Feature selection using logistic regression in case-control DNA methylation data of Parkinson's disease: A comparative study

Combinations of Feature Selection and Machine Learning Algorithms for Object-Oriented Betel Palms and Mango Plantations Classification Based on Gaofen-2 Imagery

Betel palms and mango plantations are two crucial commercial crops in tropical agricultural areas. Accurate spatial distributions of these two crops are essential in tropical agricultural regional planning and management. However, the characteristics of small patches, scattering, and perennation make it challenging to map betel palms and mango plantations in complex tropical agricultural regions. Furthermore, the excessive features of very-high-resolution (VHR) imaging might lead to a reduction in classification accuracy and an increase in computation times. To address these challenges, we selected five feature selection (FS) methods (random forest means a decrease in accuracy (RFMDA), ReliefF, random forest-recursive feature elimination (RFE), aggregated boosted tree (ABT), and logistic regression (LR)) and four machine learning algorithms (random forest (RF), support vector machine (SVM), classification and regression tree (CART), and adaptive boosting (AdaBoost)). Then, the optimal combinations of FS and machine learning algorithms suited for object-oriented classification of betel palms and mango plantations were explored using VHR Gaofen-2 imagery. In terms of overall accuracy, all optimal classification schemes exceeded 80%, and the classifiers using selected features increased the overall accuracy between 1% and 4% compared with classification without FS methods. Specifically, LR was appropriate to RF and SVM classifiers, which produced the highest classification accuracy (89.1% and 89.88% for RF and SVM, respectively). In contrast, ABT and ReliefF were found to be suitable FS methods for CART and AdaBoost classifiers, respectively. Overall, all four optimal combinations of FS methods and classifiers could precisely recognize mango plantations, whereas betel palms were best depicted by using the RF-LR method with 26 features. The results indicated that combination of feature selection and machine learning algorithms contributed to the object-oriented classification of complex tropical crops using Gaofen-2 imagery, which provide a useful methodological reference for precisely recognizing small tropical agricultural patterns.

Environmental Impact on the Epigenetic Mechanisms Underlying Parkinson’s Disease Pathogenesis: A Narrative Review

Parkinson’s disease (PD) is the second most common neurodegenerative disorder with an unclear etiology and no disease-modifying treatment to date. PD is considered a multifactorial disease, since both genetic and environmental factors contribute to its pathogenesis, although the molecular mechanisms linking these two key disease modifiers remain obscure. In this context, epigenetic mechanisms that alter gene expression without affecting the DNA sequence through DNA methylation, histone post-transcriptional modifications, and non-coding RNAs may represent the key mediators of the genetic–environmental interactions underlying PD pathogenesis. Environmental exposures may cause chemical alterations in several cellular functions, including gene expression. Emerging evidence has highlighted that smoking, coffee consumption, pesticide exposure, and heavy metals (manganese, arsenic, lead, etc.) may potentially affect the risk of PD development at least partially via epigenetic modifications. Herein, we discuss recent accumulating pre-clinical and clinical evidence of the impact of lifestyle and environmental factors on the epigenetic mechanisms underlying PD development, aiming to shed more light on the pathogenesis and stimulate future research.

Data envelopment analysis using the binary-data

Purpose

The purpose of this paper is to propose the data envelopment analysis (DEA) model that can be used as binary-valued data. Often the basic DEA models were developed by assuming that all of the data are non-negative. However, there are situations where all data are binary. As an example, the information on many diseases in health care is binary data. The existence of binary data in traditional DEA models may change the behavior of the production possibility set (PPS). This study defines a binary summation operator, expresses the modified principles and introduces the extracted PPS of axioms. Furthermore, this study proposes a binary integer programming of DEA (BIP-DEA) for assessing the efficiency scores to use as an alternate tool in prediction.

Design/methodology/approach

In this study, the extracted PPS of modified axioms and the BIP-DEA model for assessing the efficiency score is proposed.

Findings

The binary integer model was proposed to eliminate the challenges of the binary-value data in DEA.

Originality/value

The importance of the proposed model for many fields including the health-care industry is that it can predict the occurrence or non-occurrence of the events, using binary data. This model has been applied to evaluate the most important risk factors for stroke disease and mechanical disorders. The targets set by this model can help to diagnose earlier the disease and increase the patients’ chances of recovery.