LSGDM with Biogeography-Based Optimization (BBO) Model for Healthcare Applications

Area of Science:

• Health Informatics
• Artificial Intelligence in Healthcare
• Big Data Analytics

Background:

• Healthcare management increasingly relies on effective decision-making, particularly multicriteria group decision-making.
• Big data analytics offers potential for disease detection and improved healthcare delivery.
• Limited research exists on large-scale group decision-making (LSDGM) within the context of big data-driven healthcare Industry 4.0.

Purpose of the Study:

• To develop and present a novel MapReduce-based LSDGM (MR-LSDGM) model tailored for the healthcare Industry 4.0 environment.
• To enhance the accuracy and efficiency of decision-making processes in healthcare management.
• To address the gap in research concerning LSDGM in advanced healthcare settings.

Main Methods:

• The MR-LSDGM model employs a three-stage process: clustering decision-makers (DM), modeling DM preferences, and classification.
• Decision-makers are clustered using a hybrid approach combining biogeography-based optimization (BBO) and fuzzy C-means (FCM).
• Subgroup preferences are modeled using the two-tuple fuzzy linguistic representation (2TFLR) technique, with classification utilizing long short-term memory (LSTM) feature extraction and an extreme learning machine (ELM) classifier.

Main Results:

• Experimental analyses demonstrate the effectiveness of the proposed MR-LSDGM model.
• The model successfully handles massive datasets through the MapReduce platform.
• Performance metrics indicate significant improvements in healthcare management decision-making.

Conclusions:

• The developed MR-LSDGM model offers a robust solution for complex decision-making challenges in healthcare Industry 4.0.
• The integration of BBO, FCM, 2TFLR, LSTM, and ELM provides a powerful framework for analyzing large-scale group preferences.
• This research contributes to advancing big data applications in healthcare management and decision support systems.