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 replacements from the Swedish Arthroplasty Register
File(s)
Published version
Author(s)
Type
Journal Article
Abstract
Introduction While cementless fixation offers potential advantages, such as a shorter
operative 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 re-operation after
elective THR.
Methods We included 154,519 primary elective THRs from the Swedish Arthroplasty
Register(SAR), encompassing twenty-one patient-,surgical-,and implant-specific features, for
model derivation and validation in predicting 30-,60-,90-day and 1-year revision and re operation due to PPFF. Model performance was tested using the area under the curve(AUC),
and features importance were identified in the best performing algorithm.
Results The Lasso regression excelled in predicting 30-day revisions(AUC=0.85), while the
Gradient Boosting Machine(GBM) model outperformed other models by a slight margin for
all remaining endpoints(AUC range:0.79-0.86). Predictive factors for revision and re-operation
were identified, with patient features such as increasing age, higher ASA grade(> 3), and
obesity classes II-III were associated with elevated risks. A pre-operative 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 re-operation risks.
Conclusion This is the first study to develop machine learning models to forecast the risk of
periprosthetic femoral fracture necessitating re-do surgery. Future studies are required to
externally validate our algorithm and assess its applicability in clinical practice.
operative 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 re-operation after
elective THR.
Methods We included 154,519 primary elective THRs from the Swedish Arthroplasty
Register(SAR), encompassing twenty-one patient-,surgical-,and implant-specific features, for
model derivation and validation in predicting 30-,60-,90-day and 1-year revision and re operation due to PPFF. Model performance was tested using the area under the curve(AUC),
and features importance were identified in the best performing algorithm.
Results The Lasso regression excelled in predicting 30-day revisions(AUC=0.85), while the
Gradient Boosting Machine(GBM) model outperformed other models by a slight margin for
all remaining endpoints(AUC range:0.79-0.86). Predictive factors for revision and re-operation
were identified, with patient features such as increasing age, higher ASA grade(> 3), and
obesity classes II-III were associated with elevated risks. A pre-operative 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 re-operation risks.
Conclusion This is the first study to develop machine learning models to forecast the risk of
periprosthetic femoral fracture necessitating re-do surgery. Future studies are required to
externally validate our algorithm and assess its applicability in clinical practice.
Date Issued
2025-01-01
Date Acceptance
2024-09-10
Citation
Bone & Joint Research, 2025, 14 (1), pp.46-57
ISSN
2046-3758
Publisher
The British Editorial Society of Bone & Joint Surgery
Start Page
46
End Page
57
Journal / Book Title
Bone & Joint Research
Volume
14
Issue
1
Copyright Statement
© 2025 Alagha et al. Open Access This article is distributed under the terms of the Creative Commons Attributions (CC BY 4.0) licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium or format, provided the original author and source are credited.
License URL
Identifier
10.1302/2046-3758
Publication Status
Published
Date Publish Online
2025-01-24