Feasibility and Assessment of a Machine Learning-Based Predictive Model of Outcome After Lumbar Decompression Surgery

Arthur André, Bruno Peyrou, Alexandre Carpentier, Jean-Jacques Vignaux, Arthur André, Bruno Peyrou, Alexandre Carpentier, Jean-Jacques Vignaux

Abstract

Study design: Retrospective study at a unique center.

Objective: The aim of this study is twofold, to develop a virtual patients model for lumbar decompression surgery and to evaluate the precision of an artificial neural network (ANN) model designed to accurately predict the clinical outcomes of lumbar decompression surgery.

Methods: We performed a retrospective study of complete Electronic Health Records (EHR) to identify potential unfavorable criteria for spine surgery (predictors). A cohort of synthetics EHR was created to classify patients by surgical success (green zone) or partial failure (orange zone) using an Artificial Neural Network which screens all the available predictors.

Results: In the actual cohort, we included 60 patients, with complete EHR allowing efficient analysis, 26 patients were in the orange zone (43.4%) and 34 were in the green zone (56.6%). The average positive criteria amount for actual patients was 8.62 for the green zone (SD+/- 3.09) and 10.92 for the orange zone (SD 3.38). The classifier (a neural network) was trained using 10,000 virtual patients and 2000 virtual patients were used for test purposes. The 12,000 virtual patients were generated from the 60 EHR, of which half were in the green zone and half in the orange zone. The model showed an accuracy of 72% and a ROC score of 0.78. The sensitivity was 0.885 and the specificity 0.59.

Conclusion: Our method can be used to predict a favorable patient to have lumbar decompression surgery. However, there is still a need to further develop its ability to analyze patients in the "failure of treatment" zone to offer precise management of patient health before spinal surgery.

Keywords: ROC curve; lumbar decompression surgery; machine learning; retrospective study; synthetic electronic medical record.

Conflict of interest statement

Declaration of Conflicting Interests: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Figures

Figure 1.
Figure 1.
Architecture of our artificial neural network.
Figure 2.
Figure 2.
Real patient distribution according the number of pre operative criteria and their outcome (green: success/orange: failure).
Figure 3.
Figure 3.
Statistical presence of criteria for each group orange / green (EHR).
Figure 4.
Figure 4.
Number of patient criteria for the 2 zones (syn-EHRS).
Figure 5.
Figure 5.
Statistical presence of criteria for each group (syn-EHRs).
Figure 6.
Figure 6.
Training model evolution (Accuracy and loss / Number of epochs).
Figure 7.
Figure 7.
AUC of our ANN-models using EHRs and syn-EHRs.

