Development of a Machine-Learning Model of Short-Term Prognostic Prediction for Spinal Stenosis Surgery in Korean Patients

Abstract

Background: In this study, based on machine-learning technology, we aim to develop a predictive model of the short-term prognosis of Korean patients who received spinal stenosis surgery. Methods: Using the data obtained from 112 patients with spinal stenosis admitted at N hospital from February to November, 2019, a predictive analysis was conducted for the pain index, reoperation, and surgery time. Results: Results show that the predicted area under the curve was 0.803, 0.887, and 0.896 for the pain index, reoperation, and surgery time, respectively, thereby indicating the accuracy of the model. Conclusion: This study verified that the individual characteristics of the patient and treatment characteristics during surgery enable a prediction of the patient prognosis and validate the accuracy of the approach. Further studies should be conducted to extend the scope of this research by incorporating a larger and more accurate dataset.

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

“…In a study conducted in Korea, a prognostic prediction was produced for 111 individuals who had spinal stenosis ( Table 1 ). 9 An ML model also had a 92.56% positive predictive value for post-operative surgical site infections following posterior spinal infusions ( Table 1 ). 10 Another ML model that was trained to predict the frequency of blood transfusions post-adult spinal deformity surgery produced encouraging results ( Table 1 ).…”

LSS-Vgg16

“…The authors state that this study provides an estimation of patient prognosis, with individual patient characteristics and intraoperative treatment characteristics. 9…”

“…They calculated that the estimated area under the curve for the pain index, reoperation, and operative time was 0.803, 0.887, and 0.896, respectively. The authors state that this study provides an estimation of patient prognosis, with individual patient characteristics and intraoperative treatment characteristics 9…”