ä Although the criteria of Kocher et al. were an important advancement in our ability to diagnose septic arthritis of the hip early, the changing microbial landscape and availability of advanced imaging have rendered it insufficient for contemporary clinical use.ä Routine use of magnetic resonance imaging and recognition of disseminated disease have prompted the development of algorithms to predict concurrent osteoarticular infection in cases of septic arthritis and osteomyelitis that were previously assumed to be "isolated."ä Recent research has attempted to stratify childhood bone and joint infection (BJI) by severity to guide treatment planning. This is valuable, as patients with multifocal disease, more virulent pathogens, and immunocompromise can have longer hospital stays and require multiple surgeries.ä The increasing prevalence of clinical prediction algorithms in childhood BJI is not completely matched by quality in methodology. Clinicians need to be wary of adopting predictive algorithms prior to robust external validation.It has been >20 years since Kocher et al. pioneered a predictive algorithm that would allow more accurate diagnosis of septic arthritis (SA) of the pediatric hip 1 . Although the evaluation of childhood bone and joint infection (BJI) has evolved substantially since then, the core problem remains: how can we develop accurate, evidence-based clinical prediction algorithms that will provide informed guidance to clinicians? Interest in this field has expanded since the first study by Kocher et al. 1 . The popularity of clinical algorithms and machine learning appears to have superseded individual clinical experience with knowledge gained from modeling large data sets 2 . Furthermore, predictive modeling has the potential for identifying an elusive diagnosis or determining the probability of poor treatment outcome 3 . However, the increasing prevalence of clinical prediction algorithms is not completely matched by quality in methodology 4 . When assessing any predictive model, clinicians should establish several points, such as whether the population the model was derived from reflects their own local population, how well the model performed in external validation, and what practical impact these predictions will have on clinical decisions 3 .Clinical prediction algorithms for childhood BJI attempt to provide guidance for 3 main clinical problems: differentiating SA from transient synovitis (TS) of the hip, predicting periarticular infection, and predicting a more severe course of illness. These areas are the focus of this review, which aims to provide an informed analysis of the diagnostic algorithms available to clinicians in assessing childhood BJI and their performance in external validation.Differentiating TS from SA of the Hip The Kocher criteria 1 , in 1999, used 4 features to raise suspicion for SA: (1) an inability to weight-bear, (2) a white blood-cell count (WBC) of >12 • 10 9 cells/L, (3) an erythrocyte sedimentation rate (ESR) of ‡40 mm/hr, and (4) a temperature of >38.5°C (>1...