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
. 2025 Jan 7;67(1):uiae075.
doi: 10.1093/joccuh/uiae075.

Application of machine learning for detecting high fall risk in middle-aged workers using video-based analysis of the first 3 steps

Naoki Sakane  1 , Ken Yamauchi  2 , Ippei Kutsuna  1 , Akiko Suganuma  1 , Masayuki Domichi  1 , Kei Hirano  3 , Kengo Wada  3 , Masashi Ishimaru  3 , Mitsuharu Hosokawa  3 , Yosuke Izawa  3 , Yoshihiro Matsumura  3 , Junichi Hozumi  3
Affiliations

Application of machine learning for detecting high fall risk in middle-aged workers using video-based analysis of the first 3 steps

Naoki Sakane et al. J Occup Health. .

Abstract

Objectives: Falls are among the most prevalent workplace accidents, necessitating thorough screening for susceptibility to falls and customization of individualized fall prevention programs. The aim of this study was to develop and validate a high fall risk prediction model using machine learning (ML) and video-based first 3 steps in middle-aged workers.

Methods: Participants to provide training data (n = 190, mean [SD] age = 54.5 [7.7] years, 48.9% male) and validation data (n = 28, age = 52.3 [6.0] years, 53.6% male) were enrolled in this study. Pose estimation was performed using a marker-free deep pose estimation method called MediaPipe Pose. The first 3 steps, including the movements of the arms, legs, trunk, and pelvis, were recorded using an RGB camera, and the gait features were identified. Using these gait features and fall histories, a stratified k-fold cross-validation method was used to ensure balanced training and test data, and the area under the curve (AUC) and 95% CI were calculated.

Results: Of 77 gait features in the first 3 steps, we found 3 gait features in men with an AUC of 0.909 (95% CI, 0.879-0.939) for fall risk, indicating an "excellent" (0.9-1.0) classification, whereas we determined 5 gait features in women with an AUC of 0.670 (95% CI, 0.621-0.719), indicating a "sufficient" (0.6-0.7) classification.

Conclusions: These findings suggest that fall risk prediction can be developed based on ML and the first 3 steps in men; however, the accuracy was only "sufficient" in women. Further development of the formula for women is required to improve its accuracy in the middle-aged working population.

Keywords: accidental falls; falls; gait analysis; machine learning; middle age; risk assessment; workplace.

PubMed Disclaimer

Conflict of interest statement

The KH, KW, MI, MH, YI, YM, JH author has an employment relationship with Panasonic Corporation .

Figures

Figure 1
Figure 1
Gait analysis during the first 3 steps.
Figure 2
Figure 2
The definition of joint points in the MediaPipe Pose.
Figure 3
Figure 3
The definition of gait cycle and the extraction of the data.
Figure 4
Figure 4
Flow diagram of the recruitment, allocation, and analysis.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Parsons R, Blythe RD, Cramb SM, McPhail SM. Inpatient fall prediction models: a scoping review. Gerontology. 2023;69(1):14-29. 10.1159/000525727 - DOI - PubMed
    1. Matarese M, Ivziku D, Bartolozzi F, Piredda M, De Marinis MG. Systematic review of fall risk screening tools for older patients in acute hospitals. J Adv Nurs. 2015;71(6):1198-1209. 10.1111/jan.12542 - DOI - PubMed
    1. Trinh VQ, Zhang S, Kovoor J, et al. The use of natural language processing in detecting and predicting falls within the healthcare setting: a systematic review. Int J Qual Health Care. 2023;35(4)1-16. 10.1093/intqhc/mzad077 - DOI - PMC - PubMed
    1. Park SH. Tools for assessing fall risk in the elderly: a systematic review and meta-analysis. Aging Clin Exp Res. 2018;30(1):1-16. 10.1007/s40520-017-0749-0 - DOI - PubMed
    1. Liu CH, Hu YH, Lin YH. A machine learning-based fall risk assessment model for inpatients. Comput Inform Nurs. 2021;39(8):450-459. 10.1097/CIN.0000000000000727 - DOI - PubMed

Grants and funding