Abstract
Purpose
This paper aims to provide an overview of the possibility regarding the artificial intelligence application in orthopaedics to predict dislocation with a calculator according to the type of implant (hemiarthroplasty, standard total hip arthroplasty, dual mobility, constrained cups) after primary arthroplasty.
Material and methods
Among 75 results for primary arthroplasties, 26 articles were reviews on dislocation after hemiarthroplasty, 40 after standard total hip arthroplasty, seven about primary dual-mobility arthroplasty (DM THA), and two reviews about constrained implants. Although our search method for systematic reviews covers ten years (2012–2022), none for dual mobility was published before 2016, showing a recent explosion of original articles on this subject. A total of 1,069,565 implants and 26,488 dislocations in primary arthroplasties are included in these 75 reviews. We used a supervised learning model in which models assign objects to groups as input and artificial neural network (ANN) with nodes, hidden layers, and output layers. We considered only four implant types as the input layer. We considered the patient’s factors (indication for THA, demographics, spine surgery, and neurologic disease) as the second input values (hidden layer). We considered the implant position as the third input (hidden layer) property including head size, combined anteversion, or spinopelvic alignment. Surgery-related factors, approach, capsule repair, etc. were the fourth input values (hidden layer). The output was a post-operative dislocation or not within three months.
Results
The accuracy for predicting dislocation with this systematic review was 95%. Dislocation risk, based on the type of implant, was wide-ranging, from 0 to 3.9% (mean 0.31%) for the 3045 DM THA, from 0.2 to 1.2% (overall 0.91%) for the 457 constrained liners, from 1.76 to 4.2% (mean 2.1%) for 895,734 conventional total hip arthroplasties, and from 0.76 to 12.2% (mean 4.5%) for 170,329 hemiarthroplasties. In the conventional THA group, many factors increase the risk of dislocation according to the calculator, and only a few (big head, anterior approach) decrease the risk, but not very significantly. In the hemiarthroplasty group, many factors can increase the risk of dislocation until 30%, but none could decrease the risk. According to the calculator, the DM THA and the constrained liner markedly decreased the risk and were not affected by implant position, spine surgery, and spinopelvic position.
Conclusion
To our knowledge, this study is the first to yield an implant-specific dislocation risk calculator that incorporates the patient’s comorbidities, the position of components, and surgery factors affecting instability risk.
Similar content being viewed by others
Data availability
Available on reasonable request from PubMed.
Code availability
None.
References
Kunutsor SK, Barrett MC, Beswick AD, Judge A, Blom AW, Wylde V, et al. (2019) Risk factors for dislocation after primary total hip replacement: a systematic review and meta-analysis of 125 studies involving approximately five million hip replacements. Lancet Rheumatol;1:e111e21
Berry DJ, Von Knoch M, Schleck CD, Harmsen WS (2005) Effect of femoral head diameter and operative approach on risk of dislocation after primary total hip arthroplasty. J Bone Jt Surg - Ser A 87:2456–2463. https://doi.org/10.2106/JBJS.D.02860
Buckland AJ, Puvanesarajah V, Vigdorchik J, Schwarzkopf R, Jain A, Klineberg EO, Hart RA, Callaghan JJ, Hassanzadeh H (2017) Dislocation of a primary total hip arthroplasty is more common in patients with a lumbar spinal fusion. Bone Joint J 99-B(5):585–91
Abdel MP, von Roth P, Jennings MT, Hanssen AD, Pagnano MW (2016) What safe zone? The vast majority of dislocated THAs are within the Lewinnek safe zone for acetabular component position. Clin Orthop Relat Res 474(2):386–391. https://doi.org/10.1007/s11999-015-4432-5
