Risk Scores and Machine Learning to Identify Patients With Acute Periprosthetic Joints Infections That Will Likely Fail Classical Irrigation and Debridement

Abstract

The most preferred treatment for acute periprosthetic joint infection (PJI) is surgical debridement, antibiotics and retention of the implant (DAIR). The reported success of DAIR varies greatly and depends on a complex interplay of several host-related factors, duration of symptoms, the microorganism(s) causing the infection, its susceptibility to antibiotics and many others. Thus, there is a great clinical need to predict failure of the "classical" DAIR procedure so that this surgical option is offered to those most likely to succeed, but also to identify those patients who may benefit from more intensified antibiotic treatment regimens or new and innovative treatment strategies. In this review article, the current recommendations for DAIR will be discussed, a summary of independent risk factors for DAIR failure will be provided and the advantages and limitations of the clinical use of preoperative risk scores in early acute (post-surgical) and late acute (hematogenous) PJIs will be presented. In addition, the potential of implementing machine learning (artificial intelligence) in identifying patients who are at highest risk for failure of DAIR will be addressed. The ultimate goal is to maximally tailor and individualize treatment strategies and to avoid treatment generalization.

Keywords: debridement; failure; implant retention; machine learning; periprosthetic joint infection; risk score.

Figure 1

Preoperative risk scores for DAIR failure. KLIC-score for predicting DAIR failure in early acute (postsurgical) PJI (A) and CRIME80-score for predicting DAIR failure in late acute (hematogenous) PJI (B).