Top

Published in:

06-02-2023 | Original Article

Deep learning-based prediction model for postoperative complications of cervical posterior longitudinal ligament ossification

Authors: Sadayuki Ito, Hiroaki Nakashima, Toshitaka Yoshii, Satoru Egawa, Kenichiro Sakai, Kazuo Kusano, Shinji Tsutui, Takashi Hirai, Yu Matsukura, Kanichiro Wada, Keiichi Katsumi, Masao Koda, Atsushi Kimura, Takeo Furuya, Satoshi Maki, Narihito Nagoshi, Norihiro Nishida, Yukitaka Nagamoto, Yasushi Oshima, Kei Ando, Masahiko Takahata, Kanji Mori, Hideaki Nakajima, Kazuma Murata, Masayuki Miyagi, Takashi Kaito, Kei Yamada, Tomohiro Banno, Satoshi Kato, Tetsuro Ohba, Satoshi Inami, Shunsuke Fujibayashi, Hiroyuki Katoh, Haruo Kanno, Masahiro Oda, Kensaku Mori, Hiroshi Taneichi, Yoshiharu Kawaguchi, Katsushi Takeshita, Morio Matsumoto, Masashi Yamazaki, Atsushi Okawa, Shiro Imagama

Published in: European Spine Journal | Issue 11/2023

Abstract

Purpose

Postoperative complication prediction helps surgeons to inform and manage patient expectations. Deep learning, a model that finds patterns in large samples of data, outperform traditional statistical methods in making predictions. This study aimed to create a deep learning-based model (DLM) to predict postoperative complications in patients with cervical ossification of the posterior longitudinal ligament (OPLL).

Methods

This prospective multicenter study was conducted by the 28 institutions, and 478 patients were included in the analysis. Deep learning was used to create two predictive models of the overall postoperative complications and neurological complications, one of the major complications. These models were constructed by learning the patient's preoperative background, clinical symptoms, surgical procedures, and imaging findings. These logistic regression models were also created, and these accuracies were compared with those of the DLM.

Results

Overall complications were observed in 127 cases (26.6%). The accuracy of the DLM was 74.6 ± 3.7% for predicting the overall occurrence of complications, which was comparable to that of the logistic regression (74.1%). Neurological complications were observed in 48 cases (10.0%), and the accuracy of the DLM was 91.7 ± 3.5%, which was higher than that of the logistic regression (90.1%).

Conclusion

A new algorithm using deep learning was able to predict complications after cervical OPLL surgery. This model was well calibrated, with prediction accuracy comparable to that of regression models. The accuracy remained high even for predicting only neurological complications, for which the case number is limited compared to conventional statistical methods.

Inamasu J, Guiot BH, Sachs DC (2006) Ossification of the posterior longitudinal ligament: an update on its biology, epidemiology, and natural history. Neurosurgery 58:1027–1039. https://doi.org/10.1227/01.Neu.0000215867.87770.73CrossRefPubMed

Mori K, Imai S, Kasahara T, Nishizawa K, Mimura T, Matsusue Y (2014) Prevalence, distribution, and morphology of thoracic ossification of the posterior longitudinal ligament in Japanese: results of CT-based cross-sectional study. Spine 39:394–399. https://doi.org/10.1097/brs.0000000000000153CrossRefPubMed

Nam DC, Lee HJ, Lee CJ, Hwang SC (2019) Molecular pathophysiology of ossification of the posterior longitudinal ligament (OPLL). Biomol Ther 27:342–348. https://doi.org/10.4062/biomolther.2019.043CrossRef

Fujimori T, Watabe T, Iwamoto Y, Hamada S, Iwasaki M, Oda T (2016) Prevalence, concomitance, and distribution of ossification of the spinal ligaments: results of whole spine CT scans in 1500 Japanese patients. Spine 41(21):1668–1676CrossRefPubMed

Li H, Dai L-Y (2011) A systematic review of complications in cervical spine surgery for ossification of the posterior longitudinal ligament. Spine J 11:1049–1057. https://doi.org/10.1016/j.spinee.2011.09.008CrossRefPubMed

Nakashima H, Tetreault L, Nagoshi N, Nouri A, Arnold P, Yukawa Y, Toyone T, Tanaka M, Zhou Q, Fehlings MG (2016) Comparison of outcomes of surgical treatment for ossification of the posterior longitudinal ligament versus other forms of degenerative cervical myelopathy: results from the prospective, multicenter AOSpine CSM-international study of 479 patients. JBJS 98(5):370–378CrossRef

