External validation of the SORG 90-day and 1-year machine learning algorithms for survival in spinal metastatic disease

Karhade, Aditya V.; Ahmed, Ali; Pennington, Zach; Chara, Alejandro; Schilling, Andrew; Thio, Quirina C. B. S.; Ogink, Paul T.; Sciubba, Daniel M.; Schwab, Joseph H.

doi:10.1016/j.spinee.2019.09.003

Cited by 60 publications

(48 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diagnostic accuracy was compared with many of the prior scoring systems 25,28-30, 35, 38, 39, 42, 46,47 and found to be statistically superior to all of these previous scoring systems for both the 90-day and 1-year endpoints. The calculator has since been validated in an external surgical population, 49 with C-statistics of 0.75-0.81 and 0.77-0.78 for 90-day and 1-year survival, respectively.…”

Section: Nomograms Machine Learning and Calculatorsmentioning

confidence: 99%

To operate, or not to operate? Narrative review of the role of survival predictors in patient selection for operative management of patients with metastatic spine disease

Pennington¹,

Ehresman²,

Cottrill³

et al. 2021

Journal of Neurosurgery: Spine

Self Cite

View full text Add to dashboard Cite

Accurate prediction of patient survival is an essential component of the preoperative evaluation of patients with spinal metastases. Over the past quarter of a century, a number of predictors have been developed, although none have been accurate enough to be instituted as a staple of clinical practice. However, recently more comprehensive survival calculators have been published that make use of larger data sets and machine learning to predict postoperative survival among patients with spine metastases. Given the glut of calculators that have been published, the authors sought to perform a narrative review of the current literature, highlighting existing calculators along with the strengths and weaknesses of each. In doing so, they identify two “generations” of scoring systems—a first generation based on a priori factor weighting and a second generation comprising predictive tools that are developed using advanced statistical modeling and are focused on clinical deployment. In spite of recent advances, the authors found that most predictors have only a moderate ability to explain variation in patient survival. Second-generation models have a greater prognostic accuracy relative to first-generation scoring systems, but most still require external validation. Given this, it seems that there are two outstanding goals for these survival predictors, foremost being external validation of current calculators in multicenter prospective cohorts, as the majority have been developed from, and internally validated within, the same single-institution data sets. Lastly, current predictors should be modified to incorporate advances in targeted systemic therapy and radiotherapy, which have been heretofore largely ignored.

show abstract

Section: Nomograms Machine Learning and Calculatorsmentioning

confidence: 99%

To operate, or not to operate? Narrative review of the role of survival predictors in patient selection for operative management of patients with metastatic spine disease

Pennington¹,

Ehresman²,

Cottrill³

et al. 2021

Journal of Neurosurgery: Spine

Self Cite

View full text Add to dashboard Cite

show abstract

“…In their study, the nomogram was found intuitive and demonstrated a comparable level of performance. Then, in 2019, the SORG used machine-learning algorithms to develop a novel prognostic model for metastatic spinal disease [28], which was externally validated in subsequent studies [29,30].…”

Section: Classification-based Decision-making Systemsmentioning

confidence: 99%

“…Classically, prognostic models for spinal metastasis have been developed using logistic or proportional hazards regression analyses. As part of its research efforts, the SORG was able to develop prognostic models using machine-learning algorithms such as gradient boosting, decision trees, random forests, and neural networks [ 20 , 41 ], and these algorithms were externally validated elsewhere [ 29 ]. Like in other fields of medicine, evolving computational methodologies, including machine-learning algorithms, should be assessed extensively in terms of their potential in the management of spinal metastasis.…”

Section: Decision-making Systems For Managing Metastatic Spinal Tumormentioning

confidence: 99%

Treatment Strategy for Metastatic Spinal Tumors: A Narrative Review

et al. 2020

View full text Add to dashboard Cite

Metastatic spinal tumors are common, and their rising incidence can be attributed to the expanding aging population and increased survival rates among cancer patients. The decision-making process in the treatment of spinal metastasis requires a multidisciplinary approach that includes medical and radiation oncology, surgery, and rehabilitation. Various decision-making systems have been proposed in the literature in order to estimate survival and suggest appropriate treatment options for patients experiencing spinal metastasis. However, recent advances in treatment modalities for spinal metastasis, such as stereotactic radiosurgery and minimally invasive surgical techniques, have reshaped clinical practices concerning patients with spinal metastasis, making a demand for further improvements on current decision-making systems. In this review, recent improvements in treatment modalities and the evolution of decision-making systems for metastatic spinal tumors are discussed.

show abstract

“…[58][59][60][61] More specific algorithms have been created to predict preoperative factors impacting survival, discharge, and readmission rates in patients following spine surgery for spinal metastasis. 56,62,63 While some of these studies have used the National Surgical Quality Improvement Program database and insurance databases in the past, similar algorithms could be produced for other indications using large EMR datasets. Then, ML techniques such as ridge linear regression and to a much larger extent nonlinear DL models like ANNs can identify the features most relevant and helpful to predicting each post-surgical outcome.…”

Section: Clinical Prognosticationmentioning

confidence: 99%

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

et al. 2019

View full text Add to dashboard Cite

Developments in machine learning in recent years have precipitated a surge in research on the applications of artificial intelligence within medicine. Machine learning algorithms are beginning to impact medicine broadly, and the field of spine surgery is no exception. Electronic medical records are a key source of medical data that can be leveraged for the creation of clinically valuable machine learning algorithms. This review examines the current state of machine learning using electronic medical records as it applies to spine surgery. Studies across the electronic medical record data domains of imaging, text, and structured data are reviewed. Discussed applications include clinical prognostication, preoperative planning, diagnostics, and dynamic clinical assistance, among others. The limitations and future challenges for machine learning research using electronic medical records are also discussed.

show abstract

External validation of the SORG 90-day and 1-year machine learning algorithms for survival in spinal metastatic disease

Cited by 60 publications

References 32 publications

To operate, or not to operate? Narrative review of the role of survival predictors in patient selection for operative management of patients with metastatic spine disease

To operate, or not to operate? Narrative review of the role of survival predictors in patient selection for operative management of patients with metastatic spine disease

Treatment Strategy for Metastatic Spinal Tumors: A Narrative Review

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

Contact Info

Product

Resources

About