Predictive Modeling of Length of Hospital Stay Following Adult Spinal Deformity Correction

Analysis of 653 Patients with an Accuracy of 75% within 2 Days

International Spine Study Group

Research output: Contribution to journalArticle

Abstract

Background: Length of stay (LOS) after surgery for adult spinal deformity (ASD) is a critical period that allows for optimal recovery. Predictive models that estimate LOS allow for stratification of high-risk patients. Methods: A prospectively acquired multicenter database of patients with ASD was used. Patients with staged surgery or LOS >30 days were excluded. Univariable predictor importance ≥0.90, redundancy, and collinearity testing were used to identify variables for model building. A generalized linear model was constructed using a training dataset developed from a bootstrap sample; patients not randomly selected for the bootstrap sample were selected to the training dataset. LOS predictions were compared with actual LOS to calculate an accuracy percentage. Results: Inclusion criteria were met by 653 patients. The mean LOS was 7.9 ± 4.1 days (median 7 days; range, 1–28 days). Following bootstrapping, 893 patients were modeled (653 in the training model and 240 in the testing model). Linear correlations for the training and testing datasets were 0.632 and 0.507, respectively. The prediction accuracy within 2 days of actual LOS was 75.4%. Conclusions: Our model successfully predicted LOS after ASD surgery with an accuracy of 75% within 2 days. Factors relating to actual LOS, such as rehabilitation bed availability and social support resources, are not captured in large prospective datasets. Predictive analytics will play an increasing role in the future of ASD surgery, and future models will seek to improve the accuracy of these tools.

Original languageEnglish (US)
JournalWorld Neurosurgery
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Length of Stay
Social Support
Linear Models
Rehabilitation
Databases
Datasets

Keywords

  • Adult spinal deformity
  • Length of stay
  • Predictive model

ASJC Scopus subject areas

  • Surgery
  • Clinical Neurology

Cite this

@article{2ff880907e1e4fd1b69e4895aefd5e73,
title = "Predictive Modeling of Length of Hospital Stay Following Adult Spinal Deformity Correction: Analysis of 653 Patients with an Accuracy of 75{\%} within 2 Days",
abstract = "Background: Length of stay (LOS) after surgery for adult spinal deformity (ASD) is a critical period that allows for optimal recovery. Predictive models that estimate LOS allow for stratification of high-risk patients. Methods: A prospectively acquired multicenter database of patients with ASD was used. Patients with staged surgery or LOS >30 days were excluded. Univariable predictor importance ≥0.90, redundancy, and collinearity testing were used to identify variables for model building. A generalized linear model was constructed using a training dataset developed from a bootstrap sample; patients not randomly selected for the bootstrap sample were selected to the training dataset. LOS predictions were compared with actual LOS to calculate an accuracy percentage. Results: Inclusion criteria were met by 653 patients. The mean LOS was 7.9 ± 4.1 days (median 7 days; range, 1–28 days). Following bootstrapping, 893 patients were modeled (653 in the training model and 240 in the testing model). Linear correlations for the training and testing datasets were 0.632 and 0.507, respectively. The prediction accuracy within 2 days of actual LOS was 75.4{\%}. Conclusions: Our model successfully predicted LOS after ASD surgery with an accuracy of 75{\%} within 2 days. Factors relating to actual LOS, such as rehabilitation bed availability and social support resources, are not captured in large prospective datasets. Predictive analytics will play an increasing role in the future of ASD surgery, and future models will seek to improve the accuracy of these tools.",
keywords = "Adult spinal deformity, Length of stay, Predictive model",
author = "{International Spine Study Group} and Safaee, {Michael M.} and Scheer, {Justin K.} and Tamir Ailon and Smith, {Justin S.} and Hart, {Robert A.} and Burton, {Douglas C.} and Shay Bess and Neuman, {Brian J} and Passias, {Peter G.} and Emily Miller and Shaffrey, {Christopher I.} and Frank Schwab and Virginie Lafage and Klineberg, {Eric O.} and Ames, {Christopher P.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.wneu.2018.04.064",
language = "English (US)",
journal = "World Neurosurgery",
issn = "1878-8750",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Predictive Modeling of Length of Hospital Stay Following Adult Spinal Deformity Correction

T2 - Analysis of 653 Patients with an Accuracy of 75% within 2 Days

AU - International Spine Study Group

AU - Safaee, Michael M.

