Development of a preoperative predictive model for major complications following adult spinal deformity surgery

Justin K. Scheer, Justin S. Smith, Frank Schwab, Virginie Lafage, Christopher I. Shaffrey, Shay Bess, Alan H. Daniels, Robert A. Hart, Themistocles S. Protopsaltis, Gregory M. Mundis, Daniel M. Sciubba, Tamir Ailon, Douglas C. Burton, Eric Otto Klineberg, Christopher P. Ames

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

OBJECTIVE: The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS: This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS: Five hundred fifty-seven patients were included: 409 (73.4%) in the NOCOMP group, and 148 (26.6%) in the COMP group. The overall model accuracy was 87.6% correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS: A successful model (87% accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.

Original languageEnglish (US)
Pages (from-to)736-743
Number of pages8
JournalJournal of Neurosurgery: Spine
Volume26
Issue number6
DOIs
StatePublished - Jun 1 2017

Fingerprint

Scoliosis
ROC Curve
Research
Comorbidity
Decision Making
Point-of-Care Systems
Demography
Pain
Lordosis
Decision Trees
Bone Morphogenetic Proteins
Intraoperative Complications
Decompression
Reoperation
Osteoporosis
Counseling
Leg
Quality of Life
Databases
Transplants

Keywords

  • Adult spinal deformity
  • ASD
  • Complications
  • Decision tree
  • Predictive modeling
  • Sagittal malalignment
  • Scoliosis

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Scheer, J. K., Smith, J. S., Schwab, F., Lafage, V., Shaffrey, C. I., Bess, S., ... Ames, C. P. (2017). Development of a preoperative predictive model for major complications following adult spinal deformity surgery. Journal of Neurosurgery: Spine, 26(6), 736-743. https://doi.org/10.3171/2016.10.SPINE16197

Development of a preoperative predictive model for major complications following adult spinal deformity surgery. / Scheer, Justin K.; Smith, Justin S.; Schwab, Frank; Lafage, Virginie; Shaffrey, Christopher I.; Bess, Shay; Daniels, Alan H.; Hart, Robert A.; Protopsaltis, Themistocles S.; Mundis, Gregory M.; Sciubba, Daniel M.; Ailon, Tamir; Burton, Douglas C.; Klineberg, Eric Otto; Ames, Christopher P.

In: Journal of Neurosurgery: Spine, Vol. 26, No. 6, 01.06.2017, p. 736-743.

Research output: Contribution to journalArticle

Scheer, JK, Smith, JS, Schwab, F, Lafage, V, Shaffrey, CI, Bess, S, Daniels, AH, Hart, RA, Protopsaltis, TS, Mundis, GM, Sciubba, DM, Ailon, T, Burton, DC, Klineberg, EO & Ames, CP 2017, 'Development of a preoperative predictive model for major complications following adult spinal deformity surgery', Journal of Neurosurgery: Spine, vol. 26, no. 6, pp. 736-743. https://doi.org/10.3171/2016.10.SPINE16197
Scheer, Justin K. ; Smith, Justin S. ; Schwab, Frank ; Lafage, Virginie ; Shaffrey, Christopher I. ; Bess, Shay ; Daniels, Alan H. ; Hart, Robert A. ; Protopsaltis, Themistocles S. ; Mundis, Gregory M. ; Sciubba, Daniel M. ; Ailon, Tamir ; Burton, Douglas C. ; Klineberg, Eric Otto ; Ames, Christopher P. / Development of a preoperative predictive model for major complications following adult spinal deformity surgery. In: Journal of Neurosurgery: Spine. 2017 ; Vol. 26, No. 6. pp. 736-743.
@article{c69899501ee8467bb71f702bfe130219,
title = "Development of a preoperative predictive model for major complications following adult spinal deformity surgery",
abstract = "OBJECTIVE: The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS: This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS: Five hundred fifty-seven patients were included: 409 (73.4{\%}) in the NOCOMP group, and 148 (26.6{\%}) in the COMP group. The overall model accuracy was 87.6{\%} correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS: A successful model (87{\%} accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.",
keywords = "Adult spinal deformity, ASD, Complications, Decision tree, Predictive modeling, Sagittal malalignment, Scoliosis",
author = "Scheer, {Justin K.} and Smith, {Justin S.} and Frank Schwab and Virginie Lafage and Shaffrey, {Christopher I.} and Shay Bess and Daniels, {Alan H.} and Hart, {Robert A.} and Protopsaltis, {Themistocles S.} and Mundis, {Gregory M.} and Sciubba, {Daniel M.} and Tamir Ailon and Burton, {Douglas C.} and Klineberg, {Eric Otto} and Ames, {Christopher P.}",
year = "2017",
month = "6",
day = "1",
doi = "10.3171/2016.10.SPINE16197",
language = "English (US)",
volume = "26",
pages = "736--743",
journal = "Journal of neurosurgery. Spine",
issn = "1547-5654",
publisher = "American Association of Neurological Surgeons",
number = "6",

}

TY - JOUR

T1 - Development of a preoperative predictive model for major complications following adult spinal deformity surgery

AU - Scheer, Justin K.

AU - Smith, Justin S.

AU - Schwab, Frank

AU - Lafage, Virginie

AU - Shaffrey, Christopher I.

AU - Bess, Shay

AU - Daniels, Alan H.

AU - Hart, Robert A.

AU - Protopsaltis, Themistocles S.

AU - Mundis, Gregory M.

AU - Sciubba, Daniel M.

AU - Ailon, Tamir

AU - Burton, Douglas C.

AU - Klineberg, Eric Otto

AU - Ames, Christopher P.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - OBJECTIVE: The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS: This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS: Five hundred fifty-seven patients were included: 409 (73.4%) in the NOCOMP group, and 148 (26.6%) in the COMP group. The overall model accuracy was 87.6% correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS: A successful model (87% accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.

AB - OBJECTIVE: The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS: This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS: Five hundred fifty-seven patients were included: 409 (73.4%) in the NOCOMP group, and 148 (26.6%) in the COMP group. The overall model accuracy was 87.6% correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS: A successful model (87% accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.

KW - Adult spinal deformity

KW - ASD

KW - Complications

KW - Decision tree

KW - Predictive modeling

KW - Sagittal malalignment

KW - Scoliosis

UR - http://www.scopus.com/inward/record.url?scp=85020178372&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020178372&partnerID=8YFLogxK

U2 - 10.3171/2016.10.SPINE16197

DO - 10.3171/2016.10.SPINE16197

M3 - Article

C2 - 28338449

AN - SCOPUS:85020178372

VL - 26

SP - 736

EP - 743

JO - Journal of neurosurgery. Spine

JF - Journal of neurosurgery. Spine

SN - 1547-5654

IS - 6

ER -