References

    1. Weinstein JN, Tosteson TD, Lurie JD, et al. Surgical versus nonsurgical therapy for lumbar spinal stenosis. N Engl J Med. 2008;358(8):794–810.
    1. Lurie JD, Tosteson TD, Tosteson A, et al. Long-term outcomes of lumbar spinal stenosis: eight-year results of the Spine Patient Outcomes Research Trial (SPORT). Spine (Phila Pa 1976). 2015;40(2):63–76.
    1. Weinstein JN, Lurie JD, Tosteson TD, et al. Surgical versus nonsurgical treatment for lumbar degenerative spondylolisthesis. N Engl J Med. 2007;356(22):2257–2270.
    1. Bailey CS, Rasoulinejad P, Taylor D, et al. Surgery versus conservative care for persistent sciatica lasting 4 to 12 months. N Engl J Med. 2020;382(12):1093–1102.
    1. McGirt MJ, Bydon M, Archer KR, et al. An analysis from the Quality Outcomes Database, Part 1. Disability, quality of life, and pain outcomes following lumbar spine surgery: predicting likely individual patient outcomes for shared decision-making. J Neurosurg Spine. 2017;27(4):357–369.
    1. Nasser R, Yadla S, Maltenfort MG, et al. Complications in spine surgery. J Neurosurg Spine. 2010;13(2):144–157.
    1. Yeramaneni S, Robinson C, Hostin R. Impact of spine surgery complications on costs associated with management of adult spinal deformity. Curr Rev Musculoskelet Med. 2016;9(3):327–332.
    1. Kalakoti P, Hendrickson NR, Bedard NA, Pugely AJ. Opioid utilization following lumbar arthrodesis: trends and factors associated with long-term use. Spine (Phila Pa 1976). 2018;43(17):1208–1216.
    1. Austevoll IM, Gjestad R, Grotle M, et al. Follow-up score, change score or percentage change score for determining clinical important outcome following surgery? An observational study from the Norwegian Registry for Spine Surgery evaluating patient reported outcome measures in lumbar spinal stenosis and lumbar degenerative spondylolisthesis. BMC Musculoskelet Disord. 2019;20(1):31.
    1. Katz JN, Stucki G, Lipson SJ, Fossel AH, Grobler LJ, Weinstein JN. Predictors of surgical outcome in degenerative lumbar spinal stenosis. Spine. 1999;24(21):2229.
    1. Hägg O, Fritzell P, Ekselius L, Nordwall A.Predictors of outcome in fusion surgery for chronic low back pain. A report from the Swedish Lumbar Spine study. Eur Spine J. 2003;12(1):22–33.
    1. Kohlboeck G, Greimel KV, Piotrowski WP, et al. Prognosis of multifactorial outcome in lumbar discectomy: a prospective longitudinal study investigating patients with disc prolapse. Clin J Pain. 2004;20(6):455–461.
    1. Trief PM, Ploutz-Snyder R, Fredrickson BE. Emotional health predicts pain and function after fusion: a prospective multicenter study. Spine. 2006;31(7):823–830.
    1. Slover J, Abdu WA, Hanscom B, Weinstein JN. The impact of comorbidities on the change in Short-Form 36 and Oswestry scores following lumbar spine surgery. Spine. 2006;31(17):1974–1980.
    1. Braybrooke J, Ahn H, Gallant A, et al. The impact of surgical wait time on patient-based outcomes in posterior lumbar spinal surgery. Eur Spine J. 2007;16(11):1832–1839.
    1. Mannion AF, Elfering A, Staerkle R, et al. Predictors of multidimensional outcome after spinal surgery. Eur Spine J. 2007;16(6):777–786.
    1. Park P, Upadhyaya C, Garton HJL, Foley KT. The impact of minimally invasive spine surgery on perioperative complications in overweight or obese patients. Neurosurg. 2008;62(3):693–699.
    1. Garcia RM, Messerschmitt PJ, Furey CG, Bohlman HH, Cassinelli EH. Weight loss in overweight and obese patients following successful lumbar decompression. JBJS. 2008;90(4):742–747.
    1. Vaidya R, Carp J, Bartol S, Ouellette N, Lee S, Sethi A. Lumbar spine fusion in obese and morbidly obese patients. Spine. 2009;34(5):495–500.
