Machine learning applications in adult spinal deformity corrective surgery: a narrative review

Abstract

Adult spinal deformity (ASD) poses significant challenges in spinal surgery, requiring precise planning and execution for successful correction. Additionally, optimization of outcomes and reducing the high complication rates of ASD surgeries are additional challenges facing spinal deformity surgeons. The advent of machine learning (ML) has revolutionized various aspects of healthcare, including spinal surgery. This review provides a comprehensive overview of the current state of ML applications in spinal deformity corrective surgery, highlighting its potential benefits and challenges.

Keywords

Machine learning / adult spinal deformity / predictive modeling / artificial intelligence

References

[1] Schwab F,Gamez L.Adult scoliosis: prevalence, SF-36, and nutritional parameters in an elderly volunteer population.Spine2005;30:1082-5

[2] Pellisé F, Vila-Casademunt A, Núñez-Pereira S, et al; European Spine Study Group, International Spine Study Group. Surgeons’ risk perception in ASD surgery: the value of objective risk assessment on decision making and patient counselling.Eur Spine J2022;31:1174-83

[3] Joshi RS,Scheer JK.State-of-the-art reviews predictive modeling in adult spinal deformity: applications of advanced analytics.Spine Deform2021;9:1223-39 PMCID:PMC8363545

[4] Akosman I,Lyons K.The emerging role of artificial intelligence in adult spinal deformity.Semin Spine Surg2022;34:100986

[5] Haselhuhn JJ,Grover P.Spine surgeon versus AI algorithm full-length radiographic measurements: a validation study of complex adult spinal deformity patients.Spine Deform2024;12:755-61

[6] Harake ES,Jiang C.Development and validation of an artificial intelligence model to accurately predict spinopelvic parameters.J Neurosurg Spine2024;41:88-96

[7] Suri A,Kargilis D.Conquering the cobb angle: a deep learning algorithm for automated, hardware-invariant measurement of cobb angle on radiographs in patients with scoliosis.Radiol Artif Intell2023;5:e220158 PMCID:PMC10388214

[8] Galbusera F,Wilke HJ.Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach.Eur Spine J2019;28:951-60

[9] Faulks CR,Munday NR,Malham GM.Patient-specific spinal rods in adult spinal deformity surgery reduce proximal junctional failure: a review of patient outcomes and surgical technique in a prospective observational cohort.J Spine Surg2023;9:409-21 PMCID:PMC10772658

[10] Picton B,Liang J.Patient-specific rods in adult spinal deformity: a systematic review.Spine Deform2024;12:577-85 PMCID:PMC11068670

[11] Lee NJ,Boddapati V.Can machine learning accurately predict postoperative compensation for the uninstrumented thoracic spine and pelvis after fusion from the lower thoracic spine to the sacrum?.Global Spine J2022;12:559-66 PMCID:PMC9109562

[12] Arora A,Cummins DD,Clark AJ.Predictive models to assess risk of extended length of stay in adults with spinal deformity and lumbar degenerative pathology: development and internal validation.Spine J2023;23:457-66

[13] Li W,Zhou X.Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study.J Orthop Surg Res2024;19:112 PMCID:PMC10838003

[14] Arora A,Jain D.Predictive models for length of stay and discharge disposition in elective spine surgery: development, validation, and comparison to the ACS NSQIP risk calculator.Spine2023;48:E1-13 PMCID:PMC9772082

[15] Lafage R,Alshabab BS.Predictive model for selection of upper treated vertebra using a machine learning approach.World Neurosurg2021;146:e225-32

[16] Mohanty S, Hassan FM, Lenke LG, et al; International Spine Study Group. Machine learning clustering of adult spinal deformity patients identifies four prognostic phenotypes: a multicenter prospective cohort analysis with single surgeon external validation.Spine J2024;24:1095-108

[17] Ames CP, Smith JS, Pellisé F, et al; European Spine Study Group; International Spine Study Group. Development of predictive models for all individual questions of SRS-22R after adult spinal deformity surgery: a step toward individualized medicine.Eur Spine J2019;28:1998-2011

[18] Mekhael E,Saliby RM.Functional assessment using 3D movement analysis can better predict health-related quality of life outcomes in patients with adult spinal deformity: a machine learning approach.Front Surg2023;10:1166734 PMCID:PMC10189154

[19] Nassim N,Rachkidi RE.Global Sagittal Angle and T9-tilt seem to be the most clinically and functionally relevant global alignment parameters in patients with Adult Spinal Deformity.Brain Spine2024;4:102805 PMCID:PMC11033086

[20] Diebo BG,Challier V.Global sagittal axis: a step toward full-body assessment of sagittal plane deformity in the human body.J Neurosurg Spine2016;25:494-9

[21] Legaye J.Sagittal plane alignment of the spine and gravity: a radiological and clinical evaluation.Acta Orthop Belg2005;71:213-20

[22] Williamson TK,Tretiakov P.Crossing the bridge from degeneration to deformity: when does sagittal correction impact outcomes in adult spinal deformity surgery?.Spine2023;48:E25-32

[23] Johnson GW,Ali MA.Artificial intelligence to preoperatively predict proximal junction kyphosis following adult spinal deformity surgery: soft tissue imaging may be necessary for accurate models.Spine2023;48:1688-95 PMCID:PMC11101214

[24] Scheer JK, Oh T, Smith JS, et al; International Spine Study Group. Development of a validated computer-based preoperative predictive model for pseudarthrosis with 91% accuracy in 336 adult spinal deformity patients.Neurosurg Focus2018;45:E11

