomes in cluster randomized trials: a simulation study Jinhui Ma,1–3 Parminder Raina,1,2 Joseph Beyene,1 Lehana Thabane1,3–51Department of Clinical Epidemiology and Biostatistics, McMaster University, Hamilton, ON, Canada; 2McMaster University Evidence-based Practice Center, Hamilton, ON, Canada; 3Biostatistics Unit, St Joseph's Healthcare Hamilton, Hamilton, ON, Canada; 4Centre for Evaluation of Medicines, St Joseph's Healthcare Hamilton, Hamilton, ON, Canada; 5Population Health Research Institute, Hamilton Health Sciences, Hamilton, ON, CanadaIntroduction: Although researchers have proposed various strategies to handle missing outcomes in cluster randomized trials (CRTs), limited attention has been paid to the performance of these strategies. Under the assumption of covariate-dependent missingness, the objective of this simulation study is to compare the performance of various strategies in handling missing binary outcomes in CRTs under different design settings.Methods: There are six missing data strategies investigated in this paper, which include complete case analysis, standard multiple imputation (MI) strategies using either logistic regression or Markov chain Monte Carlo (MCMC) method, within-cluster MI strategies using either logistic regression or MCMC method, and MI using logistic regression with cluster as a fixed effect. The performance of these strategies is evaluated through bias, empirical standard error, root mean squared error, and coverage probability.Results: Under the assumption of covariate-dependent missingness and applying the generalized estimating equations approach for fitting the logistic regression, it was shown that complete case analysis yields valid inferences when the percentage of missing outcomes is not large (<20%) for all the designs of CRTs considered in this paper. Standard MI strategies can be adopted when the design effect is small (variance inflation factor [VIF] ≤ 3); however, they tend to underestimate the standard error of treatment effect when the design effect is large. Within-cluster MI strategy using logistic regression is valid for imputation of missing data from CRTs, especially when the cluster size is large (>50) and the design effect is large (VIF > 3). In contrast, within-cluster MI strategy using MCMC method may yield biased estimates of treatment effect for CRTs with small cluster size (≤50). MI using logistic regression with cluster as a fixed effect may substantially overestimate the standard error of the estimated treatment effect when the intracluster correlation coefficient is small. It may also lead to biased estimated treatment effect.Conclusion: Findings from this simulation study provide researchers with quantitative evidence to guide selection of an appropriate strategy to deal with missing binary outcomes.Keywords: missing data, design effect, variance inflation factor