An intelligent community-based system for healthcare prioritisation

Area of Science:

• Health Policy and Management
• Artificial Intelligence in Healthcare
• Bioethics

Background:

• Healthcare systems face resource constraints, necessitating rationing decisions.
• Rationing must balance efficiency with socially accepted values.
• Ethical considerations are paramount in patient prioritization.

Purpose of the Study:

• To develop a multi-criteria decision-support system (Vital Priority System) for patient prioritization.
• To operationalize public preferences into an AI-based framework for healthcare rationing.
• To create a transparent, consistent, and ethically grounded tool for healthcare professionals.

Main Methods:

• Utilized a Random Forest algorithm trained on data from a Portuguese online survey.
• Incorporated nine rationing criteria: clinical need, life expectancy gain, quality of life improvement, age, waiting time, parental status, lifestyle responsibility, and social role.
• Classified patients into 'priority' or 'non-priority' groups.

Main Results:

• Clinical need, expected treatment effectiveness, waiting time, and age were the most influential factors.
• Parental status showed moderate influence.
• Lifestyle and social role factors had the least weight in the prioritization model.

Conclusions:

• The Vital Priority System provides a replicable AI framework for fairer patient prioritization in Portugal.
• The system operationalizes public preferences, enhancing ethical decision-making in healthcare rationing.
• This AI-driven approach offers a transparent and consistent tool for healthcare professionals.