Abstract

Background: Falls are leading causes of injury, hospitalization, and reduced quality of life among older adults in long-term care (LTC) settings(2,8) .This study explores the use of Natural Language Processing (NLP) to evaluate the uptake and impact of Preventing Falls and Reducing Injury from Falls (2017) best practice guideline (BPG)(4,5,6) in Ontario LTC homes.

Methods: A retrospective qualitative content analysis design was employed, and data were collected from 153 LTC reports submitted between 2015 to 2022 to a qualitative nursing data reporting system(3,4). Unstructured narrative text was processed through tokenization, part-of-speech tagging, stop-word removal, stemming/lemmatization, and keyword extraction via Rapid Automatic Keyword Extraction(1,7). Thematic analysis was supported by expert review, and sentiment analysis to assess alignment with the guideline.

Results: A total of 235 unique themes were extracted. Common themes included personalized care planning, revisions to falls documentation, post-incident evaluations, scheduled rounding, staff education, and policy integration. Sentiment analysis revealed mostly neutral to positive tones, with polarity scores used to visualize differences across submissions. However, gaps were found in documentation of post-fall procedures and policy execution.

Conclusion: NLP offers a scalable and efficient alternative to manual audits for monitoring evidence-based practice in LTC homes. Its ability to process multilingual data and incorporate expert validation enhances its utility across diverse care environments. Embedding the developed NLP algorithms into implementation science offers a practical approach to real-time monitoring of guideline adoption and supports the development of advanced decision-support systems, ultimately improving resident safety and care quality.

Notes

Acknowledgment: This work is funded by the Government of Ontario, Canada. All work produced by the RNAO is editorially independent of its funding source.

References:

1. Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: Analyzing text with the natural language toolkit. O'Reilly Media

2. Kuhnow J, Hoben M, Weeks LE, Barber B, Estabrooks CA. Factors associated with falls in Canadian long term care homes: a retrospective cohort study. Canadian geriatrics journal. 2022 Dec 1;25(4):328.

3. Naik, S., Voong S., Bamford, M., Smith, K., Joyce, A., & Grinspun D. (2020). Assessment of the Nursing Quality Indicators for Reporting and Evaluation (NQuIRE) database using a data quality index. Journal of the American Medical Informatics Association, 27(5), pp. 776-782.

4. Naik S, Grinspun D. RNAO’s artificial intelligence innovations: a novel strategy to advance evidence-based nursing practice. MedUNAB. 2024 July 31;27(1):42–51.

5. MedUNAB R. RNAO’s Artificial Intelligence Innovations: A Novel Strategy to Advance Evidence-Based Nursing Practice. MedUNAB [Internet]. 2024 Dec 6 [cited 2025 Sept 3]; Available from: https://www.academia.edu/126122294/RNAO_s_Artificial_Intelligence_Innovations_A_Novel_Strategy_to_Advance_Evidence_Based_Nursing_Practice

6. Registered Nurses’ Association of Ontario (RNAO). Preventing Falls and Reducing Injury from Falls. 4th ed. Toronto (ON): RNAO; 2017.

7. Rose, S., Engel, D., Cramer, N., & Cowley, W. (2010). Automatic keyword extraction from individual documents. In M. W. Berry & J. Kogan (Eds.), Text Mining: Applications and Theory (pp. 1–20). John Wiley & Sons. https://doi.org/10.1002/9780470689646.ch1

8. Stefanacci RG, Phillips C. Shifting Paradigms in Fall Management for Long-Term Care: From Prevention to Injury Mitigation. Journal of the American Medical Directors Association. 2025 Jun 1;26(6).

Description

This study applies Natural Language Processing to assess falls prevention guideline uptake in Ontario Long Term Care facilities, revealing key themes and sentiment trends that support scalable monitoring of nursing practice.

Author Details

Shanoja Naik, PhD, MPhil, MSc (Stats), MMath, BEd, Director, Registered Nurses Association of Ontario (RNAO), Canada;

Hasitha Wimalarathna, B.Eng, PhD. Machine Learning Developer, RNAO;

Doris Grinspun, RN, BScN, MSN, PhD, LLD(hon), Dr(hc), DHC, FAAN, FCAN, O.ONT., Chief Executive Officer, RNAO

Sigma Membership

Non-member

Type

Presentation

Format Type

Text-based Document

Study Design/Type

Retrospective

Research Approach

Qualitative Research

Keywords:

Long-Term Care, Long Term Care, Interprofessional, Interdisciplinary, Accidental Falls, Accidental Falls--Prevention and Control, Natural Language Processing, Natural Language Processing--Utilization

Conference Name

37th International Nursing Research Congress

Conference Host

Sigma Theta Tau International

Conference Location

Toronto, Ontario, Canada

Conference Year

2026

Rights Holder

All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record. All permission requests should be directed accordingly and not to the Sigma Repository. All submitting authors or publishers have affirmed that when using material in their work where they do not own copyright, they have obtained permission of the copyright holder prior to submission and the rights holder has been acknowledged as necessary.

Review Type

Abstract Review Only: Reviewed by Event Host

Acquisition

Proxy-submission

Date of Issue

2026-08-03

Click above link to access the slide deck.

Share

COinS
 

Evaluating Fall Prevention Implementation Approaches Through Natural Language Processing

Toronto, Ontario, Canada

Background: Falls are leading causes of injury, hospitalization, and reduced quality of life among older adults in long-term care (LTC) settings(2,8) .This study explores the use of Natural Language Processing (NLP) to evaluate the uptake and impact of Preventing Falls and Reducing Injury from Falls (2017) best practice guideline (BPG)(4,5,6) in Ontario LTC homes.

Methods: A retrospective qualitative content analysis design was employed, and data were collected from 153 LTC reports submitted between 2015 to 2022 to a qualitative nursing data reporting system(3,4). Unstructured narrative text was processed through tokenization, part-of-speech tagging, stop-word removal, stemming/lemmatization, and keyword extraction via Rapid Automatic Keyword Extraction(1,7). Thematic analysis was supported by expert review, and sentiment analysis to assess alignment with the guideline.

Results: A total of 235 unique themes were extracted. Common themes included personalized care planning, revisions to falls documentation, post-incident evaluations, scheduled rounding, staff education, and policy integration. Sentiment analysis revealed mostly neutral to positive tones, with polarity scores used to visualize differences across submissions. However, gaps were found in documentation of post-fall procedures and policy execution.

Conclusion: NLP offers a scalable and efficient alternative to manual audits for monitoring evidence-based practice in LTC homes. Its ability to process multilingual data and incorporate expert validation enhances its utility across diverse care environments. Embedding the developed NLP algorithms into implementation science offers a practical approach to real-time monitoring of guideline adoption and supports the development of advanced decision-support systems, ultimately improving resident safety and care quality.