Related Experiment Video
Updated: Oct 20, 2025
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
10.9K
Clinical prediction models for hospital falls: a scoping review protocol
Rex Parsons1, Susanna M Cramb2,3, Steven M McPhail2,4
1Australian Centre for Health Services Innovation and Centre for Healthcare Translation, School of Public Health and Social Work, Queensland University of Technology, Kelvin Grove, Queensland, Australia rex.parsons@hdr.qut.edu.au.
BMJ Open
|September 14, 2021
Summary
This scoping review examines hospital fall prediction models, including machine learning, to improve patient safety. It assesses methodologies and reporting quality to guide future research and clinical practice.
Area of Science:
- Healthcare research
- Clinical informatics
- Patient safety
Background:
- Hospital falls are a common adverse event with significant costs and health impacts.
- Existing fall risk assessments lack clear evidence of effectiveness in acute care settings.
- Digital health records offer new opportunities for real-time fall prediction and clinical decision support.
Purpose of the Study:
- To review methodologies used in developing hospital fall prediction models.
- To assess the reporting quality of existing fall prediction models.
- To compare traditional and non-traditional (e.g., machine learning) fall prediction approaches.
Main Methods:
- A scoping review following the Arksey and O'Malley framework.
- Searches of four electronic databases (CINAHL, PubMed, IEEE Xplore, Embase) up to November 2020.
- Data extraction and reporting quality assessment using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines.
Main Results:
- This section is to be populated upon completion of the review.
- The review will identify and categorize various methodologies for hospital fall prediction.
- Reporting quality of identified studies will be systematically assessed.
Conclusions:
- This review will provide a comprehensive overview of current hospital fall prediction model development.
- Findings will inform the development of more effective, data-driven fall prevention strategies.
- The study highlights the need for standardized reporting in fall prediction model research.
