Data classification using an ensemble of filters

Ensemble feature selection with data-driven thresholding for Alzheimer's disease biomarker discovery

BACKGROUND

Feature selection is often used to identify the important features in a dataset but can produce unstable results when applied to high-dimensional data. The stability of feature selection can be improved with the use of feature selection ensembles, which aggregate the results of multiple base feature selectors. However, a threshold must be applied to the final aggregated feature set to separate the relevant features from the redundant ones. A fixed threshold, which is typically used, offers no guarantee that the final set of selected features contains only relevant features. This work examines a selection of data-driven thresholds to automatically identify the relevant features in an ensemble feature selector and evaluates their predictive accuracy and stability. Ensemble feature selection with data-driven thresholding is applied to two real-world studies of Alzheimer's disease. Alzheimer's disease is a progressive neurodegenerative disease with no known cure, that begins at least 2-3 decades before overt symptoms appear, presenting an opportunity for researchers to identify early biomarkers that might identify patients at risk of developing Alzheimer's disease.

RESULTS

The ensemble feature selectors, combined with data-driven thresholds, produced more stable results, on the whole, than the equivalent individual feature selectors, showing an improvement in stability of up to 34%. The most successful data-driven thresholds were the robust rank aggregation threshold and the threshold algorithm threshold from the field of information retrieval. The features identified by applying these methods to datasets from Alzheimer's disease studies reflect current findings in the AD literature.

CONCLUSIONS

Data-driven thresholds applied to ensemble feature selectors provide more stable, and therefore more reproducible, selections of features than individual feature selectors, without loss of performance. The use of a data-driven threshold eliminates the need to choose a fixed threshold a-priori and can select a more meaningful set of features. A reliable and compact set of features can produce more interpretable models by identifying the factors that are important in understanding a disease.

Feature selection methods on gene expression microarray data for cancer classification: A systematic review

This systematic review provides researchers interested in feature selection (FS) for processing microarray data with comprehensive information about the main research directions for gene expression classification conducted during the recent seven years. A set of 132 researches published by three different publishers is reviewed. The studied papers are categorized into nine directions based on their objectives. The FS directions that received various levels of attention were then summarized. The review revealed that 'propose hybrid FS methods' represented the most interesting research direction with a percentage of 34.9%, while the other directions have lower percentages that ranged from 13.6% down to 3%. This guides researchers to select the most competitive research direction. Papers in each category are thoroughly reviewed based on six perspectives, mainly: method(s), classifier(s), dataset(s), dataset dimension(s) range, performance metric(s), and result(s) achieved.

A hybrid feature selection model based on improved squirrel search algorithm and rank aggregation using fuzzy techniques for biomedical data classification

Feature selection has gained its importance due to the voluminous nature of the data. Owing to the computational complexity of wrapper approaches, the poor performance of filtering techniques, and the classifier dependency of embedded approaches, hybrid approaches are more commonly used in feature selection. Hybrid approaches use filtering metrics to reduce the computational complexity of wrapper algorithms and are proved to yield better feature subset. Though filtering metrics select the features based on their significance, most of them are unstable and biased towards the metric used. Moreover, the choice of filtering metrics depends largely on the distribution of data and data types. Biomedical datasets contain features with different distribution and types adding to the complexity in the choice of filtering metric. We address this problem by proposing a stable filtering method based on rank aggregation in hybrid feature selection model with Improved Squirrel search algorithm for biomedical datasets. Our proposed model is compared with other well-known and state-of-the-art methods and the results prove that our model exhibited superior performance in terms of classification accuracy and computational time. The robustness of our proposed model is proved by conducting experiments on nine biomedical datasets and with three different classifiers.

Applying Machine Learning to Kinematic and Eye Movement Features of a Movement Imitation Task to Predict Autism Diagnosis

Autism is a developmental condition currently identified by experts using observation, interview, and questionnaire techniques and primarily assessing social and communication deficits. Motor function and movement imitation are also altered in autism and can be measured more objectively. In this study, motion and eye tracking data from a movement imitation task were combined with supervised machine learning methods to classify 22 autistic and 22 non-autistic adults. The focus was on a reliable machine learning application. We have used nested validation to develop models and further tested the models with an independent data sample. Feature selection was aimed at selection stability to assure result interpretability. Our models predicted diagnosis with 73% accuracy from kinematic features, 70% accuracy from eye movement features and 78% accuracy from combined features. We further explored features which were most important for predictions to better understand movement imitation differences in autism. Consistent with the behavioural results, most discriminative features were from the experimental condition in which non-autistic individuals tended to successfully imitate unusual movement kinematics while autistic individuals tended to fail. Machine learning results show promise that future work could aid in the diagnosis process by providing quantitative tests to supplement current qualitative ones.

