Determining the short-term neurological prognosis for acute cervical spinal cord injury using machine learning

• Published in: Journal of clinical neuroscience 2022-02, Vol.96, p.74-79
• Main Authors: Okimatsu, Sho, Maki, Satoshi, Furuya, Takeo, Fujiyoshi, Takayuki, Kitamura, Mitsuhiro, Inada, Taigo, Aramomi, Masaaki, Yamauchi, Tomonori, Miyamoto, Takuya, Inoue, Takaki, Yunde, Atsushi, Miura, Masataka, Shiga, Yasuhiro, Inage, Kazuhide, Orita, Sumihisa, Eguchi, Yawara, Ohtori, Seiji
• Format: Article
• Language: English
• Subjects: ASIA impairment scale; Cervical; Cervical Cord - diagnostic imaging; Humans; Machine Learning; Prognosis; Recovery of Function; Retrospective Studies; Spinal Cord Injuries - diagnostic imaging; Spinal cord injury; Trauma
• ISSN: 0967-5868; 1532-2653
• DOI: 10.1016/j.jocn.2021.11.037

•We aimed to determine the prognosis of patients with SCI using machine learning.•The accuracy of our model to predict AIS 1 month after injury was 0.714.•It was feasible to use machine learning to predict the neurological outcomes of SCI. It is challenging to predict neurological outcomes of acute spinal cord injury (SCI) considering issues such as spinal shock and injury heterogeneity. Deep learning-based radiomics (DLR) were developed to quantify the radiographic characteristics automatically using a convolutional neural network (CNN), and to potentially allow the prognostic stratification of patients. We aimed to determine the functional prognosis of patients with cervical SCI using machine learning approach based on MRI and to assess the ability to predict the neurological outcomes. We retrospectively analyzed the medical records of SCI patients (n=215) who had undergone MRI and had an American Spinal cord Injury Association Impairment Scale (AIS) assessment at 1 month after injury, enrolled with a total of 294 MR images. Sagittal T2-weighted MR images were used for the CNN training and validation. The deep learning framework TensorFlow was used to construct the CNN architecture. After we calculated the probability of the AIS grade using the DLR, we built the identification model based upon the random forest using 3 features: the probability of each AIS grade obtained by the DLR method, age, and the initial AIS grade at admission. We performed a statistical evaluation between the actual and predicted AIS. The accuracy, precision, recall and f1 score of the ensemble model based on the DLR and RF were 0.714, 0.590, 0.565 and 0.567, respectively. The present study demonstrates that prediction of the short-term neurological outcomes for acute cervical spinal cord injury based on MRI using machine learning is feasible.