Development and external validation of predictive algorithms for six-week mortality in spinal metastasis using 4,304 patients from five institutions

Karhade, Aditya V.; Fenn, Brian P.; Groot, Olivier Q.; Shah, Akash; Yen, Hung-Kuan; Bilsky, Mark H.; Hu, Ming-Hsiao; Laufer, Ilya; Park, Don Y.; Sciubba, Daniel M.; Tobert, Daniel G.; Bono, Christopher M.; Harris, Mitchel B.; Schwab, Joseph H.

doi:10.1016/j.spinee.2022.07.089

Cited by 11 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictors used for SORG-MLA's prediction were manually collected from electronic chart review, 7 including primary cancer categorized as rapid growth, moderate growth, or slow growth tumors by Katigiri et al, 12 Eastern Cooperative Oncology Group (ECOG) performance scale, 13 presence of any Charlson comorbidities other than metastatic cancer, 14 American Spinal Injury Association (ASIA) impairment scale, 15 the presence of visceral (lung or liver), brain, or more than three spine-level metastases, whether using systemic therapy before the index treatment, body mass index (BMI), and the following nine preoperative laboratory values: hemoglobin (g/dL), platelet (×10 3 /μL), white blood cell (×10 3 /μL), absolute lymphocyte (×10 3 /μL), absolute neutrophil (×10 3 /μL), international normalized ratio, albumin (g/dL), alkaline phosphatase (IU/L), and creatinine (mg/dL). The same definitions were used for both the validation and development cohort.…”

Section: Methodsmentioning

confidence: 99%

“…4,5 However, with the progress of (minimal invasive) surgical techniques and improvements in radiation therapy, immunotherapy, radiologic technique, and postoperative care, the 3-month cutoff has been challenged, and a shorter survival landmark of 6 weeks should also be considered. 4,6 Therefore, Karhade et al 7 updated the Skeletal Oncology Research Group machine learning algorithm (SORG-MLA), a successfully tested survival prediction model based on machine learning, to provide 6-week survival estimation in a recent study. The model uses variables such as primary tumor histology, Eastern Cooperative Oncology Group score, spinal metastasis count, and laboratory values to predict the probability of survival after intervention.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Algorithm for Predicting 6-Week Survival in Spinal Metastasis: An External Validation Study Using 2,768 Taiwanese Patients

Lin

Yen

et al. 2023

J Am Acad Orthop Surg

Self Cite

View full text Add to dashboard Cite

Introduction: There are predictive algorithms for predicting 3-month and 1-year survival in patients with spinal metastasis. However, advance in surgical technique, immunotherapy, and advanced radiation therapy has enabled shortening of postoperative recovery, which returns dividends to the overall quality-adjusted life-year. As such, the Skeletal Oncology Research Group machine learning algorithm (SORG-MLA) was proposed to predict 6-week survival in patients with spinal metastasis, whereas its utility for patients treated with nonsurgical treatment was untested externally. This study aims to validate the survival prediction of the 6-week SORG-MLA for patients with spinal metastasis and provide the measurement of model consistency (MC). Methods: Discrimination using area under the receiver operating characteristic curve, calibration, Brier score, and decision curve analysis were conducted to assess the model's performance in the Taiwanese-based cohort. MC was also applied to detect the proportion of paradoxical predictions among 6-week, 3-month, and 1-year survival predictions. The long-term prognosis should not be better than the shorter-term prognosis in that of an individual. Results: The 6-week survival rate was 84.2%. The SORG-MLA retained good discrimination with an area under the receiver operating characteristic curve of 0.78 (95% confidence interval, 0.75 to 0.80) and good prediction accuracy with a Brier score of 0.11 (null model Brier score 0.13). There is an underestimation of the 6-week survival rate when the predicted survival rate is less than 50%. Decision curve analysis showed that the model was suitable for use over all threshold probabilities. MC showed suboptimal consistency between 6-week and 90-day survival prediction (78%). Conclusions: The results of this study supported the utility of the algorithm. The online tool (https://sorg-apps.shinyapps.io/spinemetssurvival/) can be used by both clinicians and patients in informative decision-making discussion before management of spinal metastasis.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

A Machine Learning Algorithm for Predicting 6-Week Survival in Spinal Metastasis: An External Validation Study Using 2,768 Taiwanese Patients

