Machine learning-driven national analysis for predicting adverse outcomes in intramedullary spinal cord tumor surgery.

Spinal tumors represent 15% of all central nervous system malignancies, with intramedullary spinal cord tumors (IMSCTs) being rare. Predominantly ependymomas and astrocytomas, IMSCTs often present late, leading to significant morbidity and mortality. Surgical excision is key but challenging due to the tumors' complex, invasive nature. Treatment involves a multidisciplinary approach, considering tumor type and patient condition, ranging from subtotal to gross total resection, possibly with adjuvant therapy. This study uses machine learning on National Cancer Database data to predict postoperative outcomes, aiming to develop a risk calculator for clinicians to assess mortality and extended hospital stay risks post-surgery.

Objective: This study investigates healthcare outcomes in patients undergoing surgical resection for intradural intramedullary spinal cord tumors (IMSCTs), employing the National Cancer Data Base (NCDB) to identify key variables. We aimed to develop supervised machine learning-based risk calculators to predict high-risk patients for mortality and extended length of stay (eLOS), stratifying IMSCTs by histology to enhance understanding and guide intervention strategies for adverse outcomes.

Methods: Patients with surgically-treated IMSCTs (2004-2017) was conducted using the NCDB. We extracted demographic and comorbidity data, employing descriptive statistics and supervised machine learning algorithms to predict mortality and eLOS.

Results: The study encompassed 7,243 surgically treated IMSCT cases, including 612 astrocytomas (8.5%), 6,041 ependymomas (83.4%), and 590 hemangioblastomas (8.1%). Mortality and eLOS rates were observed at 10.2% and 27.1%, respectively. Over 12 years (2004-2016), significant management shifts were noted for these spinal tumor types. The predictive models achieved AUCs of 0.721 for mortality and 0.586 for eLOS. Key predictive features for mortality included age, diagnosis year, behavior, histology, radiation, insurance status, patient-hospital distance, tumor grade and size, length of stay, subtotal resection (STR) to gross total resection (GTR), and sex. For eLOS, additional predictors were diagnosis-surgery interval, Charlson/Deyo score, and surgical approach. Web-based tools for both outcomes have been deployed: https://imsct-elos-predict.herokuapp.com/ ; https://imsct-risk-calcualor.herokuapp.com/ .

Conclusion: Our nationwide analysis underscores the evolution in IMSCT management and demonstrates the efficacy of machine learning in predicting mortality and eLOS, providing valuable insights for improved patient care.