Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register
Aims: While cementless fixation offers potential advantages over cemented fixation, such as a shorter operating time, concerns linger over its higher cost and increased risk of periprosthetic fractures. If the risk of fracture can be forecasted, it would aid the shared decision-making process relat...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The British Editorial Society of Bone & Joint Surgery
2025-01-01
|
| Series: | Bone & Joint Research |
| Subjects: | |
| Online Access: | https://online.boneandjoint.org.uk/doi/epdf/10.1302/2046-3758.141.BJR-2024-0134.R1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583693677363200 |
|---|---|
| author | M. A. Alagha Justin Cobb Alexander D. Liddle Henrik Malchau Ola Rolfson Maziar Mohaddes |
| author_facet | M. A. Alagha Justin Cobb Alexander D. Liddle Henrik Malchau Ola Rolfson Maziar Mohaddes |
| author_sort | M. A. Alagha |
| collection | DOAJ |
| description | Aims: While cementless fixation offers potential advantages over cemented fixation, such as a shorter operating time, concerns linger over its higher cost and increased risk of periprosthetic fractures. If the risk of fracture can be forecasted, it would aid the shared decision-making process related to cementless stems. Our study aimed to develop and validate predictive models of periprosthetic femoral fracture (PPFF) necessitating revision and reoperation after elective total hip arthroplasty (THA). Methods: We included 154,519 primary elective THAs from the Swedish Arthroplasty Register (SAR), encompassing 21 patient-, surgical-, and implant-specific features, for model derivation and validation in predicting 30-day, 60-day, 90-day, and one-year revision and reoperation due to PPFF. Model performance was tested using the area under the curve (AUC), and feature importance was identified in the best-performing algorithm. Results: The Lasso regression excelled in predicting 30-day revisions (area under the receiver operating characteristic curve (AUC) = 0.85), while the Gradient Boosting Machine (GBM) model outperformed other models by a slight margin for all remaining endpoints (AUC range: 0.79 to 0.86). Predictive factors for revision and reoperation were identified, with patient features such as increasing age, higher American Society of Anesthesiologists grade (> III), and World Health Organization obesity classes II to III associated with elevated risks. A preoperative diagnosis of idiopathic necrosis increased revision risk. Concerning implant design, factors such as cementless femoral fixation, reverse-hybrid fixation, hip resurfacing, and small (< 35 mm) or large (> 52 mm) femoral heads increased both revision and reoperation risks. Conclusion: This is the first study to develop machine-learning models to forecast the risk of PPFF necessitating secondary surgery. Future studies are required to externally validate our algorithm and assess its applicability in clinical practice. Cite this article: Bone Joint Res 2025;14(1):46–57. |
| format | Article |
| id | doaj-art-08c364d6777a4d8b90de43282e612f63 |
| institution | Kabale University |
| issn | 2046-3758 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | The British Editorial Society of Bone & Joint Surgery |
| record_format | Article |
| series | Bone & Joint Research |
| spelling | doaj-art-08c364d6777a4d8b90de43282e612f632025-01-28T06:54:24ZengThe British Editorial Society of Bone & Joint SurgeryBone & Joint Research2046-37582025-01-01141465710.1302/2046-3758.141.BJR-2024-0134.R1Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty RegisterM. A. Alagha0https://orcid.org/0000-0002-1097-7793Justin Cobb1https://orcid.org/0000-0002-6095-8822Alexander D. Liddle2https://orcid.org/0000-0001-6135-1996Henrik Malchau3https://orcid.org/0000-0002-4291-2441Ola Rolfson4https://orcid.org/0000-0001-6534-1242Maziar Mohaddes5https://orcid.org/0000-0003-1848-9054MSk Lab, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UKMSk Lab, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UKMSk Lab, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UKHarvard Medical School, Boston, Massachusetts, USADepartment of Orthopaedics, Institute of Clinical Sciences, University of Gothenburg, Gothenburg, SwedenDepartment of Orthopaedics, Institute of Clinical Sciences, University of Gothenburg, Gothenburg, SwedenAims: While cementless fixation offers potential advantages over cemented fixation, such as a shorter operating time, concerns linger over its higher cost and increased risk of periprosthetic fractures. If the risk of fracture can be forecasted, it would aid the shared decision-making process related to cementless stems. Our study aimed to develop and validate predictive models of periprosthetic femoral fracture (PPFF) necessitating revision and