Clinical Study|Articles in Press

Accounting for age in prediction of discharge destination following elective lumbar fusion: a supervised machine learning approach



      The number of elective spinal fusion procedures performed each year continues to grow, making risk factors for post-operative complications following this procedure increasingly clinically relevant. Nonhome discharge (NHD) is of particular interest due to its associations with increased costs of care and rates of complications. Notably, increased age has been found to influence rates of NHD.


      To identify aged-adjusted risk factors for nonhome discharge following elective lumbar fusion through the utilization of Machine Learning-generated predictions within stratified age groupings.


      Retrospective Database Study.


      The American College of Surgeons National Quality Improvement Program (ACS-NSQIP) database years 2008 to 2018.


      Postoperative discharge destination.


      ACS-NSQIP was queried to identify adult patients undergoing elective lumbar spinal fusion from 2008 to 2018. Patients were then stratified into the following age ranges: 30 to 44 years, 45 to 64 years, and ≥65 years. These groups were then analyzed by eight ML algorithms, each tasked with predicting post-operative discharge destination.


      Prediction of NHD was performed with average AUCs of 0.591, 0.681, and 0.693 for those aged 30 to 44, 45 to 64, and ≥65 years respectively. In patients aged 30 to 44, operative time (p<.001), African American/Black race (p=.003), female sex (p=.002), ASA class three designation (p=.002), and preoperative hematocrit (p=.002) were predictive of NHD. In ages 45 to 64, predictive variables included operative time, age, preoperative hematocrit, ASA class two or class three designation, insulin-dependent diabetes, female sex, BMI, and African American/Black race all with p<.001. In patients ≥65 years, operative time, adult spinal deformity, BMI, insulin-dependent diabetes, female sex, ASA class four designation, inpatient status, age, African American/Black race, and preoperative hematocrit were predictive of NHD with p<.001. Several variables were distinguished as predictive for only one age group including ASA Class two designation in ages 45 to 64 and adult spinal deformity, ASA class four designation, and inpatient status for patients ≥65 years.


      Application of ML algorithms to the ACS-NSQIP dataset identified a number of highly predictive and age-adjusted variables for NHD. As age is a risk factor for NHD following spinal fusion, our findings may be useful in both guiding perioperative decision-making and recognizing unique predictors of NHD among specific age groups.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to The Spine Journal
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Weiss A.J.
        • Elixhauser A.
        Trends in Operating Room Procedures in U.S. Hospitals, 2001–2011.
        in: Healthcare Cost and Utilization Project (HCUP) Statistical Briefs. Agency for Healthcare Research and Quality (US), 2006 (Available at:)
        • Martin BI
        • Mirza SK
        • Spina N
        • Spiker WR
        • Lawrence B
        • Brodke DS
        Trends in lumbar fusion procedure rates and associated hospital costs for degenerative spinal diseases in the United States, 2004 to 2015.
        Spine (Phila Pa 1976). 2019; 44: 369-376
        • Karnuta JM
        • Golubovsky JL
        • Haeberle HS
        • Rajan PV
        • Navarro SM
        • Kamath AF
        • et al.
        Can a machine learning model accurately predict patient resource utilization following lumbar spinal fusion?.
        Spine J. 2020; 20: 329-336
        • Clement ND
        • Court-Brown CM
        Elderly pelvic fractures: the incidence is increasing and patient demographics can be used to predict the outcome.
        Eur J Orthop Surg Traumatol. 2014; 24: 1431-1437
        • Marbacher S
        • Mannion AF
        • Burkhardt JK
        • Schär RT
        • Porchet F
        • Kleinstück F
        • et al.
        Patient-rated outcomes of lumbar fusion in patients with degenerative disease of the lumbar spine: does age matter?.
        Spine (Phila Pa 1976). 2016; 41: 893-900
        • Pennicooke B
        • Santacatterina M
        • Lee J
        • Elowitz E
        • Kallus N
        The effect of patient age on discharge destination and complications after lumbar spinal fusion.
        J Clin Neurosci. 2021; 91: 319-326
      1. An all-payer view of hospital discharge to postacute care, 2013 #205. Available at: Accessed December 15, 2022

        • Minetos PD
        • Canseco JA
        • Karamian BA
        • Bowles DR
        • Bhatt AH
        • Semenza NC
        • et al.
        Discharge disposition and clinical outcomes after spine surgery.
        Am J Med Qual. 2022; 37: 153-159
        • Park C
        • Cook CE
        • Garcia AN
        • Gottfried ON
        Discharge destination influences risks of readmission and complications after lumbar spine surgery in severely disabled patients.
        Clin Neurol Neurosurg. 2021; 207106801
        • Karhade AV
        • Ogink P
        • Thio Q
        • Broekman M
        • Cha T
        • Gormley WB
        • et al.
        Development of machine learning algorithms for prediction of discharge disposition after elective inpatient surgery for lumbar degenerative disc disorders.
        Neurosurg Focus. 2018; 45: E6
        • Pedregosa F
        • Varoquaux G
        • Gramfort A
        • Michel V
        • Thirion B
        • Grisel O
        • et al.
        Scikit-learn: machine learning in python.
        J Mach Learn Res. 2011; 12: 2825-2830
        • Van Rossum G.
        • Drake F.L.
        Python 3 Reference Manual. CreateSpace: Scotts, Valley, CA2009
        • Stekhoven DJ
        • Bühlmann P
        MissForest—non-parametric missing value imputation for mixed-type data.
        Bioinformatics. 2012; 28: 112-118
      2. Hyperparameter optimization using Scikit-Learn | SpringerLink. Available at: Accessed December 15, 2022

