Development of machine learning algorithms for prediction of discharge disposition after elective inpatient surgery for lumbar degenerative disc disorders.

OBJECTIVEIf not anticipated and prearranged, hospital stay can be prolonged while the patient awaits placement in a rehabilitation unit or skilled nursing facility following elective spine surgery. Preoperative prediction of the likelihood of postoperative discharge to any setting other than home (i.e., nonroutine discharge) after elective inpatient spine surgery would be helpful in terms of decreasing hospital length of stay. The purpose of this study was to use machine learning algorithms to develop an open-access web application for preoperative prediction of nonroutine discharges in surgery for elective inpatient lumbar degenerative disc disorders.METHODSThe American College of Surgeons National Surgical Quality Improvement Program was queried to identify patients who underwent elective inpatient spine surgery for lumbar disc herniation or lumbar disc degeneration between 2011 and 2016. Four machine learning algorithms were developed to predict nonroutine discharge and the best algorithm was incorporated into an open-access web application.RESULTSThe rate of nonroutine discharge for 26,364 patients who underwent elective inpatient surgery for lumbar degenerative disc disorders was 9.28%. Predictive factors selected by random forest algorithms were age, sex, body mass index, fusion, level, functional status, extent and severity of comorbid disease (American Society of Anesthesiologists classification), diabetes, and preoperative hematocrit level. On evaluation in the testing set (n = 5273), the neural network had a c-statistic of 0.823, calibration slope of 0.935, calibration intercept of 0.026, and Brier score of 0.0713. On decision curve analysis, the algorithm showed greater net benefit for changing management over all threshold probabilities than changing management on the basis of the American Society of Anesthesiologists classification alone or for all patients or for no patients. The model can be found here: https://sorg-apps.shinyapps.io/discdisposition/.CONCLUSIONSMachine learning algorithms show promising results on internal validation for preoperative prediction of nonroutine discharges. If found to be externally valid, widespread use of these algorithms via the open-access web application by healthcare professionals may help preoperative risk stratification of patients undergoing elective surgery for lumbar degenerative disc disorders.

[1]  Max Kuhn,et al.  Applied Predictive Modeling , 2013 .

[2]  A. Furlan,et al.  Impact of Insurance Precertification on Discharge of Stroke Patients to Acute Rehabilitation or Skilled Nursing Facility. , 2017, Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association.

[3]  Maxwell Boakye,et al.  Spinal Surgery: Variations in Health Care Costs and Implications for Episode-Based Bundled Payments , 2014, Spine.

[4]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[5]  A. Galloway,et al.  The use of the Risk Assessment and Prediction Tool in surgical patients in a bundled payment program. , 2017, International journal of surgery.

[6]  Mehul V. Raval,et al.  Practical Guide to Surgical Data Sets: National Surgical Quality Improvement Program (NSQIP) and Pediatric NSQIP , 2018, JAMA surgery.

[7]  E. Hess,et al.  Derivation and validation of a simple calculator to predict home discharge after surgery. , 2014, Journal of the American College of Surgeons.

[8]  M. Porter A strategy for health care reform--toward a value-based system. , 2009, The New England journal of medicine.

[9]  Haiyin Liu,et al.  Variations in Medicare payments for episodes of spine surgery. , 2014, The spine journal : official journal of the North American Spine Society.

[10]  C. Mancuso,et al.  Psychosocial Variables Contribute to Length of Stay and Discharge Destination After Lumbar Surgery Independent of Demographic and Clinical Variables , 2018, Spine.

[11]  David M Cutler,et al.  The potential for cost savings through bundled episode payments. , 2012, The New England journal of medicine.

[12]  Wei Luo,et al.  Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View , 2016, Journal of medical Internet research.

[13]  J Lyle Bootman,et al.  Value in health care. , 2006, Managed care interface.

[14]  C. Crowson,et al.  Predictors of Discharge to a Nonhome Facility in Patients Undergoing Lumbar Decompression Without Fusion for Degenerative Spine Disease , 2017, Neurosurgery.

[15]  F. Schwab,et al.  Predictors of adverse discharge disposition in adult spinal deformity and associated costs. , 2017, The spine journal : official journal of the North American Spine Society.

[16]  C. Crowson,et al.  Lumbar decompression in the elderly: increased age as a risk factor for complications and nonhome discharge. , 2017, Journal of neurosurgery. Spine.

[17]  Jun S. Kim,et al.  Predictors for Patient Discharge Destination After Elective Anterior Cervical Discectomy and Fusion , 2017, Spine.

[18]  David C. Miller,et al.  Large variations in Medicare payments for surgery highlight savings potential from bundled payment programs. , 2011, Health affairs.

[19]  Jun S. Kim,et al.  Predictors for Non-Home Patient Discharge Following Elective Adult Spinal Deformity Surgery , 2017, Global spine journal.

[20]  João Maroco,et al.  Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests , 2011, BMC Research Notes.

[21]  M. McGirt,et al.  Predictors of extended length of stay, discharge to inpatient rehab, and hospital readmission following elective lumbar spine surgery: introduction of the Carolina-Semmes Grading Scale. , 2017, Journal of neurosurgery. Spine.

[22]  M. Maze,et al.  Bundled Payments in Total Joint Arthroplasty: Targeting Opportunities for Quality Improvement and Cost Reduction , 2014, Clinical orthopaedics and related research.

[23]  Heloise M Dubois,et al.  National Databases for Neurosurgical Outcomes Research: Options, Strengths, and Limitations , 2018, Neurosurgery.

[24]  Gloria P. Lipori,et al.  MySurgeryRisk: Development and Validation of a Machine-learning Risk Algorithm for Major Complications and Death After Surgery , 2019, Annals of surgery.

[25]  Gary S Collins,et al.  Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): Explanation and Elaboration , 2015, Annals of Internal Medicine.

[26]  R. Deyo,et al.  Morbidity and mortality in association with operations on the lumbar spine. The influence of age, diagnosis, and procedure. , 1992, The Journal of bone and joint surgery. American volume.

[27]  Safdar N. Khan,et al.  Predictors of discharge to an inpatient rehabilitation facility after a single-level posterior spinal fusion procedure , 2017, European Spine Journal.

[28]  R A Deyo,et al.  Morbidity and mortality in association with operations on the lumbar spine. The influence of age, diagnosis, and procedure. , 1992, The Journal of bone and joint surgery. American volume.

[29]  R. C. Kersting Impact of Social Support, Diversity, and Poverty on Nursing Home Utilization in a Nationally Representative Sample of Older Americans , 2001, Social work in health care.

[30]  Neena K Sharma,et al.  Predicting discharge placement and health care needs after lumbar spine laminectomy. , 2014, Journal of allied health.