Security Risk Assessment of Healthcare Web Application Through Adaptive Neuro-Fuzzy Inference System: A Design...

Area of Science:

• Computer Science
• Information Security
• Healthcare Informatics

Background:

• Ensuring robust security for healthcare web applications is critical for protecting sensitive patient data.
• Traditional security measures require enhancement through advanced techniques for improved efficacy.
• Soft computing offers promising avenues for proactive security risk assessment in web application development.

Purpose of the Study:

• To propose and evaluate the adaptive neuro-fuzzy inference system (ANFIS) for identifying and assessing security risks in healthcare web application development.
• To enhance the overall security posture and longevity of healthcare web applications.
• To introduce a fuzzy regression model for security risk evaluation.

Main Methods:

• Identification of key security risk factors specific to healthcare web application development.
• Application of the adaptive neuro-fuzzy inference system (ANFIS) for quantitative risk assessment.
• Development of a fuzzy regression model to complement ANFIS in risk evaluation.

Main Results:

• The adaptive neuro-fuzzy inference system (ANFIS) demonstrated superior performance in estimating security risks compared to existing methods.
• The proposed ANFIS model provides a more acceptable and accurate estimation of security risks during development.
• Comparative analysis confirmed the efficacy of ANFIS in healthcare web application security assessment.

Conclusions:

• The ANFIS-based approach offers a valuable tool for developers to mitigate security risks in healthcare web applications.
• Implementation of this method can significantly enhance the security of sensitive healthcare data.
• This approach supports proactive risk management, contributing to more secure healthcare information systems.