An evolutionary data-conscious artificial immune recognition system

Tay, Darwin; Poh, Chueh Loo; Kitney, R.I.

doi:10.1145/2463372.2463499

Cited by 5 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…having an independent parameter set for each data class). This, when applied to an immune-inspired algorithm [15], demonstrated improved performance. Therefore a similar technique was implemented in ANCSc algorithm.…”

Section: Data Class-specific Ancsc Parametersmentioning

confidence: 99%

“…The performance of ANCSc algorithm was juxtaposed against Support Vector Machine (SVM) [12][13][14] and Evolutionary Data-Conscious Artificial Immune Recognition System (EDC-AIRS) [15] algorithms in order to corroborate its robustness to learn and generalize. SVM and EDC-AIRS algorithms were selected in this assessment because they have been demonstrated to yield competitive performance when tested with a widely benchmarked heart disease dataset (i.e.…”

Section: Introductionmentioning

confidence: 99%

“…SVM and EDC-AIRS algorithms were selected in this assessment because they have been demonstrated to yield competitive performance when tested with a widely benchmarked heart disease dataset (i.e. Statlog Heart) [15]. Experimental results indicate that ANCSc algorithm achieve a reasonable classification performance and outperforms both SVM and EDC-AIRS algorithms in this clinical risk prediction task.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel neural-inspired learning algorithm with application to clinical risk prediction

Tay

Poh

Kitney

2015

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

Clinical risk prediction - the estimation of the likelihood an individual is at risk of a disease - is a coveted and exigent clinical task, and a cornerstone to the recommendation of life saving management strategies. This is especially important for individuals at risk of cardiovascular disease (CVD) given the fact that it is the leading causes of death in many developed counties. To this end, we introduce a novel learning algorithm - a key factor that influences the performance of machine learning-based prediction models - and utilities it to develop CVD risk prediction tool. This novel neural-inspired algorithm, called the Artificial Neural Cell System for classification (ANCSc), is inspired by mechanisms that develop the brain and empowering it with capabilities such as information processing/storage and recall, decision making and initiating actions on external environment. Specifically, we exploit on 3 natural neural mechanisms responsible for developing and enriching the brain - namely neurogenesis, neuroplasticity via nurturing and apoptosis - when implementing ANCSc algorithm. Benchmark testing was conducted using the Honolulu Heart Program (HHP) dataset and results are juxtaposed with 2 other algorithms - i.e. Support Vector Machine (SVM) and Evolutionary Data-Conscious Artificial Immune Recognition System (EDC-AIRS). Empirical experiments indicate that ANCSc algorithm (statistically) outperforms both SVM and EDC-AIRS algorithms. Key clinical markers identified by ANCSc algorithm include risk factors related to diet/lifestyle, pulmonary function, personal/family/medical history, blood data, blood pressure, and electrocardiography. These clinical markers, in general, are also found to be clinically significant - providing a promising avenue for identifying potential cardiovascular risk factors to be evaluated in clinical trials.

show abstract

Section: Data Class-specific Ancsc Parametersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel neural-inspired learning algorithm with application to clinical risk prediction

Tay

Poh

Kitney

2015

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…To this end, we explore the possibility of customizing MI risk prediction models to better meet the patients' needs and clinicians' expectation. Particularly, the effect of sample age and prediction resolution-two aspects that are not commonly examined in the literature-on the performance of MI risk prediction models constructed using SVM [14]- [16] and evolutionary data-conscious artificial immune recognition system (EDC-AIRS) [17] algorithms were investigated. Here, sample age refers to the average age of individuals found in the baseline (i.e., input) dataset used to construct the clinical risk prediction model while prediction resolution refers to the prediction scale (i.e., number of years into the future where prediction of MI occurrence begins) and interval (i.e., time duration, in years, that marks the start and end of MI outcomes to be considered) employed by the clinical risk prediction model.…”

Section: The Effect Of Sample Age and Prediction Resolution On Myocarmentioning

confidence: 99%

“…EDC-AIRS algorithm [17] is a supervised classification algorithm inspired by the principles and processes associated with the human immune system. It performs classification by first constructing a pool of memory cells (i.e., candidate solutions in the form of data vectors) that are representative of the training data through repetitive optimization of the (values of the) memory cells.…”

Section: MI Risk Prediction Modelsmentioning

confidence: 99%

The Effect of Sample Age and Prediction Resolution on Myocardial Infarction Risk Prediction

Tay

Poh

Reeth

et al. 2015

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Myocardial infarction (MI) is one of the leading causes of death in many developed countries. Hence, early detection of MI events is critical for effective preventative therapies, potentially reducing avoidable mortality. One approach for early disease prediction is the use of risk prediction models developed using machine learning techniques. One important component of these models is to provide clinicians with the flexibility to customize (e.g., the prediction range) and use the risk prediction model that they deemed most beneficial for their patients. Therefore, in this paper, we develop MI prediction models and investigate the effect of sample age and prediction resolution on the performance of MI risk prediction models. The cardiovascular health study dataset was used in this study. Results indicate that the prediction model developed using SVM algorithm is capable of achieving high sensitivity, specificity, and balanced accuracy of 95.3%, 84.8%, and 90.1%, respectively, over a time span of 6 years. Both sample age and prediction resolution were found not to have a significant impact on the performance of MI risk prediction models developed using subjects aged 65 and above. This implies that risk prediction models developed using different sample age and prediction resolution is a feasible approach. These models can be integrated into a computer aided screening tool which clinicians can use to interpret and predict the MI risk status of the individual patients after performing the necessary clinical assessments (e.g., cognitive function, physical function, electrocardiography, general changes to health/lifestyle, and medications) required by the models. This could offer a means for clinicians to screen the patients at risk of having MI in the near future and prescribe early medical intervention to reduce the risk.

show abstract

Risk Prediction Analysis of Cardiovascular Disease Using Supervised Machine Learning Techniques

Ishwarya¹,

Jayanthi²

2020

Proceedings of International Conference on Artificial Intelligence, Smart Grid and Smart City Applications

View full text Add to dashboard Cite

The best thing to avoid strategic human death rates due to curable diseases is to detect them early and prevent their onset. Presently, in our society, large numbers of death rates are due to cardiovascular disease (CVD). Hence early detection of CVD is critical even though many more practices exist for earlier prediction of risk. One approach for early disease risk prediction is the use of risk prediction models developed using machine learning techniques. These models will provide clinicians to treat heart disease of the patient in a better way. Consequently in this chapter, classification mechanisms have been applied to predict the status of the disease. The machine learning algorithms involved in the prediction of CVD are EDC-AIRS, Decision Tree, and SVM. The heart disease dataset from UCI repository has been used in this study. The predictions are denoted by means of accuracy, whereas the performance measures have been calculated in terms of sensitivity, specificity, and F-measure. Results indicate that the prediction model developed using the SVM algorithm is capable of achieving high sensitivity, specificity, balanced accuracy, and F-measure. Further, these models can be integrated into a computer-aided screening tool which clinicians can use to predict the risk status of CVD after performing the necessary clinical assessments.

show abstract

An evolutionary data-conscious artificial immune recognition system

Cited by 5 publications

References 10 publications

A novel neural-inspired learning algorithm with application to clinical risk prediction

A novel neural-inspired learning algorithm with application to clinical risk prediction

The Effect of Sample Age and Prediction Resolution on Myocardial Infarction Risk Prediction

Risk Prediction Analysis of Cardiovascular Disease Using Supervised Machine Learning Techniques

Contact Info

Product

Resources

About