DATA-DRIVEN CAPACITY MANAGEMENT IN RADIOLOGY: AN ANALYSIS OF TREATABILITY AND PRIORITIZATION POLICIES UNDER SCARCITY OF RESOURCES

Vol 57, 2025 - 339347
Complete Articles (CA)
Favorite this paper
How to cite this paper?
Abstract

Computed Tomography Scheduling is an NP-hard variant of the Patient Appointment Scheduling Problem. This work proposes an architecture that integrates clinical text mining, via Natural Language Processing, to evolutionary optimization. Supported by real data (N = 52,018, 2019–2024), the comparison revealed that, while the annual segmentation of the exact model (MILP) raised the overall cost to Z = 1.74 × 108 , the continuous flow Genetic Algorithm (GA) eliminated clinical damage (Z ≈ 0). The model reduced the median waiting time for urgent cases from 42 to 1 day (p < 0.001), validating the Taguchi Loss Function in radiology. The results demonstrate that full care compliance is feasible without expanding physical resources. The success of the model lies in dynamic management and schedule compaction, which absorb seasonal peaks and align efficiency with Rawls' Maximin Principle.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Universidade Federal de Santa Maria
  • 2 Hospital Universitário de Santa Maria
Track
  • SA – OR in Health
Keywords
Operational Research in Health
Entire Program
Genetic Algorithms.
Natural Language Processing (NLP)
Patient Flow Management