Artificial Intelligence Models Predict Operative Versus Nonoperative Management of Patients with Adult Spinal Deformity with 86% Accuracy.

dc.contributor.author

Durand, Wesley M

dc.contributor.author

Daniels, Alan H

dc.contributor.author

Hamilton, David K

dc.contributor.author

Passias, Peter

dc.contributor.author

Kim, Han Jo

dc.contributor.author

Protopsaltis, Themistocles

dc.contributor.author

LaFage, Virginie

dc.contributor.author

Smith, Justin S

dc.contributor.author

Shaffrey, Christopher

dc.contributor.author

Gupta, Munish

dc.contributor.author

Klineberg, Eric

dc.contributor.author

Schwab, Frank

dc.contributor.author

Burton, Doug

dc.contributor.author

Bess, Shay

dc.contributor.author

Ames, Christopher

dc.contributor.author

Hart, Robert

dc.contributor.author

International Spine Study Group

dc.date.accessioned

2023-06-19T19:53:18Z

dc.date.available

2023-06-19T19:53:18Z

dc.date.issued

2020-09

dc.date.updated

2023-06-19T19:53:18Z

dc.description.abstract

Objective

Patients with ASD show complex and highly variable disease. The decision to manage patients operatively is largely subjective and varies based on surgeon training and experience. We sought to develop models capable of accurately discriminating between patients receiving operative versus nonoperative treatment based only on baseline radiographic and clinical data at enrollment.

Methods

This study was a retrospective analysis of a multicenter consecutive cohort of patients with ASD. A total of 1503 patients were included, divided in a 70:30 split for training and testing. Patients receiving operative treatment were defined as those undergoing surgery up to 1 year after their baseline visit. Potential predictors included available demographics, past medical history, patient-reported outcome measures, and premeasured radiographic parameters from anteroposterior and lateral films. In total, 321 potential predictors were included. Random forest, elastic net regression, logistic regression, and support vector machines (SVMs) with radial and linear kernels were trained.

Results

Of patients in the training and testing sets, 69.0% (n = 727) and 69.1% (n = 311), respectively, received operative management. On evaluation with the testing dataset, performance for SVM linear (area under the curve =0.910), elastic net (0.913), and SVM radial (0.914) models was excellent, and the logistic regression (0.896) and random forest (0.830) models performed very well for predicting operative management of patients with ASD. The SVM linear model showed 86% accuracy.

Conclusions

This study developed models showing excellent discrimination (area under the curve >0.9) between patients receiving operative versus nonoperative management, based solely on baseline study enrollment values. Future investigations may evaluate the implementation of such models for decision support in the clinical setting.
dc.identifier

S1878-8750(20)31070-6

dc.identifier.issn

1878-8750

dc.identifier.issn

1878-8769

dc.identifier.uri

https://hdl.handle.net/10161/28136

dc.language

eng

dc.publisher

Elsevier BV

dc.relation.ispartof

World neurosurgery

dc.relation.isversionof

10.1016/j.wneu.2020.05.099

dc.subject

International Spine Study Group

dc.subject

Humans

dc.subject

Scoliosis

dc.subject

Linear Models

dc.subject

Logistic Models

dc.subject

Retrospective Studies

dc.subject

Quality of Life

dc.subject

Artificial Intelligence

dc.subject

Adult

dc.subject

Middle Aged

dc.subject

Female

dc.subject

Male

dc.subject

Congenital Abnormalities

dc.title

Artificial Intelligence Models Predict Operative Versus Nonoperative Management of Patients with Adult Spinal Deformity with 86% Accuracy.

dc.type

Journal article

duke.contributor.orcid

Passias, Peter|0000-0002-1479-4070|0000-0003-2635-2226

duke.contributor.orcid

Shaffrey, Christopher|0000-0001-9760-8386

pubs.begin-page

e239

pubs.end-page

e253

pubs.organisational-group

Duke

pubs.organisational-group

School of Medicine

pubs.organisational-group

Clinical Science Departments

pubs.organisational-group

Orthopaedic Surgery

pubs.organisational-group

Neurosurgery

pubs.publication-status

Published

pubs.volume

141

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Artificial Intelligence Models Predict Operative Versus Nonoperative Management of Patients with Adult Spinal Deformity with 86% Accuracy.pdf
Size:
1.73 MB
Format:
Adobe Portable Document Format