A prognostic scoring system for predicting 1-year survival in patients with advanced cancer and spinal metastases was enhanced with machine learning for greater accuracy, according to the results of a Japanese multicenter study published in Spine.
"This model provides a practical risk assessment tool to aid surgical decision-making and optimize postoperative management," the study authors concluded in their report.
Background and Study Methods
Existing scoring systems for determining the prognostic impact of spinal metastases in patients with advanced cancers have relied upon outdated data and older treatment approaches.
"Traditional survival prediction models in clinical practice use data from the 1990s and 2000s," said lead study author Sadayuki Ito, MD, Assistant Professor, Department of Orthopaedic Surgery, Nagoya University Graduate School of Medicine. "Those models don't fully reflect the impact of modern oncologic therapies, such as molecularly targeted therapies and immune checkpoint inhibitors."
Researchers from the Japan Association of Spine Surgeons With Ambition established a prognostic scoring system with large-scale prospective data and machine learning techniques. The multicenter, prospective study included 401 patients from 35 medical centers who received surgery for their spinal metastases between 2018 and 2021. Least absolute shrinkage and selection operator (LASSO) logistic regression and stepwise variable selection was applied to determine the most significant predictors of 1-year survival.
Key Findings
The 1-year survival rate in the study was 67.1%. Patients who survived a year tended to have better performance status, lower tumor burden, and lower opioid use than those that did not survive. Five key predictors of 1-year survival were found to be age, ECOG performance status, bone metastases, opioid use, and Vitality index score prior to surgery.
The prognostic scoring system showed an area under the received operating characteristic curve (AUROC) of 0.762.
Based on the prognostic factors identified, a risk stratification system was developed to classify patients into low-, intermediate-, and high-risk groups. The 1-year survival rate was 82.2% for patients in the low-risk group, 67.2% for the intermediate-risk group, and 34.2% for the high-risk group.
"Our next step is to validate this system with data from medical institutions worldwide to ensure it can help patients globally," Dr. Ito concluded.
DISCLOSURE: For full disclosures of the study authors, visit journals.lww.com.
