Abstract
Purpose
Health-related quality of life (HRQL) instruments are essential in value-driven health care, but patients often have more specific, personal priorities when seeking surgical care. The Scoliosis Research Society-22R (SRS-22R), an HRQL instrument for spinal deformity, provides summary scores spanning several health domains, but these may be difficult for patients to utilize in planning their specific care goals. Our objective was to create preoperative predictive models for responses to individual SRS-22R questions at 1 and 2 years after adult spinal deformity (ASD) surgery to facilitate precision surgical care.
Methods
Two prospective observational cohorts were queried for ASD patients with SRS-22R data at baseline and 1 and 2 years after surgery. In total, 150 covariates were used in training machine learning models, including demographics, surgical data and perioperative complications. Validation was accomplished via an 80%/20% data split for training and testing, respectively. Goodness of fit was measured using area under receiver operating characteristic (AUROC) curves.
Results
In total, 561 patients met inclusion criteria. The AUROC ranged from 56.5 to 86.9%, reflecting successful fits for most questions. SRS-22R questions regarding pain, disability and social and labor function were the most accurately predicted. Models were less sensitive to questions regarding general satisfaction, depression/anxiety and appearance.
Conclusions
To the best of our knowledge, this is the first study to explicitly model the prediction of individual answers to the SRS-22R questionnaire at 1 and 2 years after deformity surgery. The ability to predict individual question responses may prove useful in preoperative counseling in the age of individualized medicine.
Graphic abstract
These slides can be retrieved under Electronic Supplementary Material.
Similar content being viewed by others
References
Bess S, Line B, Fu KM, McCarthy I, Lafage V, Schwab F, Shaffrey C, Ames C, Akbarnia B, Jo H, Kelly M, Burton D, Hart R, Klineberg E, Kebaish K, Hostin R, Mundis G, Mummaneni P, Smith JS, International Spine Study G (2016) The health impact of symptomatic adult spinal deformity: comparison of deformity types to United States population norms and chronic diseases. Spine (Phila Pa 1976) 41:224–233. https://doi.org/10.1097/brs.0000000000001202
Pellise F, Vila-Casademunt A, Ferrer M, Domingo-Sabat M, Bago J, Perez-Grueso FJ, Alanay A, Mannion AF, Acaroglu E, European Spine Study Group E (2015) Impact on health related quality of life of adult spinal deformity (ASD) compared with other chronic conditions. Eur Spine J 24:3–11. https://doi.org/10.1007/s00586-014-3542-1
Bridwell KH, Glassman S, Horton W, Shaffrey C, Schwab F, Zebala LP, Lenke LG, Hilton JF, Shainline M, Baldus C, Wootten D (2009) Does treatment (nonoperative and operative) improve the two-year quality of life in patients with adult symptomatic lumbar scoliosis: a prospective multicenter evidence-based medicine study. Spine (Phila Pa 1976) 34:2171–2178. https://doi.org/10.1097/brs.0b013e3181a8fdc8
Smith JS, Lafage V, Shaffrey CI, Schwab F, Lafage R, Hostin R, O’Brien M, Boachie-Adjei O, Akbarnia BA, Mundis GM, Errico T, Kim HJ, Protopsaltis TS, Hamilton DK, Scheer JK, Sciubba D, Ailon T, Fu KM, Kelly MP, Zebala L, Line B, Klineberg E, Gupta M, Deviren V, Hart R, Burton D, Bess S, Ames CP, International Spine Study G (2016) Outcomes of operative and nonoperative treatment for adult spinal deformity: a prospective, multicenter, propensity-matched cohort assessment with minimum 2-year follow-up. Neurosurgery 78:851–861. https://doi.org/10.1227/neu.0000000000001116
Smith JS, Shaffrey CI, Berven S, Glassman S, Hamill C, Horton W, Ondra S, Schwab F, Shainline M, Fu KM, Bridwell K, Spinal Deformity Study G (2009) Operative versus nonoperative treatment of leg pain in adults with scoliosis: a retrospective review of a prospective multicenter database with two-year follow-up. Spine (Phila Pa 1976) 34:1693–1698. https://doi.org/10.1097/brs.0b013e3181ac5fcd