AU - Scheer, Justin K.

AU - Ailon, Tamir

AU - Smith, Justin S.

AU - Hart, Robert A.

AU - Burton, Douglas C.

AU - Bess, Shay

AU - Neuman, Brian J

AU - Passias, Peter G.

AU - Miller, Emily

AU - Shaffrey, Christopher I.

AU - Schwab, Frank

AU - Lafage, Virginie

AU - Klineberg, Eric O.

AU - Ames, Christopher P.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Background: Length of stay (LOS) after surgery for adult spinal deformity (ASD) is a critical period that allows for optimal recovery. Predictive models that estimate LOS allow for stratification of high-risk patients. Methods: A prospectively acquired multicenter database of patients with ASD was used. Patients with staged surgery or LOS >30 days were excluded. Univariable predictor importance ≥0.90, redundancy, and collinearity testing were used to identify variables for model building. A generalized linear model was constructed using a training dataset developed from a bootstrap sample; patients not randomly selected for the bootstrap sample were selected to the training dataset. LOS predictions were compared with actual LOS to calculate an accuracy percentage. Results: Inclusion criteria were met by 653 patients. The mean LOS was 7.9 ± 4.1 days (median 7 days; range, 1–28 days). Following bootstrapping, 893 patients were modeled (653 in the training model and 240 in the testing model). Linear correlations for the training and testing datasets were 0.632 and 0.507, respectively. The prediction accuracy within 2 days of actual LOS was 75.4%. Conclusions: Our model successfully predicted LOS after ASD surgery with an accuracy of 75% within 2 days. Factors relating to actual LOS, such as rehabilitation bed availability and social support resources, are not captured in large prospective datasets. Predictive analytics will play an increasing role in the future of ASD surgery, and future models will seek to improve the accuracy of these tools.

AB - Background: Length of stay (LOS) after surgery for adult spinal deformity (ASD) is a critical period that allows for optimal recovery. Predictive models that estimate LOS allow for stratification of high-risk patients. Methods: A prospectively acquired multicenter database of patients with ASD was used. Patients with staged surgery or LOS >30 days were excluded. Univariable predictor importance ≥0.90, redundancy, and collinearity testing were used to identify variables for model building. A generalized linear model was constructed using a training dataset developed from a bootstrap sample; patients not randomly selected for the bootstrap sample were selected to the training dataset. LOS predictions were compared with actual LOS to calculate an accuracy percentage. Results: Inclusion criteria were met by 653 patients. The mean LOS was 7.9 ± 4.1 days (median 7 days; range, 1–28 days). Following bootstrapping, 893 patients were modeled (653 in the training model and 240 in the testing model). Linear correlations for the training and testing datasets were 0.632 and 0.507, respectively. The prediction accuracy within 2 days of actual LOS was 75.4%. Conclusions: Our model successfully predicted LOS after ASD surgery with an accuracy of 75% within 2 days. Factors relating to actual LOS, such as rehabilitation bed availability and social support resources, are not captured in large prospective datasets. Predictive analytics will play an increasing role in the future of ASD surgery, and future models will seek to improve the accuracy of these tools.

KW - Adult spinal deformity

KW - Length of stay

KW - Predictive model

UR - http://www.scopus.com/inward/record.url?scp=85046884293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046884293&partnerID=8YFLogxK

U2 - 10.1016/j.wneu.2018.04.064

DO - 10.1016/j.wneu.2018.04.064

M3 - Article

JO - World Neurosurgery

JF - World Neurosurgery

SN - 1878-8750

ER -