The application of artificial intelligence (AI) techniques to identify frailty within a residential aged care administrative data set

Journal article


Ambagtsheer, R. C., Shafiabady, N., Dent, E., Seiboth, C. and Beilby, J.. (2020). The application of artificial intelligence (AI) techniques to identify frailty within a residential aged care administrative data set. International Journal of Medical Informatics. 136, p. Article 104094. https://doi.org/10.1016/j.ijmedinf.2020.104094
AuthorsAmbagtsheer, R. C., Shafiabady, N., Dent, E., Seiboth, C. and Beilby, J.
Abstract

Introduction
Research has shown that frailty, a geriatric syndrome associated with an increased risk of negative outcomes for older people, is highly prevalent among residents of residential aged care facilities (also called long term care facilities or nursing homes). However, progress on effective identification of frailty within residential care remains at an early stage, necessitating the development of new methods for accurate and efficient screening.

Objectives
We aimed to determine the effectiveness of artificial intelligence (AI) algorithms in accurately identifying frailty among residents aged 75 years and over in comparison with a calculated electronic Frailty Index (eFI) based on a routinely-collected residential aged care administrative data set drawn from 10 residential care facilities located in Queensland, Australia. A secondary objective included the identification of best-performing candidate algorithms.

Methods
We designed a frailty prediction system based on the eFI identification of frailty, allocating 84.5 % and 15.5 % of the data to training and test data sets respectively. We compared the performance of 18 specific scenarios to predict frailty against eFI based on unique combinations of three ML algorithms (support vector machines [SVM], decision trees [DT] and K-nearest neighbours [KNN]) and six cases (6, 10, 11, 14, 39 and 70 input variables). We calculated accuracy, percentage positive and negative agreement, sensitivity, specificity, Cohen’s kappa and Prevalence- and Bias- Adjusted Kappa (PABAK), table frequencies and positive and negative predictive values.

Results
Of 592 eligible resident records, 500 were allocated to the training set and 92 to the test set. Three scenarios (10, 11 and 70 input variables), all based on SVM algorithm, returned overall accuracy above 75 %.
Conclusions
There is some potential for AI techniques to contribute towards better frailty identification within residential care. However, potential benefits will need to be weighed against administrative burden, data quality concerns and presence of potential bias.

Keywordsartificial intelligence; frailty; residential facilities; machine learning; health records; persona
Year2020
JournalInternational Journal of Medical Informatics
Journal citation136, p. Article 104094
PublisherElsevier Ireland, Ltd.
ISSN1386-5056
Digital Object Identifier (DOI)https://doi.org/10.1016/j.ijmedinf.2020.104094
Page range1-6
FunderNational Health and Medical Research Council (NHMRC)
Publisher's version
License
All rights reserved
File Access Level
Controlled
Output statusPublished
Publication dates
Online10 Feb 2020
Publication process dates
Accepted02 Feb 2020
Deposited17 Feb 2025
Grant ID1112672
1102208
Permalink -

https://acuresearchbank.acu.edu.au/item/9153v/the-application-of-artificial-intelligence-ai-techniques-to-identify-frailty-within-a-residential-aged-care-administrative-data-set

Restricted files

Publisher's version

  • 8
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month
These values are for the period from 19th October 2020, when this repository was created.