    1. Chen S, Anderson MV, Cheng WK, Wongworawat MD. Diabetes associated with increased surgical site infections in spinal arthrodesis. Clin Orthop Relat Res. 2009;467(7):1670–1673.
    1. Abbott AD, Tyni-Lenné R, Hedlund R. Leg pain and psychological variables predict outcome 2–3 years after lumbar fusion surgery. Eur Spine J. 2011;20(10):1626–1634.
    1. Senker W, Meznik C, Avian A, Berghold A. Perioperative morbidity and complications in minimal access surgery techniques in obese patients with degenerative lumbar disease. Eur Spine J. 2011;20(7):1182–1187.
    1. Chaichana KL, Mukherjee D, Adogwa O, Cheng JS, McGirt MJ. Correlation of preoperative depression and somatic perception scales with postoperative disability and quality of life after lumbar discectomy. J Neurosurg Spine. 2011;14(2):261–267.
    1. Sinikallio S, Aalto T, Airaksinen O, Lehto SM, Kröger H, Viinamäki H. Depression is associated with a poorer outcome of lumbar spinal stenosis surgery: a two-year prospective follow-up study. Spine. 2011;36(8):677–682.
    1. Kalanithi PA, Arrigo R, Boakye M. Morbid obesity increases cost and complication rates in spinal arthrodesis. Spine. 2012;37(11):982–988.
    1. Sørlie A, Moholdt V, Kvistad KA, et al. Modic type I changes and recovery of back pain after lumbar microdiscectomy. European Spine J., 2012;21(11): 2252–2258.
    1. Pakarinen M, Vanhanen S, Sinikallio S, et al. Depressive burden is associated with a poorer surgical outcome among lumbar spinal stenosis patients: a 5-year follow-up study. Spine J. 2014;14(10):2392–2396.
    1. Hellum C, Johnsen LG, Gjertsen Ø, et al. Predictors of outcome after surgery with disc prosthesis and rehabilitation in patients with chronic low back pain and degenerative disc: 2-year follow-up. Eur Spine J. 2012;21(4):681–690.
    1. Gaudelli C, Thomas K. Obesity and early reoperation rate after elective lumbar spine surgery: a population-based study. Evid Based Spine Care J. 2012;3(02):11–16.
    1. Mehta AI, Babu R, Karikari IO, et al. 2012 Young investigator award winner: the distribution of body mass as a significant risk factor for lumbar spinal fusion postoperative infections. Spine. 2012;37(19):1652–1656.
    1. Sharma A, Muir R, Johnston R, Carter E, Bowden G, Wilson-MacDonald J. Diabetes is predictive of longer hospital stay and increased rate of Clavien complications in spinal surgery in the UK. Ann R Coll Surg Engl. 2013;95(4):275–279.
    1. Takahashi S, Suzuki A, Toyoda H, et al. Characteristics of diabetes associated with poor improvements in clinical outcomes after lumbar spine surgery. Spine. 2013;38(6):516–522.
    1. Bekelis K, Desai A, Bakhoum SF, Missios S. A predictive model of complications after spine surgery: the National Surgical Quality Improvement Program (NSQIP) 2005–2010. Spine J. 2014;14(7):1247–1255.
    1. Lee D, Armaghani S, Archer KR, et al. Preoperative opioid use as a predictor of adverse postoperative self-reported outcomes in patients undergoing spine surgery. JBJS. 2014;96(11):e89.
    1. Kim JS, Arvind V, Oermann EK, et al. Predicting surgical complications in patients undergoing elective adult spinal deformity procedures using machine learning. Spine Deform. 2018;6(6):762–770.
    1. Coronado RA, George SZ, Devin CJ, Wegener ST, Archer KR. Pain sensitivity and pain catastrophizing are associated with persistent pain and disability after lumbar spine surgery. Arch Phys Med Rehabil. 2015;96(10):1763–1770.
    1. McGirt MJ, Sivaganesan A, Asher AL, Devin CJ. Prediction model for outcome after low-back surgery: individualized likelihood of complication, hospital readmission, return to work, and 12-month improvement in functional disability. Neurosurg Focus. 2015;39(6):E13.
