Using Machine Learning Technologies in Pressure Injury Management: Systematic Review

Area of Science:

• Medical Technology
• Artificial Intelligence in Healthcare
• Clinical Informatics

Background:

• Pressure injuries (PI) pose significant challenges due to nurse shortages and knowledge gaps.
• Machine learning (ML) offers potential solutions for improving PI prognosis and diagnostic accuracy.
• A systematic review evaluating ML applications in PI management is currently lacking.

Purpose of the Study:

• To synthesize and evaluate the existing literature on ML technologies in PI management.
• To identify the strengths and weaknesses of current ML applications in PI care.
• To highlight opportunities for future research and clinical practice improvements.

Main Methods:

• An extensive literature search was conducted across multiple databases (PubMed, EMBASE, CINAHL, etc.) in June 2020.
• Two independent investigators performed study selection, data extraction, and quality appraisal.
• Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST).

Main Results:

• 32 articles met the inclusion criteria, focusing on ML for PI management.
• ML was used for predictive modeling (38%), posture detection (34%), and image analysis (28%).
• The overall risk of bias across the studies was judged as high.

Conclusions:

• Emerging ML technologies show promising laboratory results for PI management.
• Future research should focus on large-scale clinical data validation to enhance ML effectiveness.
• Improving the methodological quality of ML studies in PI is crucial for clinical translation.