Smith JS, Shaffrey CI, Berven S, Glassman S, Hamill C, Horton W, Ondra S, Schwab F, Shainline M, Fu KM, Bridwell K, Spinal Deformity Study G (2009) Improvement of back pain with operative and nonoperative treatment in adults with scoliosis. Neurosurgery 65:86–93. https://doi.org/10.1227/01.neu.0000347005.35282.6c (discussion 84–93)
Smith JS, Shaffrey CI, Glassman SD, Berven SH, Schwab FJ, Hamill CL, Horton WC, Ondra SL, Sansur CA, Bridwell KH, Spinal Deformity Study G (2011) Risk-benefit assessment of surgery for adult scoliosis: an analysis based on patient age. Spine (Phila Pa 1976) 36:817–824. https://doi.org/10.1097/brs.0b013e3181e21783
Smith JS, Singh M, Klineberg E, Shaffrey CI, Lafage V, Schwab FJ, Protopsaltis T, Ibrahimi D, Scheer JK, Mundis G Jr, Gupta MC, Hostin R, Deviren V, Kebaish K, Hart R, Burton DC, Bess S, Ames CP, International Spine Study G (2014) Surgical treatment of pathological loss of lumbar lordosis (flatback) in patients with normal sagittal vertical axis achieves similar clinical improvement as surgical treatment of elevated sagittal vertical axis: clinical article. J Neurosurg Spine 21:160–170. https://doi.org/10.3171/2014.3.spine13580
Smith JS, Shaffrey CI, Lafage V, Schwab F, Scheer JK, Protopsaltis T, Klineberg E, Gupta M, Hostin R, Fu KM, Mundis GM Jr, Kim HJ, Deviren V, Soroceanu A, Hart RA, Burton DC, Bess S, Ames CP, International Spine Study G (2015) Comparison of best versus worst clinical outcomes for adult spinal deformity surgery: a retrospective review of a prospectively collected, multicenter database with 2-year follow-up. J Neurosurg Spine 23:349–359. https://doi.org/10.3171/2014.12.spine14777
Smith JS, Klineberg E, Lafage V, Shaffrey CI, Schwab F, Lafage R, Hostin R, Mundis GM Jr, Errico TJ, Kim HJ, Protopsaltis TS, Hamilton DK, Scheer JK, Soroceanu A, Kelly MP, Line B, Gupta M, Deviren V, Hart R, Burton DC, Bess S, Ames CP, International Spine Study G (2016) Prospective multicenter assessment of perioperative and minimum 2-year postoperative complication rates associated with adult spinal deformity surgery. J Neurosurg Spine 25:1–14. https://doi.org/10.3171/2015.11.spine151036
Scheer JK, Keefe M, Lafage V, Kelly MP, Bess S, Burton DC, Hart RA, Jain A, Lonner BS, Protopsaltis TS, Hostin R, Shaffrey CI, Smith JS, Schwab F, Ames CP (2017) Importance of patient-reported individualized goals when assessing outcomes for adult spinal deformity (ASD): initial experience with a Patient Generated Index (PGI). Spine J 17:1397–1405. https://doi.org/10.1016/j.spinee.2017.04.013
Asher MA, Lai SM, Glattes RC, Burton DC, Alanay A, Bago J (2006) Refinement of the SRS-22 Health-Related Quality of Life questionnaire Function domain. Spine (Phila Pa 1976) 31:593–597. https://doi.org/10.1097/01.brs.0000201331.50597.ea
Mannion AF, Elfering A, Bago J, Pellise F, Vila-Casademunt A, Richner-Wunderlin S, Domingo-Sabat M, Obeid I, Acaroglu E, Alanay A, Perez-Grueso FS, Baldus CR, Carreon LY, Bridwell KH, Glassman SD, Kleinstuck F, European Spine Study G (2018) Factor analysis of the SRS-22 outcome assessment instrument in patients with adult spinal deformity. Eur Spine J 27:685–699. https://doi.org/10.1007/s00586-017-5279-0
Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen H, Wang Y (2017) Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2:230–243. https://doi.org/10.1136/svn-2017-000101
Champain S, Benchikh K, Nogier A, Mazel C, Guise JD, Skalli W (2006) Validation of new clinical quantitative analysis software applicable in spine orthopaedic studies. Eur Spine J 15:982–991. https://doi.org/10.1007/s00586-005-0927-1
Lafage R, Ferrero E, Henry JK, Challier V, Diebo B, Liabaud B, Lafage V, Schwab F (2015) Validation of a new computer-assisted tool to measure spino-pelvic parameters. Spine J 15:2493–2502. https://doi.org/10.1016/j.spinee.2015.08.067