    1. Anderson JT, Haas AR, Percy R, Woods ST, Ahn UM, Ahn NU. Chronic opioid therapy after lumbar fusion surgery for degenerative disc disease in a workers’ compensation setting. Spine (Phila Pa 1976). 2015;40(22):1775–1784.
    1. Chotai S, Sivaganesan A, Parker SL, McGirt MJ, Devin CJ. Patient-specific factors associated with dissatisfaction after elective surgery for degenerative spine diseases. Neurosurg. 2015;77(2):157–163.
    1. Schöller K, Steingrüber T, Stein M, et al. Microsurgical unilateral laminotomy for decompression of lumbar spinal stenosis: long-term results and predictive factors. Acta Neurochir. 2016;158(6):1103–1113.
    1. Archer KR, Devin CJ, Vanston SW, et al. Cognitive-behavioral–based physical therapy for patients with chronic pain undergoing lumbar spine surgery: a randomized controlled trial. J Pain. 2016;17(1):76–89.
    1. Asher AL, Devin CJ, McCutcheon B, et al. Patient characteristics of smokers undergoing lumbar spine surgery: an analysis from the Quality Outcomes Database. J Neurosurg Spine. 2017;27(6):661–669.
    1. Mummaneni PV, Bisson EF, Kerezoudis P, et al. Minimally invasive versus open fusion for grade I degenerative lumbar spondylolisthesis: analysis of the Quality Outcomes Database. Neurosurg Focus. 2017;43(2):E11.
    1. Crawford CH, Carreon LY, Bydon M, Asher AL, Glassman SD. Impact of preoperative diagnosis on patient satisfaction following lumbar spine surgery. J Neurosurg Spine. 2017;26(6):709–715.
    1. Suri P, Pearson AM, Zhao W, et al. Pain recurrence after discectomy for symptomatic lumbar disc herniation. Spine. 2017;42(10):755.
    1. Sharma M, Ugiliweneza B, Aljuboori Z, Nuño MA, Drazin D, Boakye M. Factors predicting opioid dependence in patients undergoing surgery for degenerative spondylolisthesis: analysis from the MarketScan databases. J Neurosurg Spine. 2018;29(3):271–278.
    1. Dunn LK, Durieux ME, Fernández LG, et al. Influence of catastrophizing, anxiety, and depression on in-hospital opioid consumption, pain, and quality of recovery after adult spine surgery. J Neurosurg Spine. 2018;28(1):119–126.
    1. Chan AK, Bisson EF, Bydon M, et al. Laminectomy alone versus fusion for grade 1 lumbar spondylolisthesis in 426 patients from the prospective Quality Outcomes Database. J Neurosurg Spine. 2018;30(2):234–241.
    1. O’Donnell JA, Anderson JT, Haas AR, et al. Preoperative opioid use is a predictor of poor return to work in workers’ compensation patients after lumbar diskectomy. Spine. 2018;43(8):594–602.
    1. Khor S, Lavallee D, Cizik AM, et al. Development and validation of a prediction model for pain and functional outcomes after lumbar spine surgery. JAMA Surg. 2018;153(7):634–642.
    1. Dobran M, Nasi D, Paracino R, et al. Analysis of risk factors and postoperative predictors for recurrent lumbar disc herniation. Surg Neurol Int. 2019;10:36.
    1. Staub LP, Aghayev E, Skrivankova V, Lord SJ, Haschtmann D, Mannion AF. Development and temporal validation of a prognostic model for 1-year clinical outcome after decompression surgery for lumbar disc herniation. Eur Spine J. 2020;29(7):1742–1751.
    1. Mauro D, Nasi D, Paracino R, et al. The relationship between preoperative predictive factors for clinical outcome in patients operated for lumbar spinal stenosis by decompressive laminectomy. Surg Neurol Int. 2020;11:27.
    1. Rudolfsen JH, Solberg TK, Ingebrigtsen T, Olsen JA. Associations between utilization rates and patients’ health: a study of spine surgery and patient-reported outcomes (EQ-5D and ODI). BMC Health Serv Res. 2020;20(1):1–8.
    1. Asher AL, Devin CJ, Archer KR, et al. An analysis from the quality outcomes database, part 2. Predictive model for return to work after elective surgery for lumbar degenerative disease. J Neurosurg Spine. 2017;27(4):370–381.
