Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Nov 29;19(23):15919.
doi: 10.3390/ijerph192315919.

Facilitators and Barriers of Artificial Intelligence Applications in Rehabilitation: A Mixed-Method Approach

Mashael Alsobhi  1 , Harpreet Singh Sachdev  2 , Mohamed Faisal Chevidikunnan  1 , Reem Basuodan  3 , Dhanesh Kumar K U  4 , Fayaz Khan  1
Affiliations

Facilitators and Barriers of Artificial Intelligence Applications in Rehabilitation: A Mixed-Method Approach

Mashael Alsobhi et al. Int J Environ Res Public Health. .

Abstract

Artificial intelligence (AI) has been used in physical therapy diagnosis and management for various impairments. Physical therapists (PTs) need to be able to utilize the latest innovative treatment techniques to improve the quality of care. The study aimed to describe PTs' views on AI and investigate multiple factors as indicators of AI knowledge, attitude, and adoption among PTs. Moreover, the study aimed to identify the barriers to using AI in rehabilitation. Two hundred and thirty-six PTs participated voluntarily in the study. A concurrent mixed-method design was used to document PTs' opinions regarding AI deployment in rehabilitation. A self-administered survey consisting of several aspects, including demographic, knowledge, uses, advantages, impacts, and barriers limiting AI utilization in rehabilitation, was used. A total of 63.3% of PTs reported that they had not experienced any kind of AI applications at work. The major factors predicting a higher level of AI knowledge among PTs were being a non-academic worker (OR = 1.77 [95% CI; 1.01 to 3.12], p = 0.04), being a senior PT (OR = 2.44, [95%CI: 1.40 to 4.22], p = 0.002), and having a Master/Doctorate degree (OR = 1.97, [95%CI: 1.11 to 3.50], p = 0.02). However, the cost and resources of AI were the major reported barriers to adopting AI-based technologies. The study highlighted a remarkable dearth of AI knowledge among PTs. AI and advanced knowledge in technology need to be urgently transferred to PTs.

Keywords: Artificial intelligence; clinical decision support; intention to use; perceived barriers; physical therapist.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Multiple responses percentages of AI information sources. Social media and class lectures were the frequent documented source of AI knowledge among PTs.
Figure 2
Figure 2
Frequency of the main themes generated from PTs’ responses to the first open-ended question. Theme 1 was the predominant theme that showed most PTs believed in the customization of AI based on patients’ impairments.
Figure 3
Figure 3
Frequency of the main themes generated from PTs’ responses to the second open-ended question. Cost and available resources of AI were the frequently documented barrier to AI adoption among PTs.
See this image and copyright information in PMC

References

    1. Buldt A.K., Murley G.S., Butterworth P., Levinger P., Menz H.B., Landorf K.B. The relationship between foot posture and lower limb kinematics during walking: A systematic review. Gait Posture. 2013;38:363–372. doi: 10.1016/j.gaitpost.2013.01.010. - DOI - PubMed
    1. Gait Deviations of Patients with Ruptured Anterior Cruciate Ligament: A Cross-Sectional Gait Analysis Study on Male Patients|Knee Surgery & Related Research|Full Text. [(accessed on 19 September 2022)]. Available online: https://kneesurgrelatres.biomedcentral.com/articles/10.1186/s43019-021-0.... - DOI - PMC - PubMed
    1. Lee M.H., Siewiorek D.P., Smailagic A., Bernardino A. Opportunities of a Machine Learning-based Decision Support System for Stroke Rehabilitation Assessment. [(accessed on 13 May 2022)];arXiv. 2020 Available online: http://arxiv.org/abs/2002.12261.2002.12261
    1. Wu H., Chan N.-K., Zhang C.J.P., Ming W.-K. The Role of the Sharing Economy and Artificial Intelligence in Health Care: Opportunities and Challenges. J. Med. Internet Res. 2019;21:e13469. doi: 10.2196/13469. - DOI - PMC - PubMed
    1. Tack C. Artificial intelligence and machine learning | applications in musculoskeletal physiotherapy. Musculoskelet. Sci. Pract. 2018;39:164–169. doi: 10.1016/j.msksp.2018.11.012. - DOI - PubMed

LinkOut - more resources