PMID- 30947300
OWN - NLM
STAT- MEDLINE
DCOM- 20191230
LR  - 20200309
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 14
IP  - 4
DP  - 2019
TI  - Using a machine learning approach to predict outcome after surgery for 
      degenerative cervical myelopathy.
PG  - e0215133
LID - 10.1371/journal.pone.0215133 [doi]
LID - e0215133
AB  - Degenerative cervical myelopathy (DCM) is a spinal cord condition that results in 
      progressive non-traumatic compression of the cervical spinal cord. Spine surgeons 
      must consider a large quantity of information relating to disease presentation, 
      imaging features, and patient characteristics to determine if a patient will 
      benefit from surgery for DCM. We applied a supervised machine learning approach 
      to develop a classification model to predict individual patient outcome after 
      surgery for DCM. Patients undergoing surgery for DCM as a part of the AOSpine 
      CSM-NA or CSM-I prospective, multi-centre studies were included in the analysis. 
      Out of 757 patients 605, 583, and 539 patients had complete follow-up information 
      at 6, 12, and 24 months respectively and were included in the analysis. The 
      primary outcome was improvement in the SF-6D quality of life indicator score by 
      the minimum clinically important difference (MCID). The secondary outcome was 
      improvement in the modified Japanese Orthopedic Association (mJOA) score by the 
      MCID. Predictor variables reflected information about pre-operative disease 
      severity, disease presentation, patient demographics, and comorbidities. A 
      machine learning approach of feature engineering, data pre-processing, and model 
      optimization was used to create the most accurate predictive model of outcome 
      after surgery for DCM. Following data pre-processing 48, 108, and 101 features 
      were chosen for model training at 6, 12, and 24 months respectively. The best 
      performing predictive model used a random forest structure and had an average 
      area under the curve (AUC) of 0.70, classification accuracy of 77%, and 
      sensitivity of 78% when evaluated on a testing cohort that was not used for model 
      training. Worse pre-operative disease severity, longer duration of DCM symptoms, 
      older age, higher body weight, and current smoking status were associated with 
      worse surgical outcomes. We developed a model that predicted positive surgical 
      outcome for DCM with good accuracy at the individual patient level on an 
      independent testing cohort. Our analysis demonstrates the applicability of 
      machine-learning to predictive modeling in spine surgery.
FAU - Merali, Zamir G
AU  - Merali ZG
AD  - Division of Neurosurgery, University of Toronto, Toronto, Ontario, Canada.
FAU - Witiw, Christopher D
AU  - Witiw CD
AUID- ORCID: 0000-0002-3999-7632
AD  - Division of Neurosurgery, University of Toronto, Toronto, Ontario, Canada.
FAU - Badhiwala, Jetan H
AU  - Badhiwala JH
AUID- ORCID: 0000-0002-2528-1684
AD  - Division of Neurosurgery, University of Toronto, Toronto, Ontario, Canada.
FAU - Wilson, Jefferson R
AU  - Wilson JR
AD  - Division of Neurosurgery, University of Toronto, Toronto, Ontario, Canada.
AD  - Division of Neurosurgery, St. Michael's Hospital, Toronto, Ontario, Canada.
FAU - Fehlings, Michael G
AU  - Fehlings MG
AUID- ORCID: 0000-0002-5722-6364
AD  - Division of Neurosurgery, University of Toronto, Toronto, Ontario, Canada.
AD  - Division of Neurosurgery, Toronto Western Hospital, Toronto, Ontario, Canada.
LA  - eng
SI  - ClinicalTrials.gov/NCT00285337
SI  - ClinicalTrials.gov/NCT00565734
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20190404
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
SB  - IM
MH  - Comorbidity
MH  - Decompression, Surgical/*adverse effects
MH  - Female
MH  - Humans
MH  - Intervertebral Disc Degeneration/*surgery
MH  - *Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Postoperative Complications/*diagnosis/etiology
MH  - Predictive Value of Tests
MH  - Prospective Studies
MH  - Spinal Cord Diseases/*surgery
MH  - Treatment Outcome
PMC - PMC6448910
COIS- The authors have declared that no competing interests exist.
EDAT- 2019/04/05 06:00
MHDA- 2019/12/31 06:00
PMCR- 2019/04/04
CRDT- 2019/04/05 06:00
PHST- 2018/07/26 00:00 [received]
PHST- 2019/03/27 00:00 [accepted]
PHST- 2019/04/05 06:00 [entrez]
PHST- 2019/04/05 06:00 [pubmed]
PHST- 2019/12/31 06:00 [medline]
PHST- 2019/04/04 00:00 [pmc-release]
AID - PONE-D-18-22191 [pii]
AID - 10.1371/journal.pone.0215133 [doi]
PST - epublish
SO  - PLoS One. 2019 Apr 4;14(4):e0215133. doi: 10.1371/journal.pone.0215133. 
      eCollection 2019.