    1. Azimi P, Mohammadi HR, Benzel EC, Shahzadi S, Azhari S. Use of artificial neural networks to decision making in patients with lumbar spinal canal stenosis. J Neurosurg Sci. 2017;61(6):603–611.
    1. Azimi P, Mohammadi HR, Benzel EC, Shahzadi S, Azhari S. Use of artificial neural networks to predict recurrent lumbar disk herniation. J Spinal Disord Tech. 2015;28(3):E161–165.
    1. André A. The information technology revolution in health care. In: Arthur A, ed. Digital Medicine. Springer International Publishing; 2019:1–7.
    1. Dillavou ED, Sun Z, Peiris P, Huang E, Benrashid E, Chang B.IP145. Deep learning-based risk model for best management of closed surgical incisions following vascular surgery. J Vasc Surg. 2019;69(6):e149–e150.
    1. Shahid N, Rappon T, Berta W. Applications of artificial neural networks in health care organizational decision-making: a scoping review. PLoS One. 2019;14(2):e0212356.
    1. Mandal I. Developing new machine learning ensembles for quality spine diagnosis. Knowl-Based Syst. 2015;73(1):298–310.
    1. Iderberg H, Willers C, Borgström F, et al. Predicting clinical outcome and length of sick leave after surgery for lumbar spinal stenosis in Sweden: a multi-register evaluation. Eur Spine J. 2019;28(6):1423–1432.
    1. Karhade AV, Ogink PT, Thio QCBS, et al. Development of machine learning algorithms for prediction of prolonged opioid prescription after surgery for lumbar disc herniation. Spine J. 2019;19(11):1764–1771.
    1. Siccoli A, Marlies P, Schröder ML, Staartjes VE. Machine learning–based preoperative predictive analytics for lumbar spinal stenosis. Neurosurg Focus. 2019;46(5):E5.
    1. Kalagara S, Eltorai AEM, Durand WM, DePasse JM, Daniels AH. Machine learning modeling for predicting hospital readmission following lumbar laminectomy. J Neurosurg Spine. 2018;30(3):344–352.
    1. Han SS, Azad TD, Suarez PA, Ratliff JK. A machine learning approach for predictive models of adverse events following spine surgery. Spine J. 2019;19(11):1772–1781.
    1. Azimi P, Benzel EC, Shahzadi S, Azhari S, Mohammadi HR. Use of artificial neural networks to predict surgical satisfaction in patients with lumbar spinal canal stenosis. J Neurosurg Spine. 2014;20(3):300–305.
    1. Azimi P, Benzel EC, Shahzadi S, Azhari S, Zali AR. Prediction of successful surgery outcome in lumbar disc herniation based on artificial neural networks. Global Spine J. 2014;4(1_suppl):s–0034.
    1. Azimi P, Mohammadi HR, Benzel EC, Shahzadi S, Azhari S. Use of artificial neural networks to predict recurrent lumbar disk herniation. Clin Spine Surg. 2015;28(3):E161–E165.
    1. Ratliff JK, Balise R, Veeravagu A, et al. Predicting occurrence of spine surgery complications using “big data” modeling of an administrative claims database. JBJS. 2016;98(10):824–834.
    1. Oh T, Scheer JK, Smith JS, et al. Potential of predictive computer models for preoperative patient selection to enhance overall quality-adjusted life years gained at 2-year follow-up: a simulation in 234 patients with adult spinal deformity. Neurosurg Focus. 2017;43(6):E2.
    1. Scheer JK, Smith JS, Schwab F, et al. Development of a preoperative predictive model for major complications following adult spinal deformity surgery. J Neurosurg Spine. 2017;26(6):736–743.
    1. Staartjes VE, Marlies P, Vandertop WP, Schröder ML. Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar discectomy: feasibility of center-specific modeling. Spine J. 2019;19(5):853–861.
    1. Karhade AV, Ogink P, Thio Q, 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(5):E6.
