2021
DOI: 10.1093/neuros/nyab085
|View full text |Cite
|
Sign up to set email alerts
|

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning

Abstract: BACKGROUND The referral process for consultation with a spine surgeon remains inefficient, given a substantial proportion of referrals to spine surgeons are nonoperative. OBJECTIVE To develop a machine-learning-based algorithm which accurately identifies patients as candidates for consultation with a spine surgeon, using only magnetic resonance imaging (MRI). METHODS … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

1
11
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 18 publications
(19 citation statements)
references
References 19 publications
1
11
0
Order By: Relevance
“…We found that variables from imaging analyses are the most important variables to consider surgical recommendations, which is in line with a recent machine learning model showing that spinal surgery candidacy may be predicted using imaging only [21]. However, we also found as important predictors certain specific clinical symptoms including motor deficit reported by the doctor, back pain and leg weakness as reported from the patient.…”
Section: Discussionsupporting
confidence: 90%
“…We found that variables from imaging analyses are the most important variables to consider surgical recommendations, which is in line with a recent machine learning model showing that spinal surgery candidacy may be predicted using imaging only [21]. However, we also found as important predictors certain specific clinical symptoms including motor deficit reported by the doctor, back pain and leg weakness as reported from the patient.…”
Section: Discussionsupporting
confidence: 90%
“…In the outpatient primary care setting, a general practitioner must determine to refer a patient to spinal subspecialist for consultation when discover specific radiographic findings, however large proportion of referrals ultimately fail to meet criteria for surgical intervention. 34 , 35…”
Section: Resultsmentioning
confidence: 99%
“…34,35 ML could provide auxiliary information to optimize the referral process and save time of patients and surgeons. 34 Deep learning had been reported to successfully apply for diagnosis of liver masses, parkinsonian disorders, hip fractures and estimating bone age. [36][37][38][39][40] Combining multiple data, ML can provide accurate diagnostic predictions and risk warnings.…”
Section: Image Processing and Diagnosismentioning
confidence: 99%
“…For classical performance evaluation, the MDL models achieved a mean AUC of 0.725 for early surgery and 0.655 for late surgery. The early surgery performance approaches results from prior studies that used DL to predict aspects of lumbar surgeries [ 60 , 61 ]. André et al assessed the feasibility of training a DL model on synthetic patients generated from EHR data to predict the positive and negative outcomes from decompression surgery resulting in an AUC of 0.78, while Wilson et al predicted spinal surgery by applying deep learning to MRI images and achieved an AUC of 0.88.…”
Section: Discussionmentioning
confidence: 99%