Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Easydiagnos: a framework for accurate feature selection for automatic diagnosis in smart healthcare

Prasenjit Maji, Amit Kumar Mondal, Hemanta Kumar Mondal, Saraju P. Mohanty

TL;DR

An innovative algorithmic method using the Adaptive Feature Evaluator (AFE) algorithm to improve feature selection in healthcare datasets and overcome problems, highlighting its capability to improve clinical decision-making processes in real-world healthcare applications.

Abstract

The rapid advancements in artificial intelligence (AI) have revolutionized smart healthcare, driving innovations in wearable technologies, continuous monitoring devices, and intelligent diagnostic systems. However, security, explainability, robustness, and performance optimization challenges remain critical barriers to widespread adoption in clinical environments. This research presents an innovative algorithmic method using the Adaptive Feature Evaluator (AFE) algorithm to improve feature selection in healthcare datasets and overcome problems. AFE integrating Genetic Algorithms (GA), Explainable Artificial Intelligence (XAI), and Permutation Combination Techniques (PCT), the algorithm optimizes Clinical Decision Support Systems (CDSS), thereby enhancing predictive accuracy and interpretability. The proposed method is validated across three diverse healthcare datasets using six distinct machine learning algorithms, demonstrating its robustness and superiority over conventional feature selection techniques. The results underscore the transformative potential of AFE in smart healthcare, enabling personalized and transparent patient care. Notably, the AFE algorithm, when combined with a Multi-layer Perceptron (MLP), achieved an accuracy of up to 98.5%, highlighting its capability to improve clinical decision-making processes in real-world healthcare applications.

Easydiagnos: a framework for accurate feature selection for automatic diagnosis in smart healthcare

TL;DR

An innovative algorithmic method using the Adaptive Feature Evaluator (AFE) algorithm to improve feature selection in healthcare datasets and overcome problems, highlighting its capability to improve clinical decision-making processes in real-world healthcare applications.

Abstract

The rapid advancements in artificial intelligence (AI) have revolutionized smart healthcare, driving innovations in wearable technologies, continuous monitoring devices, and intelligent diagnostic systems. However, security, explainability, robustness, and performance optimization challenges remain critical barriers to widespread adoption in clinical environments. This research presents an innovative algorithmic method using the Adaptive Feature Evaluator (AFE) algorithm to improve feature selection in healthcare datasets and overcome problems. AFE integrating Genetic Algorithms (GA), Explainable Artificial Intelligence (XAI), and Permutation Combination Techniques (PCT), the algorithm optimizes Clinical Decision Support Systems (CDSS), thereby enhancing predictive accuracy and interpretability. The proposed method is validated across three diverse healthcare datasets using six distinct machine learning algorithms, demonstrating its robustness and superiority over conventional feature selection techniques. The results underscore the transformative potential of AFE in smart healthcare, enabling personalized and transparent patient care. Notably, the AFE algorithm, when combined with a Multi-layer Perceptron (MLP), achieved an accuracy of up to 98.5%, highlighting its capability to improve clinical decision-making processes in real-world healthcare applications.
Paper Structure (27 sections, 7 equations, 14 figures, 6 tables, 3 algorithms)

This paper contains 27 sections, 7 equations, 14 figures, 6 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Contribution of the Work
  3. Problems Addressed in the Current Work
  4. Solution Proposed
  5. Novelty of the Work
  6. Related Prior Research
  7. Challenges in Deploying XAI for Healthcare Applications
  8. The Proposed Novel EasyDiagnos Framework
  9. What is XAI?
  10. Genetic Algorithm and PCT for Feature Selection
  11. Exploration of Classification Techniques
  12. Logistic Regression
  13. Decision Tree
  14. Gaussian Naive Bayes
  15. Random Forest
  16. ...and 12 more sections

Figures (14)

  • Figure 1: System Model for Integrating Explainable AI in Clinical Decision Support Systems
  • Figure 2: Workflow framework of the proposed approach
  • Figure 3: Calculating the marginal distribution for a feature
  • Figure 4: Calculating the shapley value for a feature
  • Figure 5: AFE (Adaptive Feature Evaluator) algorithm flowchart
  • ...and 9 more figures