Result: Supervised Machine Learning for Predicting Length of Stay After Lumbar Arthrodesis: A Comprehensive Artificial Intelligence Approach.
Original Publication: Rosemont, IL : American Academy of Orthopaedic Surgeons, c1993-
Adogwa O, Lilly DT, Khalid S, et al.: Extended length of stay after lumbar spine surgery: Sick patients, postoperative complications, or practice style differences among hospitals and physicians? World Neurosurg 2019;123:e734-e739.
Lawson EH, Hall BL, Louie R, et al.: Association between occurrence of a postoperative complication and readmission: Implications for quality improvement and cost savings. Ann Surg 2013;258:10-18.
McCormack RA, Hunter T, Ramos N, Michels R, Hutzler L, Bosco JA: An analysis of causes of readmission after spine surgery. Spine (Phila Pa 1976) 2012;37:1260-1266.
Twitchell S, Karsy M, Reese J, et al.: Assessment of cost drivers and cost variation for lumbar interbody fusion procedures using the value driven outcomes database. Neurosurg Focus 2018;44:E10.
Zygourakis CC, Liu CY, Wakam G, et al.: Geographic and hospital variation in cost of lumbar laminectomy and lumbar fusion for degenerative conditions. Neurosurgery 2017;81:331-340.
Malik AT, Jain N, Kim J, Yu E, Khan SN: Continued inpatient care after elective 1- to 2-level posterior lumbar fusions increases 30-day postdischarge readmissions and complications. Clin Spine Surg 2018;31:E453-E459.
Dietz N, Sharma M, Alhourani A, et al.: Bundled payment models in spine surgery: Current challenges and opportunities, a systematic review. World Neurosurg 2019;123:177-183.
Beckerman D, Esparza M, Lee SI, et al.: Cost analysis of single-level lumbar fusions. Glob Spine J 2020;10:39-46.
McGirt MJ, Parker SL, Mummaneni P, et al.: Is the use of minimally invasive fusion technologies associated with improved outcomes after elective interbody lumbar fusion? Analysis of a nationwide prospective patient-reported outcomes registry. Spine J 2017;17:922-932.
Wagner SC, Butler JS, Kaye ID, Sebastian AS, Morrissey PB, Kepler CK: Risk factors for and complications after surgical delay in elective single-level lumbar fusion. Spine (Phila Pa 1976) 2018;43:228-233.
Kobayashi K, Ando K, Kato F, et al.: Predictors of prolonged length of stay after lumbar interbody fusion: A multicenter study. Glob Spine J 2019;9:466-472.
London AJ. Artificial intelligence and black-box medical decisions: Accuracy versus explainability. Hastings Cent Rep 2019;49:15-21.
Biron DR, Sinha I, Kleiner JE, et al.: A novel machine learning model developed to assist in patient selection for outpatient total shoulder arthroplasty. J Am Acad Orthop Surg 2019;28:1-6.
Navarro SM, Wang EY, Haeberle HS, et al. Machine learning and primary total knee arthroplasty: Patient forecasting for a patient-specific payment model. J Arthroplasty 2018;33:3617-3623.
Durand WM, DePasse JM, Daniels AH: Predictive modeling for blood transfusion following adult spinal deformity surgery. Spine (Phila Pa 1976) 2018;43:1058-1066.
Hopkins BS, Yamaguchi JT, Garcia R, et al. Using machine learning to predict 30-day readmissions after posterior lumbar fusion: An NSQIP study involving 23,264 patients. J Neurosurg Spine 2020;32:399-406.
ACS National Surgical Quality Improvement Program. Available at: https://www.facs.org/quality-programs/acs-nsqip. Accessed July 7, 2020.
Beretta L, Santaniello A: Nearest neighbor imputation algorithms: A critical evaluation. BMC Med Inform Decis Mak 2016;16(suppl 3):74.
Varoquaux G, Buitinck L, Louppe G, Grisel O, Pedregosa F, Mueller A: Scikit-learn. Getmobile Mob Comput Commun 2015;19:29-33.
Goyal A, Ngufor C, Kerezoudis P, McCutcheon B, Storlie C, Bydon M: Can machine learning algorithms accurately predict discharge to nonhome facility and early unplanned readmissions following spinal fusion? Analysis of a national surgical registry. J Neurosurg Spine 2019;31:568-578.
Mo X, Chen X, Li H, et al. Early and accurate prediction of clinical response to methotrexate treatment in juvenile idiopathic arthritis using machine learning. Front Pharmacol 2019;10:1155.
Westbury CF: Bayes' rule for clinicians: An introduction. Front Psychol 2010;1:192.
Andersson MG, Faverjon C, Vial F, Legrand L, Leblond A: Using Bayesrule to define the value of evidence from syndromic surveillance. PLoS One 2014;9:111335.
DiSilvestro KJ, Veeramani A, McDonald CL, et al. Predicting postoperative mortality after metastatic intraspinal neoplasm excision: Development of a machine-learning approach. World Neurosurg 2020;146:e917-e924.
