Scoping Review on ACL Surgery and Registry Data

Abstract

Purpose of Review To present an overview of registry-based anterior cruciate ligament (ACL) research, as well as provide insight into the future of ACL registries. Recent Findings During the past decades, the ACL registries have had an important role in increasing our understanding of patients with ACL injuries and their treatment. The registry data has deepened our understanding of factors that have been associated with an increased risk of sustaining an ACL injury and for evaluation of treatment factors and their impact on patient-related outcomes. Recently, registry-based ACL research using artificial intelligence (AI) and machine learning (ML) has shown potential to create clinical decision-making tools and analyzing outcomes. Thus, standardization of collected data between the registries is needed to facilitate the further collaboration between registries and to facilitate the interpretation of results and subsequently improve the possibilities for implementation of AI and ML in the registry-based research. Summary Several studies have been based on the current ACL registries providing an insight into the epidemiology of ACL injuries as well as outcomes following ACL reconstruction. However, the current ACL registries are facing future challenges, and thus, new methods and techniques are needed to ensure further good quality and clinical applicability of study findings based on ACL registry data.

Ten‐year results from the UK National Ligament Registry: Patient characteristics and factors predicting nonresponders for completion of outcome scores

“…It is well recognised that lengthy questionnaires can lead to respondent fatigue, resulting in less thoughtful answers or premature termination of their participation [19,15,18,36]. Among national ligament registries, the NLR is unique in its collection of four subjective PROMs [11]. While collecting multiple PROMS enables comparison and collaborative work with other registries, it comes at the cost of having an incomplete data set.…”

Unsupervised Machine Learning of the Combined Danish and Norwegian Knee Ligament Registers: Identification of 5 Distinct Patient Groups With Differing ACL Revision Rates

“…9,31 Since their inception, these national registers have produced several studies on ACL treatment and outcomes and have recently developed preliminary outcome prediction models using supervised machine learning methodology. 15,[20][21][22][23] The present study sought to further investigate the factors associated with subsequent ACLR revision through the application of unsupervised learning techniques to the combined Norwegian and Danish knee ligament register (KLR). The primary goal of this analysis was to identify distinct subgroups of patients within the registers and determine if the rate of subsequent revision ACLR differs between the patient clusters.…”

The days of generalised joint hypermobility assessment in all patients with ACL injury are here

“…Second anterior cruciate ligament (ACL) injury after ACL reconstruction (ACL-R) is a dreaded potential complication to both patients and healthcare professionals 1. Research conducted throughout the 2010s has helped identify factors influencing second ACL injury risk after ACL-R and the multifactorial causes of second ACL injury are now well established, with patient anatomy, surgical factors and components of the rehabilitation process each playing essential roles 2. Despite the wealth of existing knowledge, additional contributors to second ACL injury may be overlooked due to the focus on complex interactions between a subset of risk factors.…”