Rillardon L, Levassor N, Guigui P, Wodecki P, Cardinne L, Templier A, Skalli W (2003) Validation of a tool to measure pelvic and spinal parameters of sagittal balance. Rev Chir Orthop Reparatrice Appar Mot 89:218–227
O’Brien MF, Kuklo TR, Blanke K, Lenke LG (2005) Spinal deformity study group radiographic measurement manual. In: Medtronic Sofamor Danek
Carreon LY, Puno RM, Dimar JR II, Glassman SD, Johnson JR (2003) Perioperative complications of posterior lumbar decompression and arthrodesis in older adults. J Bone Joint Surg Am 85-A:2089–2092
Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc Ser B (Stat Methodol) 67:301–320
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
Chen T, He T (2015) Xgboost: extreme gradient boosting. R Package version 4.2
Breiman L (1999) Random forest. Mach Learn 45:1–35. https://doi.org/10.1023/A:1010933404324
Song L, Langfelder P, Horvath S (2013) Random generalized linear model: a highly accurate and interpretable ensemble predictor. BMC Bioinform 14:5. https://doi.org/10.1186/1471-2105-14-5
Tang F, Ishwaran H (2017) Random forest missing data algorithms. Stat Anal Data Min 10:363–377. https://doi.org/10.1002/sam.11348
Provost F (2000) Machine learning from imbalanced data sets 101 extended abstract. In: Mach Learn 3
Team RC (2016) R Core Team R. R A Lang. Environ. Stat. Comput. R Found. Strat Comput. http://www.R-project.org
Moons KG, Altman DG, Reitsma JB, Ioannidis JP, Macaskill P, Steyerberg EW, Vickers AJ, Ransohoff DF, Collins GS (2015) Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med 162:W1–73. https://doi.org/10.7326/M14-0698
Scheer JK, Osorio JA, Smith JS, Schwab F, Hart R, Hostin R, Lafage V, Jain A, Burton DC, Bess S, Ailon T, Protopsaltis TS, Klineberg EO, Shaffrey CI, Ames CP (2018) Development of a preoperative predictive model for reaching the Oswestry Disability Index minimal clinically important difference for adult spinal deformity patients. Spine Deformity 6(5):593–599. https://doi.org/10.1016/j.jspd.2018.02.010
Scheer JK, Osorio JA, Smith JS, Schwab F, Lafage V, Hart RA, Bess S, Line B, Diebo BG, Protopsaltis TS, Jain A, Ailon T, Burton DC, Shaffrey CI, Klineberg E, Ames CP, International Spine Study G (2016) Development of validated computer-based preoperative predictive model for proximal junction failure (PJF) or clinically significant PJK with 86% accuracy based on 510 ASD patients with 2-year follow-up. Spine (Phila Pa 1976) 41:E1328–E1335. https://doi.org/10.1097/brs.0000000000001598
Scheer JK, Smith JS, Schwab F, Lafage V, Shaffrey CI, Bess S, Daniels AH, Hart RA, Protopsaltis TS, Mundis GM Jr, Sciubba DM, Ailon T, Burton DC, Klineberg E, Ames CP, International Spine Study G (2017) Development of a preoperative predictive model for major complications following adult spinal deformity surgery. J Neurosurg Spine 26:736–743. https://doi.org/10.3171/2016.10.spine16197
Pellise F, Vila-Casademunt A, Nunez-Pereira S, Domingo-Sabat M, Bago J, Vidal X, Alanay A, Acaroglu E, Kleinstuck F, Obeid I, Perez-Grueso FJS, Lafage V, Bess S, Ames C, Mannion AF, European Spine Study G (2018) The Adult Deformity Surgery Complexity Index (ADSCI): a valid tool to quantify the complexity of posterior adult spinal deformity surgery and predict postoperative complications. Spine J 18:216–225. https://doi.org/10.1016/j.spinee.2017.06.042
Wilke A, Mata R (2012) Cognitive bias. In: Encyclopedia of human behavior, pp 531–535
Funding
The International Spine Study Group Foundation receives funding support from DePuy Synthes, K2M, NuVasive, Orthofix and Zimmer Biomet. The European Spine Study Group receives funding support from DePuy Synthes and Medtronic. Additional support was provided through Project PI16/01283, funded by Instituto de Salud Carlos III and co-funded by European Union (ERDF/ESF).
