PMID- 31042660
OWN - NLM
STAT- MEDLINE
DCOM- 20200831
LR  - 20200831
IS  - 1092-0684 (Electronic)
IS  - 1092-0684 (Linking)
VI  - 46
IP  - 5
DP  - 2019 May 1
TI  - Machine learning-based preoperative predictive analytics for lumbar spinal 
      stenosis.
PG  - E5
LID - 2019.2.FOCUS18723 [pii]
LID - 10.3171/2019.2.FOCUS18723 [doi]
AB  - OBJECTIVEPatient-reported outcome measures (PROMs) following decompression 
      surgery for lumbar spinal stenosis (LSS) demonstrate considerable heterogeneity. 
      Individualized prediction tools can provide valuable insights for shared 
      decision-making. The authors aim to evaluate the feasibility of predicting short- 
      and long-term PROMs, reoperations, and perioperative parameters by machine 
      learning (ML) methods.METHODSData were derived from a prospective registry. All 
      patients had undergone single- or multilevel mini-open facet-sparing 
      decompression for LSS. The prediction models were trained using various ML-based 
      algorithms to predict the endpoints of interest. Models were selected by area 
      under the receiver operating characteristic curve (AUC). The endpoints were 
      dichotomized by minimum clinically important difference (MCID) and included 
      6-week and 12-month numeric rating scales for back pain (NRS-BP) and leg pain 
      (NRS-LP) severity and the Oswestry Disability Index (ODI), as well as prolonged 
      surgery (> 45 minutes), extended length of hospital stay (> 28 hours), and 
      reoperations.RESULTSA total of 635 patients were included. The average age was 62 
      +/- 10 years, and 333 patients (52%) were male. At 6 weeks, MCID was seen in 63%, 
      76%, and 61% of patients for ODI, NRS-LP, and NRS-BP, respectively. At internal 
      validation, the models predicted MCID in these variables with accuracies of 69%, 
      76%, and 85%, and with AUCs of 0.75, 0.79, and 0.92. At 12 months, 66%, 63%, and 
      51% of patients reported MCID; the observed accuracies were 62%, 74%, and 66%, 
      with AUCs of 0.68, 0.72, and 0.79. Reoperations occurred in 60 patients (9.5%), 
      of which 27 (4.3%) occurred at the index level. Overall and index-level 
      reoperations were predicted with 69% and 63% accuracy, respectively, and with 
      AUCs of 0.66 and 0.61. In 15%, a length of surgery greater than 45 minutes was 
      observed and predicted with 78% accuracy and AUC of 0.54. Only 15% of patients 
      were admitted to the hospital for longer than 28 hours. The developed ML-based 
      model enabled prediction of extended hospital stay with an accuracy of 77% and 
      AUC of 0.58.CONCLUSIONSPreoperative prediction of a range of clinically relevant 
      endpoints in decompression surgery for LSS using ML is feasible, and may enable 
      enhanced informed patient consent and personalized shared decision-making. Access 
      to individualized preoperative predictive analytics for outcome and treatment 
      risks may represent a further step in the evolution of surgical care for patients 
      with LSS.
FAU - Siccoli, Alessandro
AU  - Siccoli A
AD  - 1Department of Neurosurgery, Bergman Clinics, Amsterdam.
FAU - de Wispelaere, Marlies P
AU  - de Wispelaere MP
AD  - 2Department of Clinical Informatics, Bergman Clinics, Amsterdam.
FAU - Schroder, Marc L
AU  - Schroder ML
AD  - 1Department of Neurosurgery, Bergman Clinics, Amsterdam.
FAU - Staartjes, Victor E
AU  - Staartjes VE
AD  - 1Department of Neurosurgery, Bergman Clinics, Amsterdam.
AD  - 3Amsterdam UMC, Vrije Universiteit Amsterdam, Neurosurgery, Amsterdam Movement 
      Sciences, Amsterdam, The Netherlands; and.
AD  - 4Department of Neurosurgery, Clinical Neuroscience Centre, University Hospital 
      Zurich, University of Zurich, Switzerland.
LA  - eng
PT  - Journal Article
PL  - United States
TA  - Neurosurg Focus
JT  - Neurosurgical focus
JID - 100896471
SB  - IM
MH  - Aged
MH  - Algorithms
MH  - *Decompression, Surgical
MH  - Feasibility Studies
MH  - Female
MH  - Humans
MH  - Length of Stay
MH  - *Lumbar Vertebrae
MH  - *Machine Learning
MH  - Male
MH  - Middle Aged
MH  - Predictive Value of Tests
MH  - Recovery of Function
MH  - Retrospective Studies
MH  - Spinal Stenosis/*surgery
MH  - Treatment Outcome
OTO - NOTNLM
OT  - ASA = American Society of Anesthesiologists
OT  - AUC = area under the receiver operating characteristic curve
OT  - GLM = generalized linear model
OT  - LSS = lumbar spinal stenosis
OT  - MCID = minimum clinically important difference
OT  - ML = machine learning
OT  - NPV = negative predictive value
OT  - NRS = numeric rating scale
OT  - NRS-BP = NRS for back pain
OT  - NRS-LP = NRS for leg pain
OT  - ODI = Oswestry Disability Index
OT  - PPV = positive predictive value
OT  - PROMs = patient-reported outcome measures
OT  - XGBoost = extreme gradient boosting
OT  - decompression
OT  - laminectomy
OT  - lumbar spinal stenosis
OT  - machine learning
OT  - outcome prediction
OT  - patient-reported outcome
EDAT- 2019/05/03 06:00
MHDA- 2020/09/01 06:00
CRDT- 2019/05/03 06:00
PHST- 2018/12/28 00:00 [received]
PHST- 2019/02/14 00:00 [accepted]
PHST- 2019/05/03 06:00 [entrez]
PHST- 2019/05/03 06:00 [pubmed]
PHST- 2020/09/01 06:00 [medline]
AID - 2019.2.FOCUS18723 [pii]
AID - 10.3171/2019.2.FOCUS18723 [doi]
PST - ppublish
SO  - Neurosurg Focus. 2019 May 1;46(5):E5. doi: 10.3171/2019.2.FOCUS18723.