Export as

Related outputs

Efficient energy utilization in smart grids an artificial intelligence perspective
Qadir, Zakria, Khan, Yasir Ali, Rana, Muhammad Tausif Afzal, Din, Fareed Ud and Shafiabady, Niusha. (2025). Efficient energy utilization in smart grids an artificial intelligence perspective. In In Bhatia, Tarandeep Kaur, El Hajjami, Salma, Kaushik, Keshav, Diallo, Gayo, Ouaissa, Mariya and Khan, Inam Ullah (Ed.). Ethical artificial intelligence in power electronics pp. 133-147 CRC Press. https://doi.org/10.1201/9781032648323-9
AI is everywhere – including countless applications you’ve likely never heard of
Shafiabady, Niusha. (2024). AI is everywhere – including countless applications you’ve likely never heard of The Conversation Media Group.
eXplainable Artificial Intelligence (XAI) for improving organisational regility
Shafiabady, Niusha, Hadjinicolaou, Nick, Hettikankanamage, Nadeesha, MohammadiSavadkoohi, Ehsan, Wu, Robert M. X. and Vakilian, James. (2024). eXplainable Artificial Intelligence (XAI) for improving organisational regility. PLoS ONE. 19(4), p. Article e0301429. https://doi.org/10.1371/journal.pone.0301429
Real-time structural health monitoring of bridges using convolutional neural network-based loss factor analysis for enhanced energy dissipation detection
Nguyen, Thanh Q., Vu, Tu B., Shafiabady, Niusha, Nguyen, Thuy T. and Nguyen, Phuoc T.. (2024). Real-time structural health monitoring of bridges using convolutional neural network-based loss factor analysis for enhanced energy dissipation detection. Structures. 70, p. Article 107733. https://doi.org/10.1016/j.istruc.2024.107733
Comparative study of ten machine learning algorithms for short-term forecasting in gas warning systems
Wu, Robert M.X., Shafiabady, Niusha, Zhang, Huan, Lu, Haiyan, Gide, Ergun, Liu, Jinrong and Charbonnier, Clement Franck Benoit. (2024). Comparative study of ten machine learning algorithms for short-term forecasting in gas warning systems. Scientific Reports. 14(1), pp. 1-18. https://doi.org/10.1038/s41598-024-67283-4
Whose job will AI replace? Here’s why a clerk in Ethiopia has more to fear than one in California
Shafiabady, Niusha. (2023). Whose job will AI replace? Here’s why a clerk in Ethiopia has more to fear than one in California The Conversation Media Group.
Using Artificial Intelligence (AI) to predict organizational agility
Shafiabady, Niusha, Hadjinicolaou, Nick, Din, Fareed Ud, Bhandari, Binayak, Wu, Robert M. X. and Vakilian, James. (2023). Using Artificial Intelligence (AI) to predict organizational agility. PLoS ONE. 18(5), p. Article e0283066. https://doi.org/10.1371/journal.pone.0283066
Using multi-focus group method as an effective tool for eliciting business system requirements : Verified by a case study
Wu, Robert M. X., Wang, Yongwen, Shafiabady, Niusha, Zhang, Huan, Yan, Wanjun, Gou, Jinwen, Shi, Yong, Liu, Bao, Gide, Ergun, Kang, Changlong, Zhang, Zhongwu, Shen, Bo, Li, Xiaoquan, Fan, Jianfeng, He, Xiangqian, Soar, Jeffrey, Zhao, Haijun, Sun, Lei, Huo, Wenying and Wang, Ya. (2023). Using multi-focus group method as an effective tool for eliciting business system requirements : Verified by a case study. PLoS ONE. 18(3), p. Article e0281603. https://doi.org/10.1371/journal.pone.0281603
Identifying presence of cybersickness symptoms using AI-based predictive learning algorithms
Zaidi, Syed Fawad M., Shafiabady, Niusha and Beilby, Justin. (2023). Identifying presence of cybersickness symptoms using AI-based predictive learning algorithms. Virtual Reality. 27(4), pp. 3613-3620. https://doi.org/10.1007/s10055-023-00813-z
V-CarE—A conceptual conceptual design model for providing COVID-19 pandemic awareness : Proposal for a virtual reality design approach to facilitate people with persistent postural-perceptual dizziness
Zaidi, Syed Fawad M., Shafiabady, Niusha, Afifi, Shereen and Beilby, Justin. (2023). V-CarE—A conceptual conceptual design model for providing COVID-19 pandemic awareness : Proposal for a virtual reality design approach to facilitate people with persistent postural-perceptual dizziness. JMIR Research Protocols. 12, p. Article e38369. https://doi.org/10.2196/38369
An FSV analysis approach to verify the robustness of the triple-correlation analysis theoretical framework
Wu, Robert M. X., Zhang, Zhongwu, Zhang, Huan, Wang, Yongwen, Shafiabady, Niusha, Yan, Wanjun, Gou, Jinwen, Gide, Ergun and Zhang, Siqing. (2023). An FSV analysis approach to verify the robustness of the triple-correlation analysis theoretical framework. Scientific Reports. 13(1), p. Article 9621. https://doi.org/10.1038/s41598-023-35900-3
Implementation of transformer-based deep learning architecture for the development of surface roughness classifier using sound and cutting force signals
Bhandari, Binayak, Park, Gijun and Shafiabady, Niusha. (2023). Implementation of transformer-based deep learning architecture for the development of surface roughness classifier using sound and cutting force signals. Neural Computing and Applications. 35(18), pp. 13275-13292. https://doi.org/10.1007/s00521-023-08425-z
Evolving Hybrid partial genetic algorithm classification model for cost-effective frailty screening : Investigative study
Oates, John, Shafiabady, Niusha, Ambagtsheer, Rachel, Beilby, Justin, Seiboth, Chris and Dent, Elsa. (2022). Evolving Hybrid partial genetic algorithm classification model for cost-effective frailty screening : Investigative study. JMIR Aging. 5(4), p. Article e38464. https://doi.org/10.2196/38464
ST (Shafiabady-Teshnehlab) optimization algorithm
Shafiabady, Niusha. (2018). ST (Shafiabady-Teshnehlab) optimization algorithm. In In Tan, Ying (Ed.). Swarm intelligence : Volume 2 : Innovation, new algorithms and methods pp. 83-110 The Institution of Engineering and Technology. https://doi.org/10.1049/pbce119g_ch4
Acute effects of methadone on EEG power spectrum and event-related potentials among heroin dependents
Motlagh, Farid, Ibrahim, Fatimah, Rashid, Rusdi, Shafiabady, Niusha, Seghatoleslam, Tahereh and Habil, Hussain. (2018). Acute effects of methadone on EEG power spectrum and event-related potentials among heroin dependents. Psychopharmacology. 235(11), pp. 3273-3288. https://doi.org/10.1007/s00213-018-5035-0