A Multiattribute Decision-Making Framework for Multidisciplinary Lung Cancer Treatment Considering Expert Willingness...

Area of Science:

• Oncology
• Decision Science
• Artificial Intelligence

Background:

• Lung cancer necessitates personalized treatment strategies based on complex patient data.
• Multidisciplinary treatment (MDT) aims to improve patient outcomes but involves intricate decision-making.
• Existing multiattribute multiexpert decision-making (MAMEDM) models often fail to account for experts' willingness to modify their initial opinions.

Purpose of the Study:

• To develop an advanced MAMEDM framework that incorporates and maximizes experts' willingness for opinion transformation.
• To improve the consensus-building process in generating optimal lung cancer treatment plans.
• To enhance the acceptance and effectiveness of treatment recommendations in clinical practice.

Main Methods:

• Utilized a linguistic scale function for preprocessing expert linguistic evaluations.
• Employed a fuzzy clustering algorithm to group experts based on their opinions.
• Determined subgroup weights using network centrality and professional titles.
• Aggregated expert opinions by maximizing willingness for opinion transformation.
• Applied the ORESTE method for ranking lung cancer treatment options.

Main Results:

• The proposed MAMEDM framework effectively integrates experts' willingness to revise evaluations.
• Expert opinion aggregation considering willingness for transformation led to enhanced decision acceptance.
• The framework demonstrated a reduced impact of noncooperative behaviors in the decision-making process.
• A case study on lung cancer treatment generation validated the framework's effectiveness.

Conclusions:

• Incorporating experts' willingness to adjust opinions is crucial for effective MAMEDM in complex medical scenarios like lung cancer treatment.
• The developed framework offers a more realistic and cooperative approach to multidisciplinary treatment planning.
• This methodology has the potential to improve shared decision-making and patient outcomes in oncology.