JMIR Publications

ABSTRACT

Background:

Pressure Injury (PI) is a common and preventable problem，yet it is a challenge for at least two reasons. First, the nurse shortage is a worldwide phenomenon. Second, the majority of nurses have insufficient PI-related knowledge. The growing Machine Learning (ML) technologies can contribute to lessening the burden of medical staff in improving the prognosis and diagnostic accuracy of PI. To our best knowledge, there is no existing systematic review to evaluate how the current ML technologies used in PI management to date.

Objective:

To synthesize and evaluate the literature of using ML technologies in PI management, and identify their strengths and weaknesses, and improvement opportunities for future research and practice.

Methods:

This paper conducted an extensive search on PubMed, Embase, Web of Science, CINAHL, the Cochrane Library, the China National Knowledge Infrastructure (CNKI), the Wanfang database, the VIP database, and the China Biomedical Literature Database to identify relevant articles. Searches were initially performed in September 2019 and were updated in June 2020. Two independent investigators conducted study selection and data extraction.

Results:

A total of thirty-two articles met the inclusion criteria. Twelve of these articles (37.5%) reported ML technologies in developing predictive models to identify risk factors, eleven (34.4%) used them in posture detection and recognition, and nine (28.1%) performed them in image analysis on tissue classification and measurement of PI wounds. These articles presented various algorithms and measured outcomes.

Conclusions:

There is an array of emerging ML technologies used in PI management, their results in the laboratory show promising prospect. Future research should apply these technologies on a large scale with clinical data to further verify and improve their effectiveness.