Artificial Neural Networks for Medical Diagnosis: A Review of Recent Trends

Fraser, Egba Anwaitu; Okonkwo,; Obikwelu, Raphael

doi:10.5121/ijcses.2020.11301

Cited by 7 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jane and Arockiam [8] reviewed about IoT preprocessing techniques for sensor data and studied about cleaning, transformation, reduction and integration in a detailed manner. Fraser et al [9] evaluated that the high risk of heart patients could be identified easily. Machine learning algorithms are easy to identify diseases when it has been applied on proper suitable datasets proposed by [10].…”

Section: Related Work or Backgroundmentioning

confidence: 99%

Hybrid optimal feature selection approach for internet of things based medical data analysis for prognosis

Bel,

Selvaraj

2024

IJ-AI

View full text Add to dashboard Cite

<p>Healthcare is very important application domain in internet of things (IoT). The aim is to provide a novel combined feature selection (FS) methods like univariate (UV) with tree-based methods (TB), recursive feature elimination (RFE) with least absolute shrinkage selection operator (LASSO), mutual information (MI) with genetic algorithm (GA) and embedded methods (EM) with univariate has been applied to internet of medical things (IoMT)based heart disease dataset. The well-suited machine learning algorithms for IoT medical data are logistic regression (LR) and support vector machine (SVM). Each combined method has been applied to the machine learning algorithms to find the best classifier for prognosis. The various performance metrices has been calculated for all the combined feature selection methods for logistic regression and support vector machine and found that for precise classification could be done using recursive elimination feature selection method with LASSO applied to logistic regression achieved a better performance than all other combined methods with high accuracy, sensitivity and high area under curve. Decision has been taken by data analytics that RFE+LASSO using LR feature selection method will provide an overall better performance for IoT based medical heart disease dataset after comparing all other combined methods with LR and SVM classifiers<em>. </em></p>

show abstract

Section: Related Work or Backgroundmentioning

confidence: 99%

Hybrid optimal feature selection approach for internet of things based medical data analysis for prognosis

Bel,

Selvaraj

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Moreover, they are not limited to forms that are linear or nonlinear. Scholars have employed ANN to solve complicated issues with success [36].Examples include SOM, MLP with BPA, RBFN, LVQ, CNN, RNN, Neuro-fuzzy networks, and so on [37][38] [7]. The researcher using ANN approaches tends to employ distinct kinds of essentials for training and learning data and knowledge representation.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced Modular-Based Neural Network Framework for Effective Medical Diagnosis

Egba, Anwaitu Fraser et al.

2024

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) are a type of machine learning algorithms that are used to solve problems such as medical diagnosis. In recent times, the amount of data that is generated daily is on the increase and the level of the complexity of problems is troubling. ANN algorithms are commonly used to overcome these challenges are further faced with the problem of having fixed data attributes as a dataset for its input layer, the complexity of having heterogeneous datasets instead of homogeneous datasets,and having a single objective output layer instead of a multi-objective output layer that could enable the diagnosis of multiple diseases. This researchproposes an enhanced modular-based Neural Network algorithm that utilizes heterogeneous datasets drawn from multiple sources, decomposed and clustered into independent units, and then trained by ANNs selected according to their learning paradigms -supervised, unsupervised, and reinforcement learning, to provide an effective, efficient and timely medical diagnosis, especially in developing countries where modern facilities are lacking with much dependence on manual methods.Thus an integrated system with multiple ANN techniques modelled into a single unit is developed. The results show that the proposed approach has been significantly successful indealing with the aforesaid problem compared to other methods with a training accuracy of 0.905, Sensitivity of 0.917, and specificity of 0.923.

show abstract

“…ANN has been successfully used by scholars for solving complex problems such as medical diagnosis. Examples include Multi-Layer Perceptron (MLP) with Back Propagation Algorithm (BPA), Self-Organizing Maps (SOM), Learning Vector Quantization (LVQ), Radial Basis Functions (RBFN), Convolutional Neural Networks (CNN), Recurrent Neural Networks, Neuro-fuzzy networks, and so on [5]. Common among the ANN techniques is that each scholar tends to use different types of fundamentals in training and learning data and representation of knowledge.…”

Section: Introductionmentioning

confidence: 99%

A Novel Enhanced Modular-Based Neural Network Framework for Effective Medical Diagnosis

Egba¹

2022

View full text Add to dashboard Cite

Medical diagnosis is a common term used in describing the activities or processes involved in detecting, recognizing, or predicting disease or a group of diseases a patient suffers based on some symptoms and signs exhibited by the patient. The job of a medical practitioner in course of disease diagnosis involves gathering or acquiring symptoms and signs, often from different sources and forms, for analysis and thereafter diagnosis or prognosis. This task is complex due to the heterogeneous and overlapping nature of symptoms and signs and comorbidity of many diseases which often results in errors in accurate diagnosis, misdiagnosis, or under diagnoses. The main objective of this research is to propose a prototype architectural framework based on modular programming principles and that of the operations of the parallel processing design with Flynn's taxonomy of parallel processing. It is believed that several heterogeneous sources datasets can be simultaneously processed concurrently, and a final result presented.

show abstract

Artificial Neural Networks for Medical Diagnosis: A Review of Recent Trends

Cited by 7 publications

References 11 publications

Hybrid optimal feature selection approach for internet of things based medical data analysis for prognosis

Hybrid optimal feature selection approach for internet of things based medical data analysis for prognosis

An Enhanced Modular-Based Neural Network Framework for Effective Medical Diagnosis

A Novel Enhanced Modular-Based Neural Network Framework for Effective Medical Diagnosis

Contact Info

Product

Resources

About