Seagrave KG, Troelsen A, Malchau H et al (2017) Acetabular cup position and risk of dislocation in primary total hip arthroplasty: a systematic review of the literature. Acta Orthop 88:10. https://doi.org/10.1080/17453674.2016.1251255
Buckland AJ, Puvanesarajah V, Vigdorchik J et al (2017) Dislocation of a primary total hip arthroplasty is more common in patients with a lumbar spinal fusion. Bone and Joint Journal 99B:585–591. https://doi.org/10.1302/0301-620X.99B5.BJJ-2016-0657.R1
Vigdorchik JM, Sharma AK, Buckland AJ et al (2021) Otto Aufranc Award: a simple hip-spine classification for total hip arthroplasty: validation and a large multicentre series. Bone Joint J 103-B(7 Supple B):17–24. https://doi.org/10.1302/0301-620X.103B7
Wyles CC, Maradit-Kremers H, Larson DR, Lewallen DG, Taunton MJ, Trousdale RT, Pagnano MW, Berry DJ, Sierra RJ (2022) Creation of a total hip arthroplasty patient-specific dislocation risk calculator. J Bone Joint Surg Am 104(12):1068–1080. https://doi.org/10.2106/JBJS.21.01171
Danaei B, McPhee J (2022) Model-based acetabular cup orientation optimization based on minimizing the risk of edge-loading and implant impingement following total hip arthroplasty. J Biomech Eng. 144(11):111008. https://doi.org/10.1115/1.4054866
Tang H, Li Y, Zhou Y, Wang S, Zhao Y, Ma ZA (2022) Modeling study of a patient-specific safe zone for THA: calculation, validation, and key factors based on standing and sitting sagittal pelvic tilt. Clin Orthop Relat Res 480(1):191–205. https://doi.org/10.1097/CORR.0000000000001923
Mortazavi SMJ, Ghadimi E, Ardakani MV, Razzaghof M, Ghasemi MA, Nili A, Vafaei A, Moharrami A, Rasta S (2022) Risk factors of dislocation after total hip arthroplasty in patients with developmental dysplasia of the hip. Int Orthop 46(4):749–759. https://doi.org/10.1007/s00264-021-05294
Wu S, Roberts K, Datta S, Du J, Ji Z, Si Y et al (2020) Deep learning in clinical natural language processing: a methodical review. J Am Med Inf Assoc 27:457–470. https://doi.org/10.1093/jamia/ocz200
Fernandez A, Garcia S, Herrera F, Chawla NV (2018) SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J Art Intell Res 61(1):863–905. https://doi.org/10.1613/jair.1.11192
Lundberg SM, Lee S-I. A (2017) Unified approach to interpreting model predictions. NIPS; New York: Curran Associates;. pp. 4765–4774
Meng Y, Yang N, Qian Z, Zhang G (2020) What makes an online review more helpful: an interpretation framework using XGBoost and SHAP values. J Theor Appl Electron Res 16(3):466–490. https://doi.org/10.3390/jtaer16030029
Girard J, Kern G, Migaud H, Delaunay C, Ramdane N, Hamadouche M (2013) Société française de chirurgie orthopédique et traumatologique Primary total hip arthroplasty revision due to dislocation: prospective French multicenter study. Orthop Traumatol Surg Res 99(5):549–53. https://doi.org/10.1016/j.otsr.2013.03.026
Skoogh O, Tsikandylakis G, Mohaddes M, Nemes S, Odin D, Grant P, Rolfson O (2019) Contemporary posterior surgical approach in total hip replacement: still more reoperations due to dislocation compared with direct lateral approach? An observational study of the Swedish Hip Arthroplasty Register including 156,979 hips. Acta Orthop 90(5):411–416. https://doi.org/10.1080/17453674.2019.1610269
Jobory A, Kärrholm J, Hansson S, Åkesson K, Rogmark C (2021) Dislocation of hemiarthroplasty after hip fracture is common and the risk is increased with posterior approach: result from a national cohort of 25,678 individuals in the Swedish Hip Arthroplasty Register. Acta Orthop 92(4):413–418. https://doi.org/10.1080/17453674.2021.1906517
Blaizot A, Veettil SK, Saidoung P et al (2022) Using artificial intelligence methods for systematic review in health sciences: a systematic review. Research Synthesis Methods 13:353–362. https://doi.org/10.1002/jrsm.1553
