Using a machine learning approach to predict outcome after surgery for degenerative cervical myelopathy

• Published in: PloS one 2019-04, Vol.14 (4), p.e0215133-e0215133
• Main Authors: Merali, Zamir G, Witiw, Christopher D, Badhiwala, Jetan H, Wilson, Jefferson R, Fehlings, Michael G
• Format: Article
• Language: English
• Subjects: Analysis; Artificial intelligence; Biology and Life Sciences; Body weight; Bone surgery; Care and treatment; Central nervous system diseases; Classification; Comorbidity; Compression; Computer and Information Sciences; Data processing; Decompression, Surgical - adverse effects; Demographic variables; Demographics; Demography; Engineering and Technology; Female; Humans; Information management; Intervertebral Disc Degeneration - surgery; Learning algorithms; Machine Learning; Male; Mathematical models; Medical personnel; Medical prognosis; Medical research; Medicine and Health Sciences; Middle Aged; Neurosurgery; Optimization; Patients; Performance prediction; Physical Sciences; Physicians; Postoperative Complications - diagnosis; Postoperative Complications - etiology; Prediction models; Predictive Value of Tests; Prospective Studies; Quality of life; Research and Analysis Methods; Risk factors; Sensitivity analysis; Signs and symptoms; Smoking; Spinal cord; Spinal cord diseases; Spinal Cord Diseases - surgery; Spine; Surgery; Surgical outcomes; Training; Treatment Outcome
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0215133

Degenerative cervical myelopathy (DCM) is a spinal cord condition that results in progressive non-traumatic compression of the cervical spinal cord. Spine surgeons must consider a large quantity of information relating to disease presentation, imaging features, and patient characteristics to determine if a patient will benefit from surgery for DCM. We applied a supervised machine learning approach to develop a classification model to predict individual patient outcome after surgery for DCM. Patients undergoing surgery for DCM as a part of the AOSpine CSM-NA or CSM-I prospective, multi-centre studies were included in the analysis. Out of 757 patients 605, 583, and 539 patients had complete follow-up information at 6, 12, and 24 months respectively and were included in the analysis. The primary outcome was improvement in the SF-6D quality of life indicator score by the minimum clinically important difference (MCID). The secondary outcome was improvement in the modified Japanese Orthopedic Association (mJOA) score by the MCID. Predictor variables reflected information about pre-operative disease severity, disease presentation, patient demographics, and comorbidities. A machine learning approach of feature engineering, data pre-processing, and model optimization was used to create the most accurate predictive model of outcome after surgery for DCM. Following data pre-processing 48, 108, and 101 features were chosen for model training at 6, 12, and 24 months respectively. The best performing predictive model used a random forest structure and had an average area under the curve (AUC) of 0.70, classification accuracy of 77%, and sensitivity of 78% when evaluated on a testing cohort that was not used for model training. Worse pre-operative disease severity, longer duration of DCM symptoms, older age, higher body weight, and current smoking status were associated with worse surgical outcomes. We developed a model that predicted positive surgical outcome for DCM with good accuracy at the individual patient level on an independent testing cohort. Our analysis demonstrates the applicability of machine-learning to predictive modeling in spine surgery.