scholarly journals Supervised Machine Learning for Aiding Diagnosis of Knee Osteoarthritis: A Systematic Review and Meta-Analysis

2020 ◽  
Author(s):  
Luca Parisi ◽  
Narrendar RaviChandran ◽  
Matteo Lanzillotta
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Gait Analysis ◽  
Meta Analysis ◽  
Supervised Machine Learning ◽  
Gait Patterns ◽  
Kinematic Data ◽  
Knee Oa ◽  
Symptomatic Knee

<p><b>Background</b></p> <p>Knee osteoarthritis (OA) remains a leading aetiology of disability worldwide. Clinical assessment of such knee-related conditions has improved with recent advances in gait analysis. Despite being a gold standard method, gait data acquired by motion capture (mocap) technology are highly non-linear and dimensional, which make traditional gait analysis challenging. Thus, extrinsic algorithms need to be used to make sense of gait data. Supervised Machine Learning (ML)-based classifiers outperform conventional statistical methods in revealing intrinsic patterns that can discern gait abnormalities when using mocap data, making them a suitable tool for aiding diagnosis of knee OA.</p> <p><b>Research question</b></p> <p>Studies have demonstrated the accuracy of supervised ML-based classifiers in gait analysis. However, these techniques have not gained wide acceptance amongst biomechanists for two reasons: the reliability of such methods has not been assessed and there is no consensus on which classifier or group of classifiers to select. Specifically, it is not clear whether classifiers that leverage optimal separating hyperplanes (OSH) or artificial neural networks (ANN) are more accurate and reliable.</p> <p><b>Methods</b></p> <p>A systematic review and meta-analysis were conducted to assess the capability of such algorithms to predict pathological kinematic and kinetic gait patterns as indicators of knee OA. With 153 eligible studies, 6 studies met the inclusion criteria for a subsequent meta-analysis, accounting for <a>273 healthy subjects and 313 patients </a>with symptomatic knee OA. The classification performance of supervised ML classifiers (OSH- or ANN-based) used in these studies was quantitatively assessed and compared across four following performance metrics: classification accuracy on the test set (ACC), sensitivity (SN), specificity (SP), and area under the receiver operating characteristic curve (AUC). </p> <p><b>Results</b></p> <p>There was no statistically significant discrepancy in the ACC between OSH- and ANN-based classifiers when dealing with kinetic and kinematic data concurrently, as well as when considering only kinematic data. However, there was a statistically significant difference in their SN and SP, with the ANN-based classifiers having higher SN and SP than OSH-based algorithms. As only one of the eligible studies reported AUC, this metric could not be assessed statistically across studies.</p> <p><b>Significance</b></p> <p>This study supports the use of ANN-based algorithms for classifying knee OA-related gait patterns as having a higher sensitivity and specificity than OSH-based classifiers. Considering their higher reliability, leveraging supervised ANN-based methods can aid biomechanists to diagnose knee OA objectively.</p>

scholarly journals Supervised Machine Learning for Aiding Diagnosis of Knee Osteoarthritis: A Systematic Review and Meta-Analysis

2020 ◽  
Author(s):  
Luca Parisi ◽  
Narrendar RaviChandran ◽  
Matteo Lanzillotta
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Gait Analysis ◽  
Meta Analysis ◽  
Supervised Machine Learning ◽  
Gait Patterns ◽  
Kinematic Data ◽  
Knee Oa ◽  
Symptomatic Knee

