International external validation of the SORG machine learning algorithms for predicting 90-day and one-year survival of patients with spine metastases using a Taiwanese cohort

Jiun Jen Yang, Chih Wei Chen, Mitchell S. Fourman, Michiel E.R. Bongers, Aditya V. Karhade, Olivier Q. Groot, Wei Hsin Lin, Hung Kuan Yen, Po Hao Huang, Shu Hua Yang, Joseph H. Schwab, Ming Hsiao Hu

Research output: Contribution to journalArticlepeer-review

23 Scopus citations


Background Context: Accurately predicting the survival of patients with spinal metastases is important for guiding surgical intervention. The SORG machine-learning (ML) algorithm for the 90-day and one-year mortality of patients with metastatic cancer to the spine has been multiply validated, with a high degree of accuracy in both internal and external validation studies. However, prior external validations were conducted using patient groups located on the east coast of the United States, representing a generally homogeneous population. The aim of this study was to externally validate the SORG algorithms with a Taiwanese population. Study Design/Setting: Retrospective study at a single tertiary care center in Taiwan Patient Sample: Four hundred and twenty-seven patients who underwent surgery for metastatic spine disease from November 1, 2010 to December 31, 2018 Outcome Measures: 90-day and one-year mortality Methods: The baseline characteristics of our validation cohort were compared with those of the previously published developmental and external validation cohorts. Discrimination (c-statistic and receiver operating curve), calibration (calibration plot, intercept, and slope), overall performance (Brier score), and decision curve analysis were used to assess the performance of the SORG ML algorithms in this cohort. Results: Ninety-day and one-year mortality rates were 110 of 427 (26%) and 256 of 427 (60%), respectively. The external validation cohort and the developmental cohort differed in body mass index (BMI), preoperative performance status, American Spinal Injury Association impairment scale, primary tumor histology and in several laboratory measurements. The SORG ML algorithm for 90-day and 1-year mortality demonstrated a high level of discriminative ability (c-statistics of 0.73 [95% confidence interval [CI], 0.67–0.78] and 0.74 [95% CI, 0.69−0.79]), overall performance, and had a positive net benefit throughout the range of threshold probabilities in decision curve analysis. The algorithm for 1-year mortality had a calibration intercept of 0.08, representing a good calibration. However, the 90-day mortality algorithm underestimated mortality for the lowest predicted probabilities, with an overall intercept of 0.81. Conclusions: The SORG algorithms for predicting 90-day and 1-year mortality in patients with spinal metastatic disease generally performed well on international external validation in a predominately Taiwanese population. However, 90-day mortality was underestimated in this group. Whether this inconsistency was due to different primary tumor characteristics, body mass index, selection bias or other factors remains unclear, and may be better understood with further validative works that utilize international and/or diverse populations.

Original languageEnglish (US)
Pages (from-to)1670-1678
Number of pages9
JournalSpine Journal
Issue number10
StatePublished - Oct 2021
Externally publishedYes


  • Body mass index
  • Neoplasm staging
  • Spine metastases
  • Surgical oncology
  • Survival
  • Taiwanese

ASJC Scopus subject areas

  • Surgery
  • Orthopedics and Sports Medicine
  • Clinical Neurology


Dive into the research topics of 'International external validation of the SORG machine learning algorithms for predicting 90-day and one-year survival of patients with spine metastases using a Taiwanese cohort'. Together they form a unique fingerprint.

Cite this