An evidence-fused neutrosophic framework for uncertainty-aware treatment selection

Area of Science:

• Decision Analysis
• Healthcare Management
• Uncertainty Quantification

Background:

• Healthcare decision-making faces challenges with incomplete data, conflicting expert opinions, and variability.
• Conventional Multi-Criteria Decision Making (MCDM) methods struggle with vagueness, indeterminacy, and inter-expert conflict.
• Existing neutrosophic approaches lack mechanisms for resolving expert conflicts before ranking.

Purpose of the Study:

• To present an integrated decision-support framework for healthcare treatment selection.
• To address limitations of existing methods in handling uncertainty and conflicting expert judgments.
• To provide a robust and scalable tool for complex healthcare environments.

Main Methods:

• Utilizes Neutrosophic Logic for truth, indeterminacy, and falsity.
• Employs Interval-Valued Fuzzy Sets (IVFS) to capture data variability.
• Integrates Dempster-Shafer Theory (DST) for evidence-theoretic fusion of expert opinions.
• Applies an extended Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for ranking.

Main Results:

• The framework transforms neutrosophic evaluations into interval-valued fuzzy representations.
• DST systematically fuses expert judgment, avoiding premature consensus.
• Extended TOPSIS generates belief-weighted neutrosophic score rankings.
• Sensitivity analysis and Monte Carlo simulations demonstrate ranking stability and robustness under uncertainty.

Conclusions:

• The proposed framework offers an uncertainty-aware decision-support tool for healthcare.
• It provides interpretable treatment prioritization, handling incomplete data and conflicting opinions.
• The approach is scalable and shows robustness, requiring further validation with real clinical data.