Back to search

University of San Francisco

Predicting the Risk of Falling with Artificial Intelligence

Abstract

dc:description.abstract

Predicting the Risk of Falling with Artificial Intelligence Abstract Background: Fall prevention is a huge patient safety concern among all healthcare organizations. The high prevalence of patient falls has grave consequences, including the cost of care, longer hospital stays, unintentional injuries, and decreased patient and staff satisfaction. Preventing a patient from falling is critical in maintaining a patient’s quality of life and averting the high cost of healthcare expenses. Local Problem: Two hospitals' healthcare system saw a significant increase in inpatient falls. The fall rate is one of the nursing quality indicators, and fall reduction is a key performance indicator of high-quality patient care. Methods: This quality improvement evidence-based observational project compared the rate of fall (ROF) between the experimental and control unit. Pearson’s chi-square and Fisher’s exact test were used to analyze and compare results. Qualtrics surveys evaluated the nurses’ perception of AI, and results were analyzed using the Mann-Whitney Rank Sum test. Intervention. Implementing an artificial intelligence-assisted fall predictive analytics model that can timely and accurately predict fall risk can mitigate the increase in inpatient falls. Results: The pilot unit (Pearson’s chi-square = p pp<0.001). Conclusions: AI-assisted automatic fall predictive risk assessment produced a significant reduction if the number of falls, the ROF, and the use of fall countermeasures. Further, nurses’ perception of AI improved after the introduction of FPAT and presentation.

Degree

thesis:*
Name thesis:degree_name
Doctor of Nursing Practice (DNP)
Level thesis:degree_level
Project
Discipline thesis:degree_discipline
Nursing

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Aquino, Ann
Contributors dc:contributor
  • Nicholas R. Webb, DNP, RN, ESQ
  • Committee Member: Juli Maxworthy, DNP, Ph.D. (c), MSN, MBA, RN, CNL, CPHQ, CPPS, CHSE, FNAP, FSSH

Subjects

dc:subject × 6

Identifiers

dc:identifier.*
Repository record dc:identifier
https://repository.usfca.edu/dnp/317

Chain of custody

source
Harvested from
University of San Francisco
Base URL
repository.usfca.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Aquino, Ann. Predicting the Risk of Falling with Artificial Intelligence. Project thesis, https://repository.usfca.edu/dnp/317