Ramos MRD, Liu G, Tan J-H, Tan JHJ, Ruiz JNM, Hey HWD, Lau L-L, Kumar N, Thambiah J, Wong H-K (2021) Risk factors for surgical complications in the management of ossification of the posterior longitudinal ligament. Spine J 21:1176–1184. https://doi.org/10.1016/j.spinee.2021.03.022CrossRefPubMed

O’Neill KR, Neuman BJ, Peters C, Riew KD (2014) Risk factors for dural tears in the cervical spine. Spine 39(17):E1015–E1020CrossRef

Shou F, Li Z, Wang H, Yan C, Liu Q, Xiao C (2015) Prevalence of C5 nerve root palsy after cervical decompressive surgery: a meta-analysis. Eur Spine J 24:2724–2734. https://doi.org/10.1007/s00586-015-4186-5CrossRefPubMed

10.

Kato S, Chikuda H, Seichi A, Ohtsu H, Kimura A, Toyama Y (2012) Radiographical risk factors for major intraoperative blood loss during laminoplasty in patients with ossification of the posterior longitudinal ligament. Spine 37(25):E1588–E1593CrossRefPubMed

11.

Shah AA, Devana SK, Lee C, Kianian R, van der Schaar M, SooHoo NF (2021) Development of a novel, potentially universal machine learning algorithm for prediction of complications after total hip arthroplasty. J Arthroplasty 36:1655-1662.e1651. https://doi.org/10.1016/j.arth.2020.12.040CrossRefPubMed

12.

Alaa A, Schaar M (2018) AutoPrognosis: automated clinical prognostic modeling via bayesian optimization with structured kernel learning. In: Jennifer D, Andreas K (eds) Proceedings of the 35th International Conference on Machine Learning. PMLR, Proceedings of Machine Learning Research. pp. 139--148.

13.

Shah AA, Devana SK, Lee C, Bugarin A, Lord EL, Shamie AN, Park DY, van der Schaar M, SooHoo NF (2021) Machine learning-driven identification of novel patient factors for prediction of major complications after posterior cervical spinal fusion. Eur Spine J. https://doi.org/10.1007/s00586-021-06961-7CrossRefPubMed

14.

LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539CrossRefPubMed

15.

Iwasaki M, Okuda S, Miyauchi A, Sakaura H, Mukai Y, Yonenobu K, Yoshikawa H (2007) Surgical strategy for cervical myelopathy due to ossification of the posterior longitudinal ligament: part 1: clinical results and limitations of laminoplasty. Spine 32:647–653. https://doi.org/10.1097/01.brs.0000257560.91147.86CrossRefPubMed

16.

Iwasaki M, Okuda S, Miyauchi A, Sakaura H, Mukai Y, Yonenobu K, Yoshikawa H (2007) Surgical strategy for cervical myelopathy due to ossification of the posterior longitudinal ligament: part 2: advantages of anterior decompression and fusion over laminoplasty. Spine 32:654–660. https://doi.org/10.1097/01.brs.0000257566.91177.cbCrossRefPubMed

17.

Tsuyama N (1984) Ossification of the posterior longitudinal ligament of the spine. Clin Orthop Relat Res 71–84

18.

Fujiyoshi T, Yamazaki M, Kawabe J, Endo T, Furuya T, Koda M, Okawa A, Takahashi K, Konishi H (2008) A new concept for making decisions regarding the surgical approach for cervical ossification of the posterior longitudinal ligament: the K-line. Spine 33:E990-993. https://doi.org/10.1097/BRS.0b013e318188b300CrossRefPubMed

19.

Veeravagu A, Connolly ID, Lamsam L, Li A, Swinney C, Azad TD, Desai A, Ratliff JK (2016) Surgical outcomes of cervical spondylotic myelopathy: an analysis of a national, administrative, longitudinal database. Neurosurg Focus FOC 40:E11. https://doi.org/10.3171/2016.3.FOCUS1669CrossRef

20.

DePasse JM, Durand W, Eltorai AEM, Palumbo MA, Daniels AH (2018) Timing of complications following posterior cervical fusion. J Orthop 15:522–526. https://doi.org/10.1016/j.jor.2018.03.010CrossRefPubMedPubMedCentral

21.