van de Schoot R, de Bruin J, Schram R et al (2021) An open source machine learning framework for efficient and transparent systematic reviews. Nat Mach Intell 3:125–133. https://doi.org/10.1038/s42256-020-00287-7
Ferdinands G (2021) AI-assisted systematic reviewing: selecting studies to compare Bayesian versus frequentist SEM for small sample sizes. Multivar Behav Res 56(153):154. https://doi.org/10.1080/00273171.2020.1853501
Norambuena GA, Wyles CC, Van Demark RE 3rd, Trousdale RT (2019) Effect of dislocation timing following primary total hip arthroplasty on the risk of redislocation and revision. Hip Int 29(5):489–495
Blanco JF, da Casa C, Fidalgo H, García-Iglesias MA, González-Garcia L, Burón-Alvarez I, Sañudo S, García-Alonso M. (2022) Effect of hip hemiarthroplasty dislocation on mortality after hip fracture surgery. Rev Esp Cir Ortop Traumatol. 13:S1888–4415(22)00229–6.https://doi.org/10.1016/j.recot.2022.08.006
Ishii Y, Noguchi H, Takeda M, Sato J, Domae Y (2012) Efficacy of an abduction brace in preventing initial dislocation in the early postoperative period after primary total hip arthroplasty. Surg Sci. 5–10. 4236/ ss. 2012. 33026
Smith TO, Jepson P, Beswick A, Sands G, Drummond A, Davis ET, Sackley CM (2016) Assistive devices, hip precautions, environmental modifications and training to prevent dislocation and improve function after hip arthroplasty. Cochrane Database Syst Rev. 10. 1002/ 14651 858. CD010 815. pub2
Valcarenghi J, Martinov S, Chahidi E, Jennart H, Bui Quoc E, Dimanche MC, Hupez A, Bhogal H, Hafez K, Callewier A, Bath O, Hernigou J (2022) Hip fractures re-operation compared with death at two year in elderly patients: lowest risk of revision with dual mobility total hip arthroplasty than with bipolar hemiarthroplasty or internal fixation of Garden I and II. Int Orthop 46(9):1945–1953. https://doi.org/10.1007/s00264-022-05479-x
Hartzler MA, Abdel MP, Sculco PK, Taunton MJ, Pagnano MW, Hanssen AD (2018) Otto Aufranc Award: dual-mobility constructs in revision THA reduced dislocation, rerevision, and reoperation compared with large femoral heads. Clin Orthop Relat Res 476(2):293–301
Esposito CI, Carroll KM, Sculco PK, Padgett DE, Jerabek SA, Mayman DJ (2018) Total hip arthroplasty patients with fixed spinopelvic alignment are at higher risk of hip dislocation. J Arthroplasty 33(5):1449–1454
Elbuluk AM, Slover J, Anoushiravani AA, Schwarzkopf R, Eftekhary N, Vigdorchik JM (2018) The cost-effectiveness of dual mobility in a spinal deformity population with high risk of dislocation: a computer-based model. Bone Joint J 100-B(10):1297–302
Dhawan R, Baré JV, Shimmin A (2022) Modular dual-mobility articulations in patients with adverse spinopelvic mobility. Bone Joint J 104(7):820–825. https://doi.org/10.1302/0301-620X.104B7.BJJ-2021-1628.R1
Acknowledgements
The authors thank the Paris-Saclay University for reviewing mathematics data.
Author information
Authors and Affiliations
Contributions
Data collection (PH, OB) and redaction (PH, PC).
Corresponding author
Ethics declarations
Ethical approval
The study does not involve individual patient data, and hence, ethics approval is not needed.
Consent to participate
Not applicable.
Consent for publication
Authors agree to publish the manuscript.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hernigou, P., Barbier, O. & Chenaie, P. Hip arthroplasty dislocation risk calculator: evaluation of one million primary implants and twenty-five thousand dislocations with deep learning artificial intelligence in a systematic review of reviews. International Orthopaedics (SICOT) 47, 557–571 (2023). https://doi.org/10.1007/s00264-022-05644-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00264-022-05644-2