Computational intelligence approaches for classification of medical data: State-of-the-art, future challenges and research directions

Kalantari, Ali; Kamsin, Amirrudin; Shamshirband, Shahaboddin; Gani, Abdullah; Alinejad‐Rokny, Hamid; Chronopoulos, Anthony T.

doi:10.1016/j.neucom.2017.01.126

Cited by 103 publications

(47 citation statements)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When a patient is assessed, diagnosed, treated, etc., obtaining clinical notes and perceiving them in the right context, organizing medical imaging data, grasping data concerning biomarkers and understanding the substantial amounts genomic data available for each patient that are useful in clinical settings are challenges of big data in healthcare. Nevertheless, data from various sensors and social media sites can be accessed to provide data about the patient's behavioral, psychological and social patterns (Kalantari et al, 2018). In the emergency department, patient information, triage and prioritization become a complex decision-making process during peak times or when many patients need to be assessed at once.…”

Section: Discussionmentioning

confidence: 99%

Healthcare Driven by Big Data Analytics

Alexander

Wang²

2018

American Journal of Engineering and Applied Sciences

View full text Add to dashboard Cite

Text messages and social network posts are often included in big data and are frequently invaluable sources of health data. When machine learning or data mining is used, it is important to perform an automatic process for integrating all available and related health data. Artificial Neural Network (ANN) is one of the machine learning methods flexible in using algorithms to detect complicated nonlinear relationships within huge datasets. Pharmacokinetics uses genetics to individualize drug therapy. Because genetic and pharmacological analysis often require large scale computation, Big Data analytics has shown potential in this area. Personal data from various sensors can often be used for making health and treatment recommendations, taking appropriate action for a patient's lifestyle choices and early diagnosis vital to advancing quality of care. Big data techniques such as hadoop and spark have been used in various areas of healthcare and big data analytics has been employed in great datasets to expose hidden patterns or correlations for effective decision-making. Challenges of big data in healthcare, concerned with gathering material from multifaceted heterogonous patient sources still exist, although hadoop has been employed as the processing unit for heterogeneous data gathered from various body sensors. The most critical necessity in a healthcare big data system is the data security; however, users are continuously applying big data-driven strategies to solve the various problems and challenges.

show abstract

Section: Discussionmentioning

confidence: 99%

Healthcare Driven by Big Data Analytics

Alexander

Wang²

2018

American Journal of Engineering and Applied Sciences

View full text Add to dashboard Cite

show abstract

“…These approaches help in disease diagnosis and other classification purposes [31]. With respect to medical images and the images of text, a new fractal watermarking method is explored in [32]. From the literature, it is understood that a framework for diagnosis of kidney diseases in diabetes patients is still desired.…”

Section: Related Workmentioning

confidence: 99%

A Framework for Diagnosing Kidney Disease in Diabetes Patients Using Classification Algorithms

Prasad¹,

Reddy²,

Puneeth³

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

Data mining algorithms are widely used to extract latent trends or patterns from databases. They are used to predict unknown class labels in order to help in accurate decision making process. The machine learning techniques are very useful in applications of healthcare domain. In this domain, the techniques are employed to diagnose diseases and even predicting the probabilities related to health and other aspects. Since diabetes is one of the diseases that prevail in Indians now and it causes other diseases as well, in this paper we studied the kidney disease diagnosis in diabetes patients. Kidney disease dataset is used to explore four different data mining algorithms. They are known as Naive Bayes, decision table, J48 and random forest. The dataset is used to have both training and testing sets and produce prediction details. These algorithms are evaluated by using measures like accuracy, mean absolute error (MAE) and root-mean-squared error (RMSE). The results revealed that all the machine learning algorithms are able to predict the disease. However, they differ in accuracy levels. With tenfold cross-validation, it is understood that random forest showed the highest accuracy, while Naive Bayes showed least MAE and RMSE. We built prototype application to demonstrate proof of the concept. Our experimental results revealed that the proposed framework to evaluate machine learning algorithms is useful.

show abstract

“…There are also challenges of big data procured from complex healthcare sources (Kalantari et al, 2017).…”

Section: Challengesmentioning

confidence: 99%

Computational Intelligence

Sadiku

Foreman

Musa

2018

ESJ

View full text Add to dashboard Cite

Computational intelligence (CI) refers to recreating human-like intelligence in a computing machine. It consists of a set of computing systems with the ability to learn and deal with new situations such that the systems are perceived to have some attributes of intelligence. It is efficient in solving realworld problems which require reasoning and decision-making. It produces more robust, simpler, and tractable solutions than the traditional techniques. This paper provides a brief introduction to computational intelligence. Keywords: Computational, artificial, intelligence, soft computing IntroductionComputational intelligence (CI) is the study of the design of intelligent systems. A system is regarded as "intelligent" only if it satisfies learning and decision-making requirements. It is familiar that the best-known manifestation of intelligence is human intelligence. The characteristic of "intelligence" is usually attributed to humans so that CI is a way of performing like human beings and using human-like reasoning, i.e. it uses inexact and fuzzy knowledge. Thus, the goal of CI is to recreate human-like intelligence in a human-made machine.The term "computational intelligence" was coined by John McCarthy in 1956. The ongoing worldwide computerization has created new opportunities for researchers. All branches of science and art have become computational: computational biology, computational physics, computational chemistry, computational ecology, computational linguistics, computational electromagnetics, computational finance, computational mechanics, computational social science, computational epistemology, computational intelligence, and so on.CI uses a combination of five main complementary techniques: (1)fuzzy logic which enables the computer to understand natural language, (2)

show abstract

Computational intelligence approaches for classification of medical data: State-of-the-art, future challenges and research directions

Cited by 103 publications

References 136 publications

Healthcare Driven by Big Data Analytics

Healthcare Driven by Big Data Analytics

A Framework for Diagnosing Kidney Disease in Diabetes Patients Using Classification Algorithms

Computational Intelligence

Contact Info

Product

Resources

About