Preoperative Risk Prediction Models for Short-Term Revision and Death After Total Hip Arthroplasty

Abstract

Background: Because of the increasing number of total hip arthroplasties (THAs), even a small proportion of complications after the operation can lead to substantial individual difficulties and health-care costs. The aim of this study was to develop simple-to-use risk prediction models to assess the risk of the most common reasons for implant failure to facilitate clinical decision-making and to ensure long-term survival of primary THAs. Methods: We analyzed patient and surgical data reported to the Finnish Arthroplasty Register (FAR) on 25,919 primary THAs performed in Finland between May 2014 and January 2018. For the most frequent adverse outcomes after primary THA, we developed multivariable Lasso regression models based on the data of the randomly selected training cohort (two-thirds of the data). The performances of all models were validated using the remaining, independent test set consisting of 8,640 primary THAs (one-third of the data) not used for building the models. Results: The most common outcomes within 6 months after the primary THA were revision operations due to periprosthetic joint infection (1.1%), dislocation (0.7%), or periprosthetic fracture (0.5%), and death (0.7%). For each of these outcomes, Lasso regression identified subsets of variables required for accurate risk predictions. The highest discrimination performance, in terms of area under the receiver operating characteristic curve (AUROC), was observed for death (0.84), whereas the performance was lower for revisions due to periprosthetic joint infection (0.68), dislocation (0.64), or periprosthetic fracture (0.65). Conclusions: Based on the small number of preoperative characteristics of the patient and modifiable surgical parameters, the developed risk prediction models can be easily used to assess the risk of revision or death. All developed models hold the potential to aid clinical decision-making, ultimately leading to improved clinical outcomes. Level of Evidence: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Improved risk prediction of chemotherapy‐induced neutropenia—model development and validation with real‐world data

“…The improved performance is explained by the different input variables resulting from the applied iterative variable selection procedure used successfully also before. 22 , 23 , 24 Alternatively, poorly adjusted regression coefficients due to inherent differences between patient populations and local healthcare practices or overfitting may explain the worse performance of previous models. For example, the Lyman model had drastically different coefficients for different treatment regimens compared to Lasso and Li models (Table 2 , Table S1 ) which might explain its underperformance.…”

“…The improved performance is explained by the different input variables resulting from the applied iterative variable selection procedure used successfully also before 22‐24 . Alternatively, poorly adjusted regression coefficients due to inherent differences between patient populations and local healthcare practices or overfitting may explain the worse performance of previous models.…”

“…To identify the most influential predictors and to account for model variability due to random subsampling, the model construction was performed iteratively in multiple steps similarly as before. 22 , 23 , 24 In previous studies, this approach has led to models with fewer variables but retaining the same prediction accuracy as the more complex models. During model development and validation, only patients with complete data for the selected predictors were used.…”

“…We applied penalized logistic regression with least absolute shrinkage and selection operator (Lasso) penalty to the training cohort to construct a multivariable model for predicting the individualized risk of NI. To identify the most influential predictors and to account for model variability due to random subsampling, the model construction was performed iteratively in multiple steps similarly as before 22‐24 . In previous studies, this approach has led to models with fewer variables but retaining the same prediction accuracy as the more complex models.…”

Stable Iterative Variable Selection

“…On the other hand, a relatively low number of iterations would lead to not covering all binning arrangements. In practice, we have observed that 100 iterations is sufficient for obtaining a stable set of features in a range of datasets ( Klén et al , 2019 , 2020 ; Venäläinen et al , 2020 , 2021 ).…”