PMID- 32344139
OWN - NLM
STAT- MEDLINE
DCOM- 20201216
LR  - 20201216
IS  - 1878-8769 (Electronic)
IS  - 1878-8750 (Linking)
VI  - 140
DP  - 2020 Aug
TI  - Development and Validation of Machine Learning Algorithms for Predicting Adverse 
      Events After Surgery for Lumbar Degenerative Spondylolisthesis.
PG  - 627-641
LID - S1878-8750(20)30842-1 [pii]
LID - 10.1016/j.wneu.2020.04.135 [doi]
AB  - BACKGROUND: Preoperative prognostication of adverse events (AEs) for patients 
      undergoing surgery for lumbar degenerative spondylolisthesis (LDS) can improve 
      risk stratification and help guide the surgical decision-making process. The aim 
      of this study was to develop and validate a set of predictive variables for 
      30-day AEs after surgery for LDS. METHODS: The American College of Surgeons 
      National Surgical Quality Improvement Program was used for this study 
      (2005-2016). Logistic regression (enter, stepwise, and forward) and LASSO (least 
      absolute shrinkage and selection operator) methods were performed to identify and 
      select variables for analyses, which resulted in 26 potential models. The final 
      model was selected based on clinical criteria and numeric results. RESULTS: The 
      overall 30-day rate of AEs for 80,610 patients who underwent surgery for LDS in 
      this database was 4.9% (n = 3965). The median age of the cohort was 58.0 years 
      (range, 18-89 years). The model with the following 10-predictive factors (age, 
      gender, American Society of Anesthesiologists grade, autogenous iliac bone graft, 
      instrumented fusion, levels of surgery, surgical approach, functional status, 
      preoperative serum albumin [g/dL] and serum alkaline phosphatase [IU/L]) 
      performed well on the discrimination, calibration, Brier score, and decision 
      analyses to develop machine learning algorithms. Logistic regression showed 
      higher areas under the curve than did LASSO methods across the different models. 
      The predictive probability derived from the best model is uploaded on an 
      open-access Web application, which can be found at: 
      https://spine.massgeneral.org/drupal/Lumbar-Degenerative-AdverseEvents. 
      CONCLUSIONS: It is feasible to develop machine learning algorithms from large 
      datasets to provide useful tools for patient counseling and surgical risk 
      assessment.
CI  - Copyright (c) 2020 Elsevier Inc. All rights reserved.
FAU - Fatima, Nida
AU  - Fatima N
AD  - Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical 
      School, Boston, Massachusetts, USA.
FAU - Zheng, Hui
AU  - Zheng H
AD  - Department of Biostatistics, Massachusetts General Hospital, Harvard Medical 
      School, Boston, Massachusetts, USA.
FAU - Massaad, Elie
AU  - Massaad E
AD  - Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical 
      School, Boston, Massachusetts, USA.
FAU - Hadzipasic, Muhamed
AU  - Hadzipasic M
AD  - Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical 
      School, Boston, Massachusetts, USA.
FAU - Shankar, Ganesh M
AU  - Shankar GM
AD  - Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical 
      School, Boston, Massachusetts, USA.
FAU - Shin, John H
AU  - Shin JH
AD  - Department of Neurosurgery, Massachusetts General Hospital, Harvard Medical 
      School, Boston, Massachusetts, USA. Electronic address: 
      Shin.john@mgh.harvard.edu.
LA  - eng
PT  - Journal Article
PT  - Validation Study
DEP - 20200425
PL  - United States
TA  - World Neurosurg
JT  - World neurosurgery
JID - 101528275
RN  - 0 (Serum Albumin)
RN  - EC 3.1.3.1 (Alkaline Phosphatase)
SB  - IM
MH  - Adolescent
MH  - Adult
MH  - Age Factors
MH  - Aged
MH  - Aged, 80 and over
MH  - *Algorithms
MH  - Alkaline Phosphatase/blood
MH  - Bone Transplantation/*methods
MH  - Clinical Decision Rules
MH  - Decision Making
MH  - Female
MH  - Functional Status
MH  - Humans
MH  - Ilium/transplantation
MH  - Logistic Models
MH  - Lumbar Vertebrae/*surgery
MH  - *Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Neurosurgical Procedures/*methods
MH  - Postoperative Complications/*epidemiology
MH  - Prognosis
MH  - Risk Factors
MH  - Serum Albumin/metabolism
MH  - Sex Factors
MH  - Spinal Fusion/*methods
MH  - Spondylolisthesis/*surgery
MH  - Transplantation, Autologous
MH  - Young Adult
OTO - NOTNLM
OT  - Artificial intelligence
OT  - Lumbar degenerative spondylolisthesis
OT  - Machine learning
OT  - Spine surgery
EDAT- 2020/04/29 06:00
MHDA- 2020/12/17 06:00
CRDT- 2020/04/29 06:00
PHST- 2020/03/23 00:00 [received]
PHST- 2020/04/17 00:00 [accepted]
PHST- 2020/04/29 06:00 [pubmed]
PHST- 2020/12/17 06:00 [medline]
PHST- 2020/04/29 06:00 [entrez]
AID - S1878-8750(20)30842-1 [pii]
AID - 10.1016/j.wneu.2020.04.135 [doi]
PST - ppublish
SO  - World Neurosurg. 2020 Aug;140:627-641. doi: 10.1016/j.wneu.2020.04.135. Epub 2020 
      Apr 25.