Lin

Yen

et al. 2023

J Am Acad Orthop Surg

Self Cite

View full text Add to dashboard Cite

show abstract

“…Studies with a large sample size from a multi-institutional or multinational cohort should be conducted for developing an accurate and reliable prognostic model. Therefore, recently introduced predictive algorithms have been developed and validated using multi-institutional databases [19,25,36]. Additionally, a large database from multicenter and multinational tumor registries should be a prerequisite in developing future prognostic models for spinal metastasis.…”

Section: Current Trends and Future Directionsmentioning

confidence: 99%

“…However, the SORG used multiple machinelearning algorithms, like gradient boosting, decision trees, random forests, and neural networks, for developing their prognostic models [25,39]. More recently, Karhade et al [36] developed and introduced predictive algorithms for 6-week mortality in patients with spinal metastasis using five different machine-learning algorithms. These algorithms could assist surgeons in identifying patients for whom surgery could do more harm than good [36].…”

Section: Current Trends and Future Directionsmentioning

confidence: 99%

“…More recently, Karhade et al [36] developed and introduced predictive algorithms for 6-week mortality in patients with spinal metastasis using five different machine-learning algorithms. These algorithms could assist surgeons in identifying patients for whom surgery could do more harm than good [36]. These evolving computational methodologies would be extensively utilized in predicting the prognosis of spinal metastatic tumors.…”

Section: Current Trends and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

An Updated Review on the Treatment Strategy for Spinal Metastasis from the Spine Surgeon’s Perspective

et al. 2022

View full text Add to dashboard Cite

Spinal metastasis is a common issue causing significant pain and disability in cancer patients. A multidisciplinary approach consisting of chemotherapy, radiotherapy, and surgical treatment is used for treating patients with metastatic spinal tumors. Due to recent advancements in medical and radiation oncology, like tumor genetics and stereotactic radiotherapy, this treatment strategy would change inevitably. Therefore, the decision-making systems developed for assisting physicians and surgeons to choose the most appropriate treatment for each patient with spinal metastasis need to evolve. In this review, the recent developments, validations, and modifications of these systems, as well as suggestions for future systems have been discussed. Recently, separation surgery combined with stereotactic radiotherapy (hybrid therapy) has gained popularity. Additionally, the evidence for hybrid therapy presented in the literature has been reviewed.

show abstract

More help than harm: surgery for metastatic spinal cord compression is associated with more favorable overall survival within a propensity score analysis

Leitner,

Bratschitsch,

Kostwein

et al. 2023

Eur Spine J

View full text Add to dashboard Cite

Purpose Indication for surgical decompression in metastatic spinal cord compression (MSCC) is often based on prognostic scores such as the modified Bauer score (mBs), with favorable prognosis suggestive of surgery and poor prognosis of non-surgical management. This study aimed to clarify if (1) surgery may directly affect overall survival (OS) aside from short-term neurologic outcome, (2) explore whether selected patient subgroups with poor mBs might still benefit from surgery, and (3) gauge putative adverse effects of surgery on short-term oncologic outcomes. Methods Single-center propensity score analyses with inverse-probability-of-treatment-weights (IPTW) of OS and short-term neurologic outcomes in MSCC patients treated with or without surgery between 2007 and 2020. Results Among 398 patients with MSCC, 194 (49%) underwent surgery. During a median follow-up of 5.8 years, 355 patients (89%) died. MBs was the most important predictor for spine surgery (p < 0.0001) and the strongest predictor of favorable OS (p < 0.0001). Surgery was associated with improved OS after accounting for selection bias with the IPTW method (p = 0.021) and emerged as the strongest determinant of short-term neurological improvement (p < 0.0001). Exploratory analyses delineated a subgroup of patients with an mBs of 1 point who still benefited from surgery, and surgery did not result in a higher risk of short-term oncologic disease progression. Conclusion This propensity score analysis corroborates the concept that spine surgery for MSCC associates with more favorable neurological and OS outcomes. Selected patients with poor prognosis might also benefit from surgery, suggesting that even those with low mBs may be considered for this intervention.

show abstract

Development and external validation of predictive algorithms for six-week mortality in spinal metastasis using 4,304 patients from five institutions

Cited by 11 publications

References 30 publications

A Machine Learning Algorithm for Predicting 6-Week Survival in Spinal Metastasis: An External Validation Study Using 2,768 Taiwanese Patients

A Machine Learning Algorithm for Predicting 6-Week Survival in Spinal Metastasis: An External Validation Study Using 2,768 Taiwanese Patients

An Updated Review on the Treatment Strategy for Spinal Metastasis from the Spine Surgeon’s Perspective

More help than harm: surgery for metastatic spinal cord compression is associated with more favorable overall survival within a propensity score analysis

Contact Info

Product

Resources

About