Author information
Authors and Affiliations
Consortia
Corresponding author
Ethics declarations
Conflict of interest
Dr. Ames reports personal fees from DePuy Synthes, personal fees from Stryker, personal fees from Biomet Spine, personal fees from NuVasive, personal fees from Next Orthosurgical, personal fees from DePuy Synthes, personal fees from Medtronic, personal fees from Stryker, personal fees from Medicrea, personal fees from K2M, personal fees from UCSF, outside the submitted work. Dr. Smith reports grants from DePuy Synthes/ISSG, during the conduct of the study; personal fees from Zimmer Biomet, personal fees from NuVasive, personal fees from K2M, personal fees from AlloSource, from Cerapedics, grants from NREF, grants from AOSpine, from DePuy Synthes/ISSG, outside the submitted work. Dr. Pellisé reports grants from DePuy Synthes Spine, grants from Fondo de Investigaciones Sanitarias, during the conduct of the study; personal fees from DePuy Synthes Spine, grants from Medtronic, grants from Zimmer Biomet, outside the submitted work. Dr. Kelly reports grants from AOSpine, grants from DePuy Synthes, grants from DePuy Synthes, outside the submitted work. Dr. Gum reports grants from DePuy Synthes Spine, personal fees from Acuity, personal fees from Alphatec Spine, personal fees from DePuy Synthes, personal fees from K2M, personal fees from Medtronic, personal fees from NuVasive, personal fees from Stryker Spine, outside the submitted work. Dr. Alanay reports grants from DePuy Synthes, during the conduct of the study; grants from DePuy Synthes, grants from outside the submitted work. Dr. Acaroglu reports grants from DePuy Synthes, during the conduct of the study; grants from Medtronic, personal fees from AOSpine, outside the submitted work. Dr. Sánchez Pérez-Grueso reports grants and other from DePuy Synthes, other from K2M, outside the submitted work. Dr. Kleinstueck reports grants from DePuy Synthes, during the conduct of the study. Dr. Obeid reports grants from DePuy Synthes, during the conduct of the study; personal fees from DePuy Synthes, personal fees from Medtronic, personal fees from Alphatecspine, personal fees from Spineart, personal fees from Clariance, outside the submitted work. Dr. Vila-Casademunt has nothing to disclose. Mr. Shaffrey has nothing to disclose. Dr. Burton reports grants, personal fees and other from DePuy Spine, non-financial support from International Spine Study Group, non-financial support from Scoliosis Research Society, non-financial support from University of Kansas Physicians, other from Bioventus, other from Pfizer, outside the submitted work. Dr. Lafage reports grants from SRS, NASS, grants from DePuy Spine, grants from NuVasive, grants from Stryker, grants from K2M, personal fees from DePuy Spine, personal fees from AO Spine, personal fees from K2M, outside the submitted work. Dr. Schwab reports grants from DePuy Spine, grants from Stryker, grants from K2M, grants from NuVasive, personal fees from Medicrea, personal fees from Zimmer Biomet, personal fees from NuVasive, personal fees from K2M, personal fees from MSD, other from Nemaris INC, outside the submitted work. Dr. Shaffrey reports grants from ISSG Foundation, during the conduct of the study; personal fees from Medtronic, personal fees from NuVasive, personal fees from Zimmer Biomet, outside the submitted work. Dr. Bess reports grants from DePuy Synthes Spine, grants from K2 Medical, during the conduct of the study; grants from NuVasive, grants from Medtronic, grants from Stryker Spine, grants from Biomet Spine, grants from Orthofix, personal fees from K2 Medical, outside the submitted work. Dr. Serra-Burriel has nothing to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
IRB approval obtained through each of the member sites contributing cases.
Electronic supplementary material
Below is the link to the electronic supplementary material.
586_2019_6079_MOESM2_ESM.tif
Graphical summary of the accuracy and kappa for five-class classification of each individual answer of the SRS-22R based on two assessed baseline time horizons, preoperatively and postoperatively: (A) baseline to 1 year and (B) baseline to 2 years. The upper panels represent the preoperative baseline models (i.e., models only include information available prior to surgery), and the lower panels represent the postoperative baseline models (i.e., models include information available up to the point of hospital discharge following surgery). Average estimates are presented as dots, and 95% confidence intervals are presented as delimiters (TIFF 765 kb)
Rights and permissions
About this article
Cite this article
Ames, C.P., Smith, J.S., Pellisé, F. et al. Development of predictive models for all individual questions of SRS-22R after adult spinal deformity surgery: a step toward individualized medicine. Eur Spine J 28, 1998–2011 (2019). https://doi.org/10.1007/s00586-019-06079-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00586-019-06079-x