Background Artificial intelligence is an emerging technology with rapid growth and increasing applications in orthopaedics. This study aimed to summarize the existing evidence and recent developments of artificial intelligence in diagnosing knee osteoarthritis and predicting outcomes of total knee arthroplasty. Methods PubMed and EMBASE databases were searched for articles published in peer-reviewed journals between January 1, 2010 and May 31, 2021. The terms included: ‘artificial intelligence’, ‘machine learning’, ‘knee’, ‘osteoarthritis’, and ‘arthroplasty’. We selected studies focusing on the use of AI in diagnosis of knee osteoarthritis, prediction of the need for total knee arthroplasty, and prediction of outcomes of total knee arthroplasty. Non-English language articles and articles with no English translation were excluded. A reviewer screened the articles for the relevance to the research questions and strength of evidence. Results Machine learning models demonstrated promising results for automatic grading of knee radiographs and predicting the need for total knee arthroplasty. The artificial intelligence algorithms could predict postoperative outcomes regarding patient-reported outcome measures, patient satisfaction and short-term complications. Important weaknesses of current artificial intelligence algorithms included the lack of external validation, the limitations of inherent biases in clinical data, the requirement of large datasets in training, and significant research gaps in the literature. Conclusions Artificial intelligence offers a promising solution to improve detection and management of knee osteoarthritis. Further research to overcome the weaknesses of machine learning models may enhance reliability and allow for future use in routine healthcare settings.
Background: Knee osteoarthritis (OA) is one of the most common and debilitating degenerative joint diseases worldwide. While radiography is the most commonly used imaging modality, it is associated with drawbacks which newer modalities such as magnetic resonance imaging (MRI) and ultrasound could overcome. Nevertheless, the role of imaging in clinical practice and research in knee OA has not been clearly defined. Furthermore, guidelines on imaging in knee OA from different authoritative bodies have not been compared in previous studies. Therefore, the present review aims to summarise existing evidence and compare guidelines on the use of different imaging modalities in evaluating knee OA.Methods: This is a narrative review based on a search of published clinical guidelines and the PubMed database for articles published between 1 January 1990 and 31 May 2020. Results:There is no broad consensus on the value of imaging in patients with typical OA presentation. If imaging is required, current evidence and clinical guidelines support the use of radiography and MRI as first-and second-line diagnostic modalities respectively. Since radiographic OA features have limited sensitivity and do not manifest in early stages, MRI is the preferred option for whole-joint evaluation in OA research. Discrepancies exist regarding the use of alternative imaging modalities including ultrasound, computed tomography and nuclear medicine. Conclusion:Radiography and MRI are the imaging modalities of choice. Other modalities have their respective advantages, and more research is warranted for the standardisation of image acquisition and interpretation methodology, in order to evaluate their validity, reliability and responsiveness in OA research. K E Y W O R D S clinical guidelines, imaging, knee osteoarthritis 1 | INTRODUCTION Knee osteoarthritis (OA) is one of the most common and debilitating degenerative joint diseases worldwide, with 80% of OA patients suffering from movement limitations and 25% of them being unable to carry out major activities in their daily lives (Neogi, 2013).Although cartilage degeneration and osteophyte formation remain the structural hallmarks of knee OA, the disease is now increasingly recognised as a whole-organ disorder affecting tissues in the entire knee joint, such as the meniscus and synovium (Hayashi, Guermazi, & Hunter, 2011). Its clinical presentation is heterogeneous, with typical symptoms including pain, stiffness and movement restriction.
Background Arthroplasty services worldwide have been significantly disrupted by the pandemic of coronavirus disease 2019 (COVID-19). This retrospective comparative study aimed to characterize its impact on arthroplasty services in Hong Kong. Methods From January 1 to June 30, 2020, the patients of “COVID-19 cohort” underwent elective total hip or knee replacement in Hong Kong public hospitals. The cohort was compared to the “control cohort” during the same period in 2019. Data analysis was performed to compare the two cohorts’ numbers of operations, hospital admission, orthopaedic clinic attendances, and waiting time. Results A total of 33,111 patient episodes were analyzed. During the study period, the elective arthroplasty operations and hospitalizations decreased by 53 and 54%, respectively (P < 0.05). Reductions were most drastic from February to April, with surgical volume declining by 86% (P < 0.05). The primary arthroplasty operations decreased by 91% (P < 0.05), while the revision operations remained similar. Nevertheless, 14 public hospitals continued performing elective arthroplasty for patients with semi-urgent indications, including infection, progressive bone loss, prosthesis loosening, dislocation or mechanical failure of arthroplasty, and tumor. At the institution with the highest arthroplasty surgical volume, infection (28%) was the primary reason for surgery, followed by prosthesis loosening (22%) and progressive bone loss (17%). The orthopaedic clinic attendances also decreased by 20% (P < 0.05). Increases were observed in waiting time and the total number of patients on the waiting list for elective arthroplasty. Conclusions Despite the challenges, public hospitals in Hong Kong managed to continue providing elective arthroplasty services for high-priority patients. Arthroplasty prioritization, infection control measures, and post-pandemic service planning can enhance hospital preparedness to mitigate the impact of current and future pandemics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.