Hu YJ, Ku TH, Jan RH, Wang K, Tseng YC, Yang SF: Decision tree-based learning to predict patient controlled analgesia consumption and readjustment. BMC Med Inform Decis Mak 2012;12:131.
Zhang Z, Zhao Y, Canes A, Steinberg D, Lyashevska O: Predictive analytics with gradient boosting in clinical medicine. Ann Transl Med 2019;7:152.
Cao C, Liu F, Tan H, et al. Deep learning and its applications in biomedicine. Genomics, Proteomics Bioinforma 2018;16:17-32.
Hajian-Tilaki K: Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Casp J Intern Med 2013;4:627-635.
Churpek MM, Carey KA, Edelson DP, et al. Internal and external validation of a machine learning risk score for acute kidney injury. JAMA Netw Open 2020;3:e2012892.
Yang S, Berdine G: The receiver operating characteristic (ROC) curve. Southwest Respir Crit Care Chron 2017;5:34.
Rufibach K: Use of Brier score to assess binary predictions. J Clin Epidemiol 2010;63:938-939.
Kalagara S, Eltorai AEM, Durand WM, Mason DePasse J, Daniels AH: Machine learning modeling for predicting hospital readmission following lumbar laminectomy. J Neurosurg Spine 2019;30:344-352.
Koo AB, Elsamadicy AA, Kundishora AJ, et al. Geographic variation in outcomes and costs after spinal fusion for adolescent idiopathic scoliosis. World Neurosurg 2020;136:e347-e354.
Malik AT, Deiparine S, Khan SN, Kim J, Yu E: Costs associated with a 90-day episode of care after single-level anterior lumbar interbody fusion. World Neurosurg 2020;135:e716-e722.
Ugiliweneza B, Kong M, Nosova K, et al. Spinal surgery: Variations in health care costs and implications for episode-based bundled payments. Spine (Phila Pa 1976) 2014;39:1235-1242.
Wright DJ, Mukamel DB, Greenfield S, Samuel Bederman S: Cost variation within spinal fusion payment groups. Spine (Phila Pa 1976) 2016;41:1747-1753.
Sanders AE, Andras LM, Sousa T, Kissinger C, Cucchiaro G, Skaggs DL: Accelerated discharge protocol for posterior spinal fusion patients with adolescent idiopathic scoliosis decreases hospital postoperative charges 22%. Spine (Phila Pa 1976) 2017;42:92-97.
Fletcher ND, Andras LM, Lazarus DE, et al.: Use of a novel pathway for early discharge was associated with a 48% shorter length of stay after posterior spinal fusion for adolescent idiopathic scoliosis. J Pediatr Orthop 2017;37:92-97.
Park P, Nerenz DR, Aleem IS, et al.: Risk factors associated with 90-day readmissions after degenerative lumbar fusion: An examination of the Michigan spine surgery improvement collaborative (MSSIC) registry. Clin Neurosurg 2019;85:402-408.
Further Information
Introduction: Few studies have evaluated the utility of machine learning techniques to predict and classify outcomes, such as length of stay (LOS), for lumbar fusion patients. Six supervised machine learning algorithms may be able to predict and classify whether a patient will experience a short or long hospital LOS after lumbar fusion surgery with a high degree of accuracy.
Methods: Data were obtained from the National Surgical Quality Improvement Program between 2009 and 2018. Demographic and comorbidity information was collected for patients who underwent anterior, anterolateral, or lateral transverse process technique arthrodesis procedure; anterior lumbar interbody fusion (ALIF); posterior, posterolateral, or lateral transverse process technique arthrodesis procedure; posterior lumbar interbody fusion/transforaminal lumbar interbody fusion (PLIF/TLIF); and posterior fusion procedure posterior spine fusion (PSF). Machine learning algorithmic analyses were done with the scikit-learn package in Python on a high-performance computing cluster. In the total sample, 85% of patients were used for training the models, whereas the remaining patients were used for testing the models. C-statistic area under the curve and prediction accuracy (PA) were calculated for each of the models to determine their accuracy in correctly classifying the test cases.
Results: In total, 12,915 ALIF patients, 27,212 PLIF/TLIF patients, and 23,406 PSF patients were included in the algorithmic analyses. The patient factors most strongly associated with LOS were sex, ethnicity, dialysis, and disseminated cancer. The machine learning algorithms yielded area under the curve values of between 0.673 and 0.752 (PA: 69.6% to 80.1%) for ALIF, 0.673 and 0.729 (PA: 66.0% to 81.3%) for PLIF/TLIF, and 0.698 and 0.749 (PA: 69.9% to 80.4%) for PSF.
Conclusion: Machine learning classification algorithms were able to accurately predict long LOS for ALIF, PLIF/TLIF, and PSF patients. Supervised machine learning algorithms may be useful in clinical and administrative settings. These data may additionally help inform predictive analytic models and assist in setting patient expectations.
Level Iii: Diagnostic study, retrospective cohort study.
(Copyright © 2021 by the American Academy of Orthopaedic Surgeons.)