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
. 2023 Jan 28;10(2):172.
doi: 10.3390/bioengineering10020172.

Smart Work Injury Management (SWIM) System: A Machine Learning Approach for the Prediction of Sick Leave and Rehabilitation Plan

Peter H F Ng  1   2 , Peter Q Chen  2 , Zackary P T Sin  2 , Sun H S Lai  3 , Andy S K Cheng  1
Affiliations

Smart Work Injury Management (SWIM) System: A Machine Learning Approach for the Prediction of Sick Leave and Rehabilitation Plan

Peter H F Ng et al. Bioengineering (Basel). .

Abstract

As occupational rehabilitation services are part of the public medical and health services in Hong Kong, work-injured workers are treated along with other patients and are not considered a high priority for occupational rehabilitation services. The idea of a work trial arrangement in the private market occurred to meet the need for a more coordinated occupational rehabilitation practice. However, there is no clear service standard in private occupational rehabilitation services nor concrete suggestions on how to offer rehabilitation plans to injured workers. Electronic Health Records (EHRs) data can provide a foundation for developing a model to improve this situation. This project aims at using a machine-learning-based approach to enhance the traditional prediction of disability duration and rehabilitation plans for work-related injury and illness. To help patients and therapists to understand the machine learning result, we also developed an interactive dashboard to visualize machine learning results. The outcome is promising. Using the variational autoencoder, our system performed better in predicting disability duration. We have around 30% improvement compared with the human prediction error. We also proposed further development to construct a better system to manage the work injury case.

Keywords: artificial intelligence; electronic health record; interactive dashboard; rehabilitation case management; rehabilitation plan; variational autoencoder; work injury.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Overview of our current work (SWIM 1.0).
Figure 2
Figure 2
Overview of the machine learning and latent space concept in SWIM 1.0.
Figure 3
Figure 3
Dynamic logs count for each strategy.
Figure 4
Figure 4
Concept of latent space in SWIM 1.0.
Figure 5
Figure 5
Network architecture.
Figure 6
Figure 6
Sample screen of SWIM 1.0.
Figure 7
Figure 7
Error metrics of all industries (N = 2932).
Figure 8
Figure 8
Accuracy of: (a) BLM test cases using KNN; (b) HLM test cases using KNN.
Figure 9
Figure 9
Distribution of: (a) predicted DS probability; (b) predicted legal probability.
Figure 10
Figure 10
Overall concept of SWIM 2.0 development.
Figure 11
Figure 11
Comparison of SWIM 1.0 and 2.0 prediction model.
Figure 12
Figure 12
Overall flow of new case management in SWIM 2.0.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Liu S., Vahedian F., Hachen D., Lizardo O., Poellabauer C., Striegel A., Milenković T. Heterogeneous Network Approach to Predict Individuals’ Mental Health. ACM Trans. Knowl. Discov. Data. 2021;15:1–26. doi: 10.1145/3429446. - DOI
    1. Wang Y., Chen W., Pi D., Yue L. Adversarially regularized medication recommendation model with multi-hop memory network. Knowl. Inf. Syst. 2021;63:125–142. doi: 10.1007/s10115-020-01513-9. - DOI
    1. Yao L., Zhang Y., Wei B., Zhang W., Jin Z. A Topic Modeling Approach for Traditional Chinese Medicine Prescriptions. IEEE Trans. Knowl. Data Eng. (TKDE) 2018;30:1007–1021. doi: 10.1109/TKDE.2017.2787158. - DOI
    1. Spiotta M., Terenziani P., Dupré D.T. Temporal Conformance Analysis and Explanation of Clinical Guidelines Execution: An Answer Set Programming Approach. IEEE Trans. Knowl. Data Eng. 2017;29:2567–2580. doi: 10.1109/TKDE.2017.2734084. - DOI
    1. Solares J.R., Raimondi F.E., Zhu Y., Rahimian F., Canoy D., Tran J., Gomes A.C., Payberah A.H., Zottoli M., Nazarzadeh M., et al. Deep learning for electronic health records: A comparative review of multiple deep neural architectures. J. Biomed. Inform. 2020;101:103337. doi: 10.1016/j.jbi.2019.103337. - DOI - PubMed