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
. 2024 Jan 1;13(1):253.
doi: 10.3390/jcm13010253.

Verification of the Accuracy of Cervical Spinal Cord Injury Prognosis Prediction Using Clinical Data-Based Artificial Neural Networks

Jun Kishikawa  1   2 , Kazu Kobayakawa  2 , Hirokazu Saiwai  2 , Kazuya Yokota  1 , Kensuke Kubota  1 , Tetsuo Hayashi  1 , Yuichiro Morishita  1 , Muneaki Masuda  1 , Hiroaki Sakai  1 , Osamu Kawano  1 , Yasuharu Nakashima  2 , Takeshi Maeda  1
Affiliations

Verification of the Accuracy of Cervical Spinal Cord Injury Prognosis Prediction Using Clinical Data-Based Artificial Neural Networks

Jun Kishikawa et al. J Clin Med. .

Abstract

Background: In patients with cervical spinal cord injury (SCI), we need to make accurate prognostic predictions in the acute phase for more effective rehabilitation. We hypothesized that a multivariate prognosis would be useful for patients with cervical SCI.

Methods: We made two predictive models using Multiple Linear Regression (MLR) and Artificial Neural Networks (ANNs). We adopted MLR as a conventional predictive model. Both models were created using the same 20 clinical parameters of the acute phase data at the time of admission. The prediction results were classified by the ASIA Impairment Scale. The training data consisted of 60 cases, and prognosis prediction was performed for 20 future cases (test cohort). All patients were treated in the Spinal Injuries Center (SIC) in Fukuoka, Japan.

Results: A total of 16 out of 20 cases were predictable. The correct answer rate of MLR was 31.3%, while the rate of ANNs was 75.0% (number of correct answers: 12).

Conclusion: We were able to predict the prognosis of patients with cervical SCI from acute clinical data using ANNs. Performing effective rehabilitation based on this prediction will improve the patient's quality of life after discharge. Although there is room for improvement, ANNs are useful as a prognostic tool for patients with cervical SCI.

Keywords: artificial intelligence; artificial neural networks (ANNs); cervical spinal cord injury; prognosis prediction; rehabilitation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
ANNs are inspired by the sophisticated functionality of human brains.
Figure 2
Figure 2
They are comprised of a large number of connected nodes, each of which performs a simple mathematical operation.
Figure 3
Figure 3
We adopted neural networks in JMP® Pro version 14.2.0 (SAS Institute Inc., Cary, NC, USA). Weight Decay is used as a penalty method. It consists of input, 1st, 2nd, and output layers. The number of nodes in the 1st and 2nd layers are 5 and 10, respectively. The outputs are the ASIA Impairment Scale (AIS) at hospital discharge.
Figure 4
Figure 4
The prediction accuracy of MLR was 31.3% (5 correct answers). On the other hand, the correct answer rate of prediction using ANNs was 75.0% (12 correct answers). The correct answer rate of ANNs for each final AIS was 66% for AIS A, 50% for B, 60% for C, and 100% for D. The size of the circle represents the number of applicable cases. Green indicates that the prediction is correct, yellow indicates an error of one level, and red indicates an error of two or more levels.
See this image and copyright information in PMC

References

    1. Burns A.S., Ditunno J.F. Establishing Prognosis and Maximizing Functional Outcomes after Spinal Cord Injury: A Review of Current and Future Directions in Rehabilitation Management. Spine. 2001;26:S137–S145. doi: 10.1097/00007632-200112151-00023. - DOI - PubMed
    1. van Middendorp J.J., Hosman A.J., Donders A.R.T., Pouw M.H., Ditunno J.F., Curt A., Geurts A.C., Van de Meent H. A clinical prediction rule for ambulation outcomes after traumatic spinal cord injury: A longitudinal cohort study. Lancet. 2011;377:1004–1010. doi: 10.1016/S0140-6736(10)62276-3. - DOI - PubMed
    1. Miyakoshi N., Suda K., Kudo D., Sakai H., Nakagawa Y., Mikami Y., Suzuki S., Tokioka T., Tokuhiro A., Takei H., et al. A nationwide survey on the incidence and characteristics of traumatic spinal cord injury in Japan in 2018. Spinal Cord. 2020;59:626–634. doi: 10.1038/s41393-020-00533-0. - DOI - PubMed
    1. Sasaki M., Honmou O., Akiyama Y., Uede T., Hashi K., Kocsis J.D. Transplantation of an acutely isolated bone marrow fraction repairs demyelinated adult rat spinal cord axons. Glia. 2001;35:26–34. doi: 10.1002/glia.1067. - DOI - PMC - PubMed
    1. Honmou O., Yamashita T., Morita T., Oshigiri T., Hirota R., Iyama S., Kato J., Sasaki Y., Ishiai S., Ito Y.M., et al. Intravenous infusion of auto serum-expanded autologous mesenchymal stem cells in spinal cord injury patients: 13 case series. Clin. Neurol. Neurosurg. 2021;203:106565. doi: 10.1016/j.clineuro.2021.106565. - DOI - PubMed

LinkOut - more resources