reoperation after elective total hip arthroplasty (THA). Methods: We included 154,519 primary elective THAs from the Swedish Arthroplasty Register (SAR), encompassing 21 patient-, surgical-, and implant-specific features, for model derivation and validation in predicting 30-day, 60-day, 90-day, and one-year revision and reoperation due to PPFF. Model performance was tested using the area under the curve (AUC), and feature importance was identified in the best-performing algorithm. Results: The Lasso regression excelled in predicting 30-day revisions (area under the receiver operating characteristic curve (AUC) = 0.85), while the Gradient Boosting Machine (GBM) model outperformed other models by a slight margin for all remaining endpoints (AUC range: 0.79 to 0.86). Predictive factors for revision and reoperation were identified, with patient features such as increasing age, higher American Society of Anesthesiologists grade (> III), and World Health Organization obesity classes II to III associated with elevated risks. A preoperative diagnosis of idiopathic necrosis increased revision risk. Concerning implant design, factors such as cementless femoral fixation, reverse-hybrid fixation, hip resurfacing, and small (< 35 mm) or large (> 52 mm) femoral heads increased both revision and reoperation risks. Conclusion: This is the first study to develop machine-learning models to forecast the risk of PPFF necessitating secondary surgery. Future studies are required to externally validate our algorithm and assess its applicability in clinical practice. Cite this article: Bone Joint Res 2025;14(1):46–57.https://online.boneandjoint.org.uk/doi/epdf/10.1302/2046-3758.141.BJR-2024-0134.R1machine learningtotal hip arthroplastyperiprosthetic fractureperiprosthetic femoral fracturesimplant failurerevision surgeryanesthesiologistssarfemoral headscementless fixationhip resurfacing arthroplastyarthroplasty registriesidiopathic necrosis |
| spellingShingle | M. A. Alagha Justin Cobb Alexander D. Liddle Henrik Malchau Ola Rolfson Maziar Mohaddes Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register Bone & Joint Research machine learning total hip arthroplasty periprosthetic fracture periprosthetic femoral fractures implant failure revision surgery anesthesiologists sar femoral heads cementless fixation hip resurfacing arthroplasty arthroplasty registries idiopathic necrosis |
| title | Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register |
| title_full | Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register |
| title_fullStr | Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register |
| title_full_unstemmed | Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register |
| title_short | Prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty: a simplified and validated model based on 154,519 total hip arthroplasties from the Swedish Arthroplasty Register |
| title_sort | prediction of implant failure risk due to periprosthetic femoral fracture after primary elective total hip arthroplasty a simplified and validated model based on 154 519 total hip arthroplasties from the swedish arthroplasty register |
| topic | machine learning total hip arthroplasty periprosthetic fracture periprosthetic femoral fractures implant failure revision surgery anesthesiologists sar femoral heads cementless fixation hip resurfacing arthroplasty arthroplasty registries idiopathic necrosis |
| url | https://online.boneandjoint.org.uk/doi/epdf/10.1302/2046-3758.141.BJR-2024-0134.R1 |
| work_keys_str_mv | AT maalagha predictionofimplantfailureriskduetoperiprostheticfemoralfractureafterprimaryelectivetotalhiparthroplastyasimplifiedandvalidatedmodelbasedon154519totalhiparthroplastiesfromtheswedisharthroplastyregister AT justincobb predictionofimplantfailureriskduetoperiprostheticfemoralfractureafterprimaryelectivetotalhiparthroplastyasimplifiedandvalidatedmodelbasedon154519totalhiparthroplastiesfromtheswedisharthroplastyregister AT alexanderdliddle predictionofimplantfailureriskduetoperiprostheticfemoralfractureafterprimaryelectivetotalhiparthroplastyasimplifiedandvalidatedmodelbasedon154519totalhiparthroplastiesfromtheswedisharthroplastyregister AT henrikmalchau predictionofimplantfailureriskduetoperiprostheticfemoralfractureafterprimaryelectivetotalhiparthroplastyasimplifiedandvalidatedmodelbasedon154519totalhiparthroplastiesfromtheswedisharthroplastyregister AT olarolfson predictionofimplantfailureriskduetoperiprostheticfemoralfractureafterprimaryelectivetotalhiparthroplastyasimplifiedandvalidatedmodelbasedon154519totalhiparthroplastiesfromtheswedisharthroplastyregister AT maziarmohaddes predictionofimplantfailureriskduetoperiprostheticfemoralfractureafterprimaryelectivetotalhiparthroplastyasimplifiedandvalidatedmodelbasedon154519totalhiparthroplastiesfromtheswedisharthroplastyregister |