A Commentary on “Deep Learning-Enhanced Hand Grip and Release Test for Degenerative Cervical Myelopathy: Shortening Assessment Duration to 6 Seconds”

Article information

Neurospine. 2025;22(2):613-614

Publication date (electronic) : 2025 June 30

doi : https://doi.org/10.14245/ns.2550126.063

¹Nanfang Hospital, Southern Medical University/The First School of Clinical Medicine, Southern Medical University, Guangzhou, China

²Fuyang Yingdong District Maternal and Child Health Hospital (Fuyang Seventh People’s Hospital), Fuyang, China

Corresponding Author Tian Gao Fuyang Yingdong District Maternal and Child Health Hospital (Fuyang Seventh People’s Hospital), Fuyang, China Email: tiangao1996happy@gmail.com

Received 2025 January 17; Revised 2025 February 9; Accepted 2025 February 16.

To the editor,

Degenerative cervical myelopathy (DCM) is a leading cause of upper limb dysfunction, with hand clumsiness being one of its most prominent early symptoms [1-3]. While the traditional 10-second grip-and-release test has been widely used to assess hand function in DCM patients [3,4], its reliance on video recording and manual cycle counting introduces operational complexity and potential measurement errors [3]. This study innovatively proposes a deep learning-enhanced grip-and-release test (DL-HGRT), which integrates artificial intelligence and portable devices to deliver a more efficient, accurate, and streamlined method for the early diagnosis and management of DCM [5].

A key innovation of this study is the incorporation of the 3D-MobileNetV2 [6] deep learning model into the test, overcoming the limitations of traditional methods and significantly enhancing diagnostic performance. Compared to previous studies, DL-HGRT demonstrated higher sensitivity and specificity, with an area under the receiver operating characteristic curve of 0.93—substantially higher than the 0.71 to 0.77 [7] reported in earlier research. This improvement underscores DL-HGRT’s reliability as a diagnostic tool, particularly in distinguishing DCM patients from healthy individuals. Furthermore, the study revealed that reducing the test duration from the conventional 10 seconds [3] to 6 seconds did not compromise diagnostic accuracy. The 6-second test not only saves time but also reduces the burden of data storage and transmission, making it more practical and accessible. This finding highlights DL-HGRT’s ability to maintain high diagnostic efficiency while significantly enhancing user convenience.

What is surprising about this study is the practicality of the DL-HGRT model. By analyzing grip-and-release cycle counts and average grip times, the study demonstrated that even with a shorter test duration, DL-HGRT could accurately differentiate between DCM patients and healthy controls, paving the way for remote monitoring and screening. Even more impressively, DL-HGRT has the potential to be implemented on smartphones, allowing for home-based monitoring and follow-up, thereby extending clinical tools into everyday life.

Despite its strengths, the study acknowledges some limitations, such as not fully accounting for confounding factors that affect hand function and the potential inclusion of undiagnosed DCM cases in the control group. Additionally, as the study was conducted at a single center with a partial overlap of participants from the authors’ previous study [6], its findings require validation through independent external cohorts to confirm generalizability.

In summary, DL-HGRT demonstrates a meaningful advancement by combining deep learning with traditional testing methods, improving both diagnostic accuracy and operational efficiency. The discovery of the effective 6-second test duration provides a powerful tool for quick and reliable DCM screening. Supported by artificial intelligence and mobile technology, DLHGRT holds immense potential as a critical component in the early detection and intervention of DCM, with promising applications in both clinical and home settings.

Notes

Conflict of Interest

The authors have nothing to disclose.

References

1. Kalsi-Ryan S, Karadimas SK, Fehlings MG. Cervical spondylotic myelopathy: the clinical phenomenon and the current pathobiology of an increasingly prevalent and devastating disorder. Neuroscientist 2013;19:409–21.

2. Law KKP, Lau KKL, Shea GKH, et al. Quantitative physical performance tests can effectively detect degenerative cervical myelopathy: a systematic review and meta-analysis. Eur Spine J 2022;31:3347–64.

3. Ono K, Ebara S, Fuji T, et al. Myelopathy hand. New clinical signs of cervical cord damage. J Bone Joint Surg Br 1987;69:215–9.

4. Hosono N, Sakaura H, Mukai Y, et al. A simple performance test for quantifying the severity of cervical myelopathy. J Bone Joint Surg Br 2008;90:1210–3.

5. Ye Y, Chang Y, Wu W, et al. Deep Learning-enhanced hand grip and release test for degenerative cervical myelopathy: shortening assessment duration to 6 seconds. Neurospine 2024;21:46–56.

6. Zheng S, Liang G, Chen J, et al. Severity assessment of cervical spondylotic myelopathy based on intelligent video analysis. IEEE J Biomed Health Inform 2022;26:4486–96.

7. Machino M, Ando K, Kobayashi K, et al. Cut off value in each gender and decade of 10-s grip and release and 10-s step test: a comparative study between 454 patients with cervical spondylotic myelopathy and 818 healthy subjects. Clin Neurol Neurosurg 2019;184:105414.

Article information Continued

This is an open access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.