Cruz JA, Wishart DS (2007) Applications of machine learning in cancer prediction and prognosis. Cancer Inf 2:59–77

22.

Luo W, Phung D, Tran T, Gupta S, Rana S, Karmakar C, Shilton A, Yearwood J, Dimitrova N, Ho TB, Venkatesh S, Berk M (2016) Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J Med Internet Res 18:e323. https://doi.org/10.2196/jmir.5870CrossRefPubMedPubMedCentral

23.

Bakhsh W, Saleh A, Yokogawa N, Gruber J, Rubery PT, Mesfin A (2019) Cervical ossification of the posterior longitudinal ligament: a computed tomography-based epidemiological study of 2917 patients. Glob Spine J 9:820–825. https://doi.org/10.1177/2192568219833658CrossRef

24.

Kimura A, Takeshita K, Yoshii T, Egawa S, Hirai T, Sakai K, Kusano K, Nakagawa Y, Wada K, Katsumi K, Fujii K, Furuya T, Nagoshi N, Kanchiku T, Nagamoto Y, Oshima Y, Nakashima H, Ando K, Takahata M, Mori K, Nakajima H, Murata K, Matsunaga S, Kaito T, Yamada K, Kobayashi S, Kato S, Ohba T, Inami S, Fujibayashi S, Katoh H, Kanno H, Watanabe K, Imagama S, Koda M, Kawaguchi Y, Nakamura M, Matsumoto M, Yamazaki M, Okawa A (2021) Impact of diabetes mellitus on cervical spine surgery for ossification of the posterior longitudinal ligament. J Clin Med 10(21):5026. https://doi.org/10.3390/jcm10153375CrossRefPubMedPubMedCentral

25.

Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G (2018) Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med 178:1544–1547. https://doi.org/10.1001/jamainternmed.2018.3763CrossRefPubMedPubMedCentral

Title: Deep learning-based prediction model for postoperative complications of cervical posterior longitudinal ligament ossification
Authors: Sadayuki Ito
Hiroaki Nakashima
Toshitaka Yoshii
Satoru Egawa
Kenichiro Sakai
Kazuo Kusano
Shinji Tsutui
Takashi Hirai
Yu Matsukura
Kanichiro Wada
Keiichi Katsumi
Masao Koda
Atsushi Kimura
Takeo Furuya
Satoshi Maki
Narihito Nagoshi
Norihiro Nishida
Yukitaka Nagamoto
Yasushi Oshima
Kei Ando
Masahiko Takahata
Kanji Mori
Hideaki Nakajima
Kazuma Murata
Masayuki Miyagi
Takashi Kaito
Kei Yamada
Tomohiro Banno
Satoshi Kato
Tetsuro Ohba
Satoshi Inami
Shunsuke Fujibayashi
Hiroyuki Katoh
Haruo Kanno
Masahiro Oda
Kensaku Mori
Hiroshi Taneichi
Yoshiharu Kawaguchi
Katsushi Takeshita
Morio Matsumoto
Masashi Yamazaki
Atsushi Okawa
Shiro Imagama
Publication date: 06-02-2023
Publisher: Springer Berlin Heidelberg
Published in: European Spine Journal / Issue 11/2023
Print ISSN: 0940-6719
Electronic ISSN: 1432-0932
DOI: https://doi.org/10.1007/s00586-023-07562-2

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Deep learning-based prediction model for postoperative complications of cervical posterior longitudinal ligament ossification

Abstract

Purpose

Methods

Results

Conclusion

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 11/2023

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT

Letter to the Editor concerning "Alterations of 3D acetabular and lower limb parameters in adolescent idiopathic scoliosis" by Karam M, et al. (Eur Spine J [2020]; 29(8):2010–2017): Does windswept deformity of the knee exist in 274 participants with adolescent idiopathic scoliosis?

The correlation between osteoporotic vertebrae fracture risk and bone mineral density measured by quantitative computed tomography and dual energy X-ray absorptiometry: a systematic review and meta-analysis

Characteristics of paraspinal muscle degeneration in patients with adult degenerative scoliosis

Deep phenotyping the cervical spine: automatic characterization of cervical degenerative phenotypes based on T2-weighted MRI

The contribution of preoperative balanced halo-pelvic traction to severe rigid spinal deformity correction