PMID- 30453080 OWN - NLM STAT- MEDLINE DCOM- 20200227 LR - 20200227 IS - 1878-1632 (Electronic) IS - 1529-9430 (Linking) VI - 19 IP - 5 DP - 2019 May TI - Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar discectomy: feasibility of center-specific modeling. PG - 853-861 LID - S1529-9430(18)31239-7 [pii] LID - 10.1016/j.spinee.2018.11.009 [doi] AB - BACKGROUND CONTEXT: There 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. PURPOSE: To evaluate the feasibility of deriving robust deep learning-based predictive analytics from single-center, single-surgeon data. STUDY DESIGN: Derivation of predictive models from a prospective registry. PATIENT SAMPLE: Patients who underwent single-level tubular microdiscectomy for lumbar disc herniation. OUTCOME MEASURES: Numeric rating scales for leg and back pain severity and Oswestry Disability Index scores at 12 months postoperatively. METHODS: Data 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. RESULTS: A 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. CONCLUSIONS: Our 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. CI - Copyright (c) 2018 Elsevier Inc. All rights reserved. FAU - Staartjes, Victor E AU - Staartjes VE AD - 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. FAU - de Wispelaere, Marlies P AU - de Wispelaere MP AD - Department of Clinical Informatics, Bergman Clinics Amsterdam, Rijksweg 69, 1411 GE Naarden, The Netherlands. FAU - Vandertop, William Peter AU - Vandertop WP AD - Neurosurgical Center Amsterdam, Amsterdam University Medical Centers, de Boelelaan 1117, 1081 HV Amsterdam, The Netherlands. FAU - Schroder, Marc L AU - Schroder ML AD - Department of Neurosurgery, Bergman Clinics Amsterdam, Rijksweg 69, 1411 GE Naarden, The Netherlands. LA - eng PT - Evaluation Study PT - Journal Article DEP - 20181116 PL - United States TA - Spine J JT - The spine journal : official journal of the North American Spine Society JID - 101130732 RN - Intervertebral disc disease SB - IM MH - Adult MH - Deep Learning/*standards MH - Diskectomy/*adverse effects/statistics & numerical data MH - Feasibility Studies MH - Female MH - Humans MH - Intervertebral Disc Degeneration/surgery MH - Intervertebral Disc Displacement/surgery MH - Lumbar Vertebrae/surgery MH - Male MH - Middle Aged MH - *Patient Reported Outcome Measures MH - Postoperative Complications/*epidemiology OTO - NOTNLM OT - Decision making OT - Disc herniation OT - Discectomy OT - Machine learning OT - Outcome measures OT - Sciatica EDAT- 2018/11/20 06:00 MHDA- 2020/02/28 06:00 CRDT- 2018/11/20 06:00 PHST- 2018/09/06 00:00 [received] PHST- 2018/11/12 00:00 [revised] PHST- 2018/11/12 00:00 [accepted] PHST- 2018/11/20 06:00 [pubmed] PHST- 2020/02/28 06:00 [medline] PHST- 2018/11/20 06:00 [entrez] AID - S1529-9430(18)31239-7 [pii] AID - 10.1016/j.spinee.2018.11.009 [doi] PST - ppublish SO - Spine J. 2019 May;19(5):853-861. doi: 10.1016/j.spinee.2018.11.009. Epub 2018 Nov 16.