An efficient SVM-GA feature selection model for large healthcare databases

Chow, Rick; Zhong, Wei; Blackmon, Michael; Stolz, Richard W.; Dowell, Marsha

doi:10.1145/1389095.1389362

Cited by 8 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for mutation types (Gaussian, switching, and sparsity) we followed the methods of phase I in addition to optimization with simple validation. Given the guidance of [43, 44], we considered various values for C and gamma; the default for gamma=1.0 was best. We also confirmed that the default value for epsilon=0.1 was reasonable for our data.…”

Section: Methodsmentioning

confidence: 99%

Screening nonrandomized studies for medical systematic reviews: A comparative study of classifiers

Bekhuis

Demner‐Fushman

2012

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objectives To investigate whether (1) machine learning classifiers can help identify nonrandomized studies eligible for full-text screening by systematic reviewers; (2) classifier performance varies with optimization; and (3) the number of citations to screen can be reduced. Methods We used an open-source, data-mining suite to process and classify biomedical citations that point to mostly nonrandomized studies from 2 systematic reviews. We built training and test sets for citation portions and compared classifier performance by considering the value of indexing, various feature sets, and optimization. We conducted our experiments in 2 phases. The design of phase I with no optimization was: 4 classifiers × 3 feature sets × 3 citation portions. Classifiers included k-nearest neighbor, naïve Bayes, complement naïve Bayes, and evolutionary support vector machine. Feature sets included bag of words, and 2- and 3-term n-grams. Citation portions included titles, titles and abstracts, and full citations with metadata. Phase II with optimization involved a subset of the classifiers, as well as features extracted from full citations, and full citations with overweighted titles. We optimized features and classifier parameters by manually setting information gain thresholds outside of a process for iterative grid optimization with 10-fold cross-validations. We independently tested models on data reserved for that purpose and statistically compared classifier performance on 2 types of feature sets. We estimated the number of citations needed to screen by reviewers during a second pass through a reduced set of citations. Results In phase I, the evolutionary support vector machine returned the best recall for bag of words extracted from full citations; the best classifier with respect to overall performance was k-nearest neighbor. No classifier attained good enough recall for this task without optimization. In phase II, we boosted performance with optimization for evolutionary support vector machine and complement naïve Bayes classifiers. Generalization performance was better for the latter in the independent tests. For evolutionary support vector machine and complement naïve Bayes classifiers, the initial retrieval set was reduced by 46% and 35%, respectively. Conclusions Machine learning classifiers can help identify nonrandomized studies eligible for full-text screening by systematic reviewers. Optimization can markedly improve performance of classifiers. However, generalizability varies with the classifier. The number of citations to screen during a second independent pass through the citations can be substantially reduced.

show abstract

Section: Methodsmentioning

confidence: 99%

Screening nonrandomized studies for medical systematic reviews: A comparative study of classifiers

Bekhuis

Demner‐Fushman

2012

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…• National and regional level: At this level, how to represent and keep the data of patients typically is a critical research issue [31] . Finding useful information from the data of a national or regional medical center [26,44,55,56] has been a promising research trend in recent years because a data analytics system can verify the assumption and find out interesting patterns from a sufficient amount of data. Moreover, metaheuristic-based data mining algorithms can be used to find out the relationships between symptoms and particular disease, or even the relationships between cause and effect of human behaviors and disease.…”

Section: Research Issues Of Healthcarementioning

confidence: 99%

Metaheuristic Algorithms for Healthcare: Open Issues and Challenges

Tsai

Chiang

Ksentini

et al. 2016

Computers & Electrical Engineering

View full text Add to dashboard Cite

“…Optimization of SVM parameters were performed by evaluating a set of cost-gamma combinations defined using uniform design (UD) method [48]. UD is a technique that scatters a set of points uniformly across the cost-gamma landscape, proposed to alleviate the computational loads associated with the search for the optimal cost-gamma pair [49]. This search process begins by initializing a 30-points UD (global) search across the defined costgamma landscape.…”

Section: Ga-svmmentioning

confidence: 99%

A biological continuum based approach for efficient clinical classification

Tay

Poh

Goh

et al. 2014

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Clinical feature selection problem is the task of selecting and identifying a subset of informative clinical features that are useful for promoting accurate clinical diagnosis. This is a significant task of pragmatic value in the clinical settings as each clinical test is associated with a different financial cost, diagnostic value, and risk for obtaining the measurement. Moreover, with continual introduction of new clinical features, the need to repeat the feature selection task can be very time consuming. Therefore to address this issue, we propose a novel feature selection technique for diagnosis of myocardial infarction - one of the leading causes of morbidity and mortality in many high-income countries. This method adopts the conceptual framework of biological continuum, the optimization capability of genetic algorithm for performing feature selection and the classification ability of support vector machine. Together, a network of clinical risk factors, called the biological continuum based etiological network (BCEN), was constructed. Evaluation of the proposed methods was carried out using the cardiovascular heart study (CHS) dataset. Results demonstrate a significant speedup of 4.73-fold can be achieved for the development of MI classification model. The key advantage of this methodology is the provision of a reusable (feature subset) paradigm for efficient development of up-to-date and efficacious clinical classification models.

show abstract

An efficient SVM-GA feature selection model for large healthcare databases

Cited by 8 publications

References 13 publications

Screening nonrandomized studies for medical systematic reviews: A comparative study of classifiers

Screening nonrandomized studies for medical systematic reviews: A comparative study of classifiers

Metaheuristic Algorithms for Healthcare: Open Issues and Challenges

A biological continuum based approach for efficient clinical classification

Contact Info

Product

Resources

About