    1. Kuo C-Y, Yu L-C, Chen H-C, Chan C-L. Comparison of models for the prediction of medical costs of spinal fusion in Taiwan Diagnosis-Related Groups by machine learning algorithms. Healthc Inform Res. 2018;24(1):29–37.
    1. 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;1–11.
    1. Shah AA, Karhade AV, Bono CM, Harris MB, Nelson SB, Schwab JH. Development of a machine learning algorithm for prediction of failure of nonoperative management in spinal epidural abscess. Spine J. 2019;19(10):1657–1665.
    1. Karhade AV, Shah AA, Bono CM, et al. Development of machine learning algorithms for prediction of mortality in spinal epidural abscess. Spine J. 2019;19(12):1950–1959.
    1. 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. 2019;1(aop):1–8.
    1. Nelson A, Herron D, Rees G, Nachev P. Predicting scheduled hospital attendance with artificial intelligence. NPJ Digit Med. 2019;2(1):1–7.
    1. Hopkins BS, Mazmudar A, Driscoll C, et al. Using artificial intelligence (AI) to predict postoperative surgical site infection: a retrospective cohort of 4046 posterior spinal fusions. Clin Neurol Neurosurg. 2020;192:105718.
    1. Yoon J, Drumright LN, Van Der Schaar M. Anonymization through data synthesis using Generative Adversarial Networks (ADS-GAN). IEEE Journal of Biomedical and Health Informatics; 2020.
    1. Baowaly MK, Lin C-C, Liu C-L, Chen K-T. Synthesizing electronic health records using improved generative adversarial networks. J Am Med Inform Assoc. 2019;26(3):228–241.
    1. Buczak AL, Babin S, Moniz L. Data-driven approach for creating synthetic electronic medical records. BMC Med Inform Decis Mak. 2010;10(1):59.
    1. Yale A, Dash S, Dutta R. Privacy preserving synthetic health data. F1000Res. 2019;8:724.
    1. Walonoski J, Kramer M, Nichols J, et al. Synthea: an approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record. J Am Med Inform Assoc. 2017;25(3):230–238.
    1. He H, Bai Y, Garcia EA, Li S. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, 1-8 June 2008. IEEE; 2008.
    1. Teutonico D, Musuamba F, Maas HJ, et al. Generating virtual patients by multivariate and discrete re-sampling techniques. Pharm Res. 2015;32(10):3228–3237.
    1. McLachlan S, Dube K, Gallagher T.Using the caremap with health incidents statistics for generating the realistic synthetic electronic healthcare record. In: 2016 IEEE International Conference on Healthcare Informatics (ICHI), Chicago, IL, 4-7 October 2016. IEEE; 2016.
    1. Kim JS, Merrill RK, Arvind V, et al. Examining the ability of artificial neural networks machine learning models to accurately predict complications following posterior lumbar spine fusion. Spine (Phila Pa 1976). 2018;43(12):853–860.
    1. Pollack AH, Simon TD, Snyder J, Pratt W. Creating synthetic patient data to support the design and evaluation of novel health information technology. J Biomed Inform. 2019;95:103201.
    1. Lønne G, Fritzell P, Hägg O, et al. Lumbar spinal stenosis: comparison of surgical practice variation and clinical outcome in three national spine registries. Spine J. 2019;19(1):41–49.
    1. Hestness J, Narang S, Ardalani N, et al. Deep learning scaling is predictable, empirically. arXiv. arXiv preprint arXiv:171200409 . 2017.
    1. Malik AT, Khan SN. Predictive modeling in spine surgery. Ann Transl Med. 2019;7(suppl 5):S173.
    1. Hills JM, Pennings JS, Archer KR, et al. Preoperative opioids and 1-year patient-reported outcomes after spine surgery. Spine (Phila Pa 1976). 2019;44(12):887–895.
    1. Oleisky ER, Pennings JS, Hills J, et al. Comparing different chronic preoperative opioid use definitions on outcomes after spine surgery. Spine J. 2019;19(6):984–994.

Source: PubMed

Sponsorit ja yhteistyökumppanit

Sairaudet

Huumeiden interventiot

3
Tilaa