[25] Burström G,Hoppenbrouwers J.Machine learning for automated 3-dimensional segmentation of the spine and suggested placement of pedicle screws based on intraoperative cone-beam computer tomography.J Neurosurg Spine2019;31:147-54

[26] Siemionow KB,Foy MP,Luciano CJ.Autonomous lumbar spine pedicle screw planning using machine learning: A validation study.J Craniovertebr Junction Spine2021;12:223-7 PMCID:PMC8501821

[27] Wilson JP Jr,Kandregula S,Guthikonda B.Proposed applications of machine learning to intraoperative neuromonitoring during spine surgeries.Neurosci Inf2023;3:100143

[28] Pierce KE,Naessig S.Validation of the ACS-NSQIP risk calculator: a machine-learning risk tool for predicting complications and mortality following adult spinal deformity corrective surgery.Int J Spine Surg2021;15:1210-6 PMCID:PMC9468937

[29] Kim JS,Oermann EK.Predicting surgical complications in patients undergoing elective adult spinal deformity procedures using machine learning.Spine Deform2018;6:762-70

[30] Raman T,Varlotta C,Errico TJ.Decision tree-based modelling for identification of predictors of blood loss and transfusion requirement after adult spinal deformity surgery.Int J Spine Surg2020;14:87-95 PMCID:PMC7043811

[31] De la Garza Ramos R,Ryvlin J.An artificial neural network model for the prediction of perioperative blood transfusion in adult spinal deformity surgery.J Clin Med2022;11:4436 PMCID:PMC9369471

[32] Durand WM,Daniels AH.Predictive modeling for blood transfusion after adult spinal deformity surgery: a tree-based machine learning approach.Spine2018;43:1058-66

[33] Ames CP, Smith JS, Pellisé F, et al; European Spine Study Group, International Spine Study Group. Development of deployable predictive models for minimal clinically important difference achievement across the commonly used health-related quality of life instruments in adult spinal deformity surgery.Spine2019;44:1144-53

[34] Patel AV,Schwartz JT.Emerging technologies in the treatment of adult spinal deformity.Neurospine2021;18:417-27 PMCID:PMC8497255

[35] Löchel J,Dreischarf M.Deep learning algorithm for fully automated measurement of sagittal balance in adult spinal deformity.Eur Spine J2024;Online ahead of print:

[36] Hopkins BS,Driscoll C.Using artificial intelligence (AI) to predict postoperative surgical site infection: a retrospective cohort of 4046 posterior spinal fusions.Clin Neurol Neurosurg2020;192:105718

[37] Schonfeld E,Shah A.Evaluating computer vision, large language, and genome-wide association models in a limited sized patient cohort for pre-operative risk stratification in adult spinal deformity surgery.J Clin Med2024;13:656 PMCID:PMC10856542

[38] Jain D,Burch S,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.Spine2020;45:1151-60

[39] Arora A,Cummins DD.Development and internal validation of predictive models to assess risk of post-acute care facility discharge in adults undergoing multi-level instrumented fusions for lumbar degenerative pathology and spinal deformity.Spine Deform2023;11:163-73 PMCID:PMC9768002

[40] Lee CH,Oh JK.Development and validation of an online calculator to predict proximal junctional kyphosis after adult spinal deformity surgery using machine learning.Neurospine2023;20:1272-80 PMCID:PMC10762414

[41] Noh SH,Park GE.Predicting mechanical complications after adult spinal deformity operation using a machine learning based on modified global alignment and proportion scoring with body mass index and bone mineral density.Neurospine2023;20:265-74 PMCID:PMC10080453

[42] Balaban B,Yucekul A.Building clinically actionable models for predicting mechanical complications in postoperatively well-aligned adult spinal deformity patients using XGBoost algorithm.Inform Med Unlocked2023;37:101191

[43] Lovecchio F,Sheikh Alshabab B.Can discharge radiographs predict junctional complications? A decision tree analysis.Global Spine J2024;14:970-7 PMCID:PMC11192123

[44] Ryu SJ,Ha Y.Risk factors for unplanned reoperation after corrective surgery for adult spinal deformity.Bone Joint Res2023;12:245-55 PMCID:PMC10067324

[45] Ames CP,Gum JL.Utilization of predictive modeling to determine episode of care costs and to accurately identify catastrophic cost nonwarranty outlier patients in adult spinal deformity surgery: a step toward bundled payments and risk sharing.Spine2020;45:E252-65

[46] Wondra JP 2nd,Greenberg J.Validation of adult spinal deformity surgical outcome prediction tools in adult symptomatic lumbar scoliosis.Spine2023;48:21-8 PMCID:PMC9771887

[47] Yagi M,Fujita N,Ebata S.Revolutionizing spinal care: current applications and future directions of artificial intelligence and machine learning.J Clin Med2023;12:4188 PMCID:PMC10342311

[48] Haddad S,Raganato R.Future data points to implement in adult spinal deformity assessment for artificial intelligence modeling prediction: the importance of the biological dimension.Int J Spine Surg2023;17:S34-44 PMCID:PMC10318909

[49] Choy W,Scheer JK,Ames CP.Biomarkers in adult spinal deformity surgery.Semin Spine Surg2023;35:101058

[50] Galbusera F,Samartzis D.Commentary on “Predicting mechanical complications after adult spinal deformity operation using a machine learning based on modified global alignment and proportion scoring with body mass index and bone mineral density”.Neurospine2023;20:275-7 PMCID:PMC10080439