EUVIMEDEUVIMED entdecken
Crossref

A multimodal machine learning model integrating clinical and MRI data for predicting neurological outcomes following surgical treatment for cervical spinal cord injury

Tomoaki Shimizu, Kento Inomata, Kota Suda, Satoko Matsumoto Harmon, Miki Komatsu, Masahiro Ota, Hiroki Ushirozako, Akio Minami, Satoshi Maki, Tsutomu Endo, Katsuhisa Yamada, Norimasa Iwasaki und 3 weitere

European Spine Journal · 2025

DOI: 10.1007/s00586-025-08873-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Spine Journal, 2025. Verfasst von Tomoaki Shimizu und 14 weiteren Autor:innen. Beteiligte Einrichtung: Hokkaido Spinal Cord Injury Center, Hokkaido, Japan. tomoaki.shimizu.96@gmail.com. Hauptthemen laut MEDLINE: Spinal Cord Injuries, Machine Learning, Magnetic Resonance Imaging, Cervical Vertebrae. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: CSP VA, Grant of Japan Orthopaedics and Traumatology Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: Predicting the prognosis of cervical spinal cord injury (CSCI) is crucial for patients and healthcare providers, as it informs treatment decisions and rehabilitation planning. This study aimed to develop a multimodal machine learning model integrating clinical and MRI data to predict neurological outcomes in CSCI patients. METHODS: We conducted a retrospective study of 247 patients with traumatic CSCI who underwent posterior decompression and fusion surgery at a specialized spinal cord injury center between April 2015 and June 2021. Clinical data, including demographics, comorbidities, laboratory data, and neurological findings, were collected. T2-weighted sagittal MRI images were analyzed using a convolutional neural network pre-trained on RadImageNet. Clinical and MRI features were integrated to construct a multimodal predictive model using the Light Gradient Boosting Machine algorithm, validated with 5-fold cross-validation. The primary outcome was defined as achieving American Spinal Injury Association (ASIA) Impairment Scale (AIS) grade D or higher at 6 months post-injury. Shapley Additive Explanations identified key contributing factors in predicting these neurological outcomes. RESULTS: The model achieved an accuracy of 0.90 and an AUC of 0.94 for predicting recovery to AIS grade D or higher at 6 months post-injury. Key predictors included lower extremity ASIA motor score (AMS), AIS grade at admission, upper extremity AMS, age, HbA1c, and MRI-derived features. CONCLUSION: This multimodal model demonstrated superior predictive accuracy compared to previous monomodal approaches, emphasizing the value of combining clinical and MRI data. These findings highlight the potential of multimodal predictive models in improving clinical decision-making and outcomes for CSCI patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spinal Cord InjuriesMachine LearningMagnetic Resonance ImagingCervical VertebraeCervical CordHumansMaleFemaleMiddle AgedRetrospective StudiesAdultDecompression, SurgicalPrognosisSpinal FusionTreatment OutcomeAged

Stichwörter der Autor:innen

Cervical spinal cord injuryDeep learningMachine learningMultimodal prediction modelNeurological outcomes

Autor:innen und Institutionen

  • Hokkaido Spinal Cord Injury Center, Hokkaido, Japan. tomoaki.shimizu.96@gmail.com.
  • University of Tsukuba, Tsukuba, Japan. tomoaki.shimizu.96@gmail.com.
  • Hokkaido Spinal Cord Injury Center, Hokkaido, Japan.
  • University of Tsukuba, Tsukuba, Japan.
  • Chiba University, Chiba, Japan.
  • Hokkaido University, Sapporo, Japan.

Förderung

  • CSP VA
  • Grant of Japan Orthopaedics and Traumatology Research Foundation

Zitieren

APA

Shimizu, T., Inomata, K., Suda, K., Matsumoto Harmon, S., Komatsu, M., Ota, M., Ushirozako, H., Minami, A., Maki, S., Endo, T., Yamada, K., Iwasaki, N., Takahashi, H., Yamazaki, M., & Koda, M. (2025). A multimodal machine learning model integrating clinical and MRI data for predicting neurological outcomes following surgical treatment for cervical spinal cord injury. European Spine Journal. https://doi.org/10.1007/s00586-025-08873-2

Vancouver

Shimizu T, Inomata K, Suda K, Matsumoto Harmon S, Komatsu M, Ota M, et al. A multimodal machine learning model integrating clinical and MRI data for predicting neurological outcomes following surgical treatment for cervical spinal cord injury. European Spine Journal. 2025. doi:10.1007/s00586-025-08873-2

BibTeX
@article{Shimizu2025,
  author = {Shimizu, Tomoaki and Inomata, Kento and Suda, Kota and Matsumoto Harmon, Satoko and Komatsu, Miki and Ota, Masahiro and Ushirozako, Hiroki and Minami, Akio and Maki, Satoshi and Endo, Tsutomu and Yamada, Katsuhisa and Iwasaki, Norimasa and Takahashi, Hiroshi and Yamazaki, Masashi and Koda, Masao},
  title = {A multimodal machine learning model integrating clinical and MRI data for predicting neurological outcomes following surgical treatment for cervical spinal cord injury},
  journal = {European Spine Journal},
  year = {2025},
  doi = {10.1007/s00586-025-08873-2}
}
Kostenlos starten →