Predictive Models for Necrotizing Soft Tissue Infections: Are the Available Scores Trustable?

Area of Science:

• Infectious Diseases
• Surgical Pathology
• Medical Informatics

Background:

• Necrotizing soft tissue infections (NSTIs) are severe conditions with high morbidity and mortality.
• Early and reliable prognostic assessment tools for NSTIs are lacking in current medical literature.
• Existing scoring systems demonstrate limitations in sensitivity, specificity, and validation for NSTI patients.

Purpose of the Study:

• To review and analyze existing prognostic scoring systems for NSTIs.
• To identify limitations and areas for improvement in current NSTI assessment tools.
• To explore the potential of novel approaches, including AI, for NSTI prognosis.

Main Methods:

• Systematic literature search of PubMed and Google Scholar.
• Overview and critical analysis of five scoring systems: LRINEC, PLR, NLR, NECROSIS, and POTTER.
• Evaluation of each system's strengths, weaknesses, and potential for improvement or novel application.

Main Results:

• The LRINEC score lacks sensitivity and requires supplementary clinical data.
• The NECROSIS score shows promise but needs external validation.
• NLR and PLR offer insights into immune response but lack NSTI specificity.
• The POTTER score, utilizing AI, is innovative but not yet validated for NSTI.

Conclusions:

• A reliable, comprehensive scoring system for NSTI prognosis is still needed.
• Further development is required to address the limitations of existing tools.
• Integrative models, potentially incorporating AI like the POTTER score, may offer future solutions.