Early infectious diseases identification based on complex probabilistic hesitant fuzzy N-soft information

Area of Science:

• Medical informatics
• Decision science
• Fuzzy set theory

Background:

• Infectious diseases pose a significant public health challenge in Pakistan, contributing to high morbidity and mortality.
• Similar clinical presentations of diseases like tuberculosis, hepatitis, COVID-19, dengue, and malaria complicate accurate diagnosis.
• Economic limitations in Pakistan hinder access to essential diagnostic kits and treatment options, exacerbating diagnostic difficulties.

Purpose of the Study:

• To address the diagnostic challenges faced by medical professionals in Pakistan concerning infectious diseases.
• To introduce a novel mathematical framework for improved disease identification and decision-making in resource-limited settings.
• To develop and validate a new decision-making algorithm utilizing complex probabilistic hesitant fuzzy N-soft sets for medical diagnosis.

Main Methods:

• Introduction and definition of the complex probabilistic hesitant fuzzy N-soft set and its fundamental operations (union, intersection, complements, soft logical operators).
• Exploration of the theoretical properties, theorems, and proofs associated with the proposed N-soft set structure.
• Development of decision-making algorithms designed for medical professionals to interpret complex probabilistic hesitant fuzzy N-soft information for disease diagnosis.

Main Results:

• The study defines novel operations and properties for complex probabilistic hesitant fuzzy N-soft sets, providing a robust mathematical foundation.
• Algorithms were developed to facilitate disease identification using the proposed N-soft set framework, aiding clinical decision-making.
• Numerical illustrations and comparative analyses demonstrated the practical applicability and sensitivity of the developed approach in case studies.

Conclusions:

• The complex probabilistic hesitant fuzzy N-soft set offers a promising tool to overcome diagnostic uncertainties in infectious disease management.
• The developed algorithms can assist healthcare providers in Pakistan and similar settings to make more informed and accurate diagnostic decisions.
• This research contributes a novel methodology to medical informatics and decision science for tackling complex diagnostic challenges in public health.