• Victor E Staartjes, Marlies P de Wispelaere, William Peter Vandertop, and Marc L Schröder.
• Department of Neurosurgery, Bergman Clinics Amsterdam, Rijksweg 69, 1411 GE Naarden, The Netherlands; Amsterdam UMC, Vrije Universiteit Amsterdam, Neurosurgery, Amsterdam Movement Sciences, de Boelelaan 1117, 1081 HV Amsterdam, The Netherlands; Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Frauenklinikstrasse 10, 8091 Zurich, Switzerland. Electronic address: victor.staartjes@gmail.com.
• Spine J. 2019 May 1; 19 (5): 853-861.

Background ContextThere is considerable variability in patient-reported outcome measures following surgery for lumbar disc herniation. Individualized prediction tools that are derived from center- or even surgeon-specific data could provide valuable insights for shared decision-making.PurposeTo evaluate the feasibility of deriving robust deep learning-based predictive analytics from single-center, single-surgeon data.Study DesignDerivation of predictive models from a prospective registry.Patient SamplePatients who underwent single-level tubular microdiscectomy for lumbar disc herniation.Outcome MeasuresNumeric rating scales for leg and back pain severity and Oswestry Disability Index scores at 12 months postoperatively.MethodsData were derived from a prospective registry. We trained deep neural network-based and logistic regression-based prediction models for patient-reported outcome measures. The primary endpoint was achievement of the minimum clinically important difference (MCID) in numeric rating scales and Oswestry Disability Index, defined as a 30% or greater improvement from baseline. Univariate predictors of MCID were also identified using conventional statistics.ResultsA total of 422 patients were included (mean [SD] age: 48.5 [11.5] years; 207 [49%] female). After 1 year, 337 (80%), 219 (52%), and 337 (80%) patients reported a clinically relevant improvement in leg pain, back pain, and functional disability, respectively. The deep learning models predicted MCID with high area-under-the-curve of 0.87, 0.90, and 0.84, as well as accuracy of 85%, 87%, and 75%. The regression models provided inferior performance measures for each of the outcomes.ConclusionsOur study demonstrates that generating personalized and robust deep learning-based analytics for outcome prediction is feasible even with limited amounts of center-specific data. With prospective validation, the ability to preoperatively and reliably inform patients about the likelihood of symptom improvement could prove useful in patient counselling and shared decision-making.Copyright © 2018 Elsevier Inc. All rights reserved.

26 keywords...

hide…