        • Kaneko H
        Cross-validated permutation feature importance considering correlation between features.
        Anal Sci Adv. 2022; 3: 278-287
        • Alam MdZ
        • Rahman MS
        • Rahman MS
        A random forest based predictor for medical data classification using feature ranking.
        Inform Med Unlocked. 2019; 15100180
        • Erickson BJ
        • Kitamura F
        Magician's corner: 9. Performance metrics for machine learning models.
        Radiol Artif Intell. 2021; 3e200126
      3. Ling, C. X., Huang, J., & Zhang, H. (2003). AUC: a better measure than accuracy in comparing learning algorithms. In Advances in Artificial Intelligence: 16th Conference of the Canadian Society for Computational Studies of Intelligence, AI 2003, Halifax, Canada, June 11–13, 2003, Proceedings 16 (pp. 329-341). Springer Berlin Heidelberg.

        • Hunter JD
        Matplotlib: a 2D graphics environment.
        Comput Sci Eng. 2007; 9: 90-95
        • Arrighi-Allisan AE
        • Neifert SN
        • Gal JS
        • Deutsch BC
        • Caridi JM
        Discharge destination as a predictor of postoperative outcomes and readmission following posterior lumbar fusion.
        World Neurosurg. 2019; 122: e139-e146
        • Aldebeyan S
        • Aoude A
        • Fortin M
        • Nooh A
        • Jarzem P
        • Ouellet J
        • et al.
        Predictors of discharge destination after lumbar spine fusion surgery.
        Spine (Phila Pa 1976). 2016; 41: 1535-1541
        • Ogura Y
        • Gum JL
        • Steele P
        • Crawford CH
        • Djurasovic M
        • Owens RK
        • et al.
        Drivers for nonhome discharge in a consecutive series of 1502 patients undergoing 1- or 2-level lumbar fusion.
        J Neurosurg Spine. 2020; 33: 766-771
        • Stephens BF
        • Khan I
        • Chotai S
        • Sivaganesan A
        • Devin CJ
        Drivers of cost in adult thoracolumbar spine deformity surgery.
        World Neurosurg. 2018; 118: e206-e211
        • Elsamadicy AA
        • Freedman IG
        • Koo AB
        • Wyatt D
        • Hengartner AC
        • Havlik J
        • et al.
        Patient- and hospital-related risk factors for non-routine discharge after lumbar decompression and fusion for spondylolisthesis.
        Clin Neurol Neurosurg. 2021; 209: 106902
        • Passias PG
        • Poorman GW
        • Bortz CA
        • Qureshi R
        • Diebo BG
        • Paul JC
        • et al.
        Predictors of adverse discharge disposition in adult spinal deformity and associated costs.
        Spine J. 2018; 18: 1845-1852
        • Karhade AV
        • Ogink PT
        • Thio QCBS
        • Cha TD
        • Hershman SH
        • Schoenfeld AJ
        • et al.
        Discharge disposition after anterior cervical discectomy and fusion.
        World Neurosurg. 2019; 132: e14-e20
        • Mummaneni PV
        • Bydon M
        • Knightly J
        • Alvi MA
        • Goyal A
        • Chan AK
        • et al.
        Predictors of nonroutine discharge among patients undergoing surgery for grade I spondylolisthesis: insights from the quality outcomes database.
        J Neurosurg Spine. 2019; 32: 523-532
        • Ahn A
        • Phan K
        • Cheung ZB
        • White SJW
        • Kim JS
        • Cho SKW
        Predictors of discharge disposition following laminectomy for intradural extramedullary spinal tumors.
        World Neurosurg. 2019; 123: e427-e432
        • Elsamadicy AA
        • Freedman IG
        • Koo AB
        • David WB
        • Lee M
        • Kundishora MJ
        • et al.
        Influence of gender on discharge disposition after spinal fusion for adult spine deformity correction.
        Clin Neurol Neurosurg. 2020; 194: 105875
        • Ye I
        • Phan K
        • Cheung ZB
        • White SJW
        • Nguyen J
        • Cho B
        • et al.
        Predictive risk factors of nonhome discharge following elective posterior cervical fusion.
        World Neurosurg. 2018; 119: e574-e579
        • Ogink PT
        • Karhade AV
        • Thio QCBS
        • Gormley WB
        • Oner FC
        • Verlaan J
        • et al.
        Predicting discharge placement after elective surgery for lumbar spinal stenosis using machine learning methods.
        Eur Spine J. 2019; 28: 1433-1440
        • Jain D
        • Durand W
        • Burch S
        • Daniels A
        • Berven S.
        Machine learning for predictive modeling of 90-day readmission, major medical complication, and discharge to a facility in patients undergoing long segment posterior lumbar spine fusion.
        Spine. 2020; 45: 1151-1160
        • Hamilton BH
        • Ko CY
        • Richards K
        • Hall BL
        Missing data in the American college of surgeons national surgical quality improvement program are not missing at random: implications and potential impact on quality assessments.
        J Am Coll Surg. 2010; 210: 125
        • Cava WL
        • Bauer C
        • Moore JH
        • Pendergrass SA
        Interpretation of machine learning predictions for patient outcomes in electronic health records.
        AMIA Annu Symp Proc. 2020; 2019: 572-581