Classification of Microarray Data

The automatic classification of DNA microarray data is one of the hot topics in the field of bioinformatics, since it is an effective tool for the diagnosis of diseases in patients. The aim of this chapter is to present the most relevant aspects related to the classification of microarrays. We carried out an analysis of the strategies used for the classification of microarray data and a review of the main methods used in the literature. In addition, other related aspects are addressed as the reduction of dimensionality, to try to eliminate redundant information in genes, or the treatment of imbalanced data and missing of data. To conclude, we present an exhaustive review of the main scientific works in journals to show the most successful techniques applied in this discipline as well as the most used datasets to verify their effectiveness.

A Review of Microarray Datasets: Where to Find Them and Specific Characteristics

The advent of DNA microarray datasets has stimulated a new line of research both in bioinformatics and in machine learning. This type of data is used to collect information from tissue and cell samples regarding gene expression differences that could be useful for disease diagnosis or for distinguishing specific types of tumor. Microarray data classification is a difficult challenge for machine learning researchers due to its high number of features and the small sample sizes. This chapter is devoted to reviewing the microarray databases most frequently used in the literature. We also make the interested reader aware of the problematic of data characteristics in this domain, such as the imbalance of the data, their complexity, and the so-called dataset shift.

Neuropsychological predictors of conversion from mild cognitive impairment to Alzheimer's disease: a feature selection ensemble combining stability and predictability

BACKGROUND

Predicting progression from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) is an utmost open issue in AD-related research. Neuropsychological assessment has proven to be useful in identifying MCI patients who are likely to convert to dementia. However, the large battery of neuropsychological tests (NPTs) performed in clinical practice and the limited number of training examples are challenge to machine learning when learning prognostic models. In this context, it is paramount to pursue approaches that effectively seek for reduced sets of relevant features. Subsets of NPTs from which prognostic models can be learnt should not only be good predictors, but also stable, promoting generalizable and explainable models.

METHODS

We propose a feature selection (FS) ensemble combining stability and predictability to choose the most relevant NPTs for prognostic prediction in AD. First, we combine the outcome of multiple (filter and embedded) FS methods. Then, we use a wrapper-based approach optimizing both stability and predictability to compute the number of selected features. We use two large prospective studies (ADNI and the Portuguese Cognitive Complaints Cohort, CCC) to evaluate the approach and assess the predictive value of a large number of NPTs.

RESULTS

The best subsets of features include approximately 30 and 20 (from the original 79 and 40) features, for ADNI and CCC data, respectively, yielding stability above 0.89 and 0.95, and AUC above 0.87 and 0.82. Most NPTs learnt using the proposed feature selection ensemble have been identified in the literature as strong predictors of conversion from MCI to AD.

CONCLUSIONS

The FS ensemble approach was able to 1) identify subsets of stable and relevant predictors from a consensus of multiple FS methods using baseline NPTs and 2) learn reliable prognostic models of conversion from MCI to AD using these subsets of features. The machine learning models learnt from these features outperformed the models trained without FS and achieved competitive results when compared to commonly used FS algorithms. Furthermore, the selected features are derived from a consensus of methods thus being more robust, while releasing users from choosing the most appropriate FS method to be used in their classification task.

The Cross-Entropy Based Multi-Filter Ensemble Method for Gene Selection

The gene expression profile has the characteristics of a high dimension, low sample, and continuous type, and it is a great challenge to use gene expression profile data for the classification of tumor samples. This paper proposes a cross-entropy based multi-filter ensemble (CEMFE) method for microarray data classification. Firstly, multiple filters are used to select the microarray data in order to obtain a plurality of the pre-selected feature subsets with a different classification ability. The top N genes with the highest rank of each subset are integrated so as to form a new data set. Secondly, the cross-entropy algorithm is used to remove the redundant data in the data set. Finally, the wrapper method, which is based on forward feature selection, is used to select the best feature subset. The experimental results show that the proposed method is more efficient than other gene selection methods and that it can achieve a higher classification accuracy under fewer characteristic genes.