Iranian
Biomedical Journal
Volume 28, Issue 7 (Special Issue 2024)
IBJ 2024, 28(7): 264-264 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Tabatabaei M S, Keramati Asl A, Zibaei F, Bahramnezhad F. Impact of Utilizing Machine Learning for Bedsore Management in Patients Admitted to Critical and Intensive Care Units: A Systematic Review. IBJ 2024; 28 (7) :264-264
URL: http://ibj.pasteur.ac.ir/article-1-4924-en.html
URL: http://ibj.pasteur.ac.ir/article-1-4924-en.html
Abstract:
Introduction: Pressure injuries represent a significant challenge in the medical field, particularly within intensive care units (ICUs), where patients are frequently affected. These injuries impact patients’ quality of life and contribute to increased healthcare costs. Machine learning (ML), a subset of artificial intelligence, is being increasingly integrated into nursing practice for various applications, including the prediction of hospital-acquired pressure injuries. This study employed an ML algorithm using the R programming language to assess the risk of pressure injuries in ICU patients. This study reviewed and compared various ML and artificial intelligence tools.
Search Strategy: A systematic search was conducted in electronic databases using keywords such as “bedsore”, “outcome”, “machine learning”, “ICUs” to identify studies on the application of ML and AI for bedsore management in ICU settings. The electronic databases searched included PubMed, Medline, Embase and Scopus, covering the period from 2020 to 2024. After reviewing 63 articles, about 40 were included in the article, and 16 were utilized in this abstract.
Results: Results showed the promising effects of ML tools in preventing and treating patient bedsores. Pressure mapping systems and wearable devices effectively prevented bedsores by monitoring pressure points and patient movement, alerting caregivers to potential risks. Conversely, computer vision systems, predictive analytics, and natural language processing have facilitated more accurate diagnosis, personalized care plans, and informed decision-making for treating existing bedsores. These ML tools have the potential to significantly enhance patient outcomes and reduce the incidence of bedsores in healthcare settings.
Conclusion and Discussion: This review highlights the potential of ML in managing bedsores in ICUs. Studies have shown that ML models can accurately predict patients at high risk of developing bedsores. Additionally, AI tools can assist in customizing preventive measures and monitoring patients for early signs of pressure injury. However, there are limitations, such as small sample sizes in many studies, and further research is needed to assess the generalizability of the findings. Integrating ML into clinical workflows and addressing concerns regarding the interpretability and bias of these models remain ongoing areas of exploration.
Search Strategy: A systematic search was conducted in electronic databases using keywords such as “bedsore”, “outcome”, “machine learning”, “ICUs” to identify studies on the application of ML and AI for bedsore management in ICU settings. The electronic databases searched included PubMed, Medline, Embase and Scopus, covering the period from 2020 to 2024. After reviewing 63 articles, about 40 were included in the article, and 16 were utilized in this abstract.
Results: Results showed the promising effects of ML tools in preventing and treating patient bedsores. Pressure mapping systems and wearable devices effectively prevented bedsores by monitoring pressure points and patient movement, alerting caregivers to potential risks. Conversely, computer vision systems, predictive analytics, and natural language processing have facilitated more accurate diagnosis, personalized care plans, and informed decision-making for treating existing bedsores. These ML tools have the potential to significantly enhance patient outcomes and reduce the incidence of bedsores in healthcare settings.
Conclusion and Discussion: This review highlights the potential of ML in managing bedsores in ICUs. Studies have shown that ML models can accurately predict patients at high risk of developing bedsores. Additionally, AI tools can assist in customizing preventive measures and monitoring patients for early signs of pressure injury. However, there are limitations, such as small sample sizes in many studies, and further research is needed to assess the generalizability of the findings. Integrating ML into clinical workflows and addressing concerns regarding the interpretability and bias of these models remain ongoing areas of exploration.
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
IBJ is a member of Committee on Publication Ethics (COPE)
and follows its guidelines |
The articles of this journal are licensed under
a Creative Commons Attribution-NonDerivatives 4.0 International License. .png) |
 IBJ is owned and published by Pasteur Institute of Iran |