<p><b>Background</b></p> <p>Knee osteoarthritis (OA) remains a leading aetiology of disability worldwide. Clinical assessment of such knee-related conditions has improved with recent advances in gait analysis. Despite being a gold standard method, gait data acquired by motion capture (mocap) technology are highly non-linear and dimensional, which make traditional gait analysis challenging. Thus, extrinsic algorithms need to be used to make sense of gait data. Supervised Machine Learning (ML)-based classifiers outperform conventional statistical methods in revealing intrinsic patterns that can discern gait abnormalities when using mocap data, making them a suitable tool for aiding diagnosis of knee OA.</p> <p><b>Research question</b></p> <p>Studies have demonstrated the accuracy of supervised ML-based classifiers in gait analysis. However, these techniques have not gained wide acceptance amongst biomechanists for two reasons: the reliability of such methods has not been assessed and there is no consensus on which classifier or group of classifiers to select. Specifically, it is not clear whether classifiers that leverage optimal separating hyperplanes (OSH) or artificial neural networks (ANN) are more accurate and reliable.</p> <p><b>Methods</b></p> <p>A systematic review and meta-analysis were conducted to assess the capability of such algorithms to predict pathological kinematic and kinetic gait patterns as indicators of knee OA. With 153 eligible studies, 6 studies met the inclusion criteria for a subsequent meta-analysis, accounting for <a>273 healthy subjects and 313 patients </a>with symptomatic knee OA. The classification performance of supervised ML classifiers (OSH- or ANN-based) used in these studies was quantitatively assessed and compared across four following performance metrics: classification accuracy on the test set (ACC), sensitivity (SN), specificity (SP), and area under the receiver operating characteristic curve (AUC). </p> <p><b>Results</b></p> <p>There was no statistically significant discrepancy in the ACC between OSH- and ANN-based classifiers when dealing with kinetic and kinematic data concurrently, as well as when considering only kinematic data. However, there was a statistically significant difference in their SN and SP, with the ANN-based classifiers having higher SN and SP than OSH-based algorithms. As only one of the eligible studies reported AUC, this metric could not be assessed statistically across studies.</p> <p><b>Significance</b></p> <p>This study supports the use of ANN-based algorithms for classifying knee OA-related gait patterns as having a higher sensitivity and specificity than OSH-based classifiers. Considering their higher reliability, leveraging supervised ANN-based methods can aid biomechanists to diagnose knee OA objectively.</p>

scholarly journals Hypertonic dextrose injections (prolotherapy) in the treatment of symptomatic knee osteoarthritis: A systematic review and meta-analysis

2016 ◽  
Vol 6 (1) ◽  
Author(s):  
Regina WS Sit ◽  
Vincent CH Chung ◽  
Kenneth D. Reeves ◽  
David Rabago ◽  
Keith KW Chan ◽  
...  
Keyword(s):  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Primary Outcome ◽  
Meta Analysis ◽  
Knee Oa ◽  
Composite Scale ◽  
Symptomatic Knee Osteoarthritis ◽  
Symptomatic Knee ◽  
Pain Subscale ◽  
Hypertonic Dextrose

Abstract Hypertonic dextrose injections (prolotherapy) is an emerging treatment for symptomatic knee osteoarthritis (OA) but its efficacy is uncertain. We conducted a systematic review with meta-analysis to synthesize clinical evidence on the effect of prolotherapy for knee OA. Fifteen electronic databases were searched from their inception to September 2015. The primary outcome of interest was score change on the Western Ontario and McMaster Universities Arthritis Index (WOMAC). Three randomized controlled trials (RCTs) of moderate risk of bias and one quasi–randomized trial were included, with data from a total of 258 patients. In the meta-analysis of two eligible studies, prolotherapy is superior to exercise alone by a standardized mean difference (SMD) of 0.81 (95% CI: 0.18 to 1.45, p = 0.012), 0.78 (95% CI: 0.25 to 1.30, p = 0.001) and 0.62 (95% CI: 0.04 to 1.20, p = 0.035) on the WOMAC composite scale; and WOMAC function and pain subscale scores respectively. Moderate heterogeneity exists in all cases. Overall, prolotherapy conferred a positive and significant beneficial effect in the treatment of knee OA. Adequately powered, longer-term trials with uniform end points are needed to better elucidate the efficacy of prolotherapy.

Safety of Intra-Articular Hyaluronic Acid for Knee Osteoarthritis: Systematic Review and Meta-Analysis of Randomized Trials Involving More than 8,000 Patients

Cartilage ◽  
2019 ◽  
pp. 194760351988878
Author(s):  
Larry E. Miller ◽  
Samir Bhattacharyya ◽  
William R. Parrish ◽  
Michael Fredericson ◽  
Brad Bisson ◽  
...  
Keyword(s):  
Systematic Review ◽  
Hyaluronic Acid ◽  
Adverse Events ◽  
Knee Osteoarthritis ◽  
Randomized Controlled Trials ◽  
Meta Analysis ◽  
Controlled Trials ◽  
Knee Oa ◽  
Randomized Controlled ◽  
Symptomatic Knee

Objective The objective of this systematic review and meta-analysis was to report the safety of intra-articular hyaluronic acid (IAHA) in patients with symptomatic knee osteoarthritis (OA). Methods We identified randomized controlled trials reporting the safety of IAHA versus IA saline in adults with symptomatic knee OA. Main safety outcomes were adverse events (AEs), local AEs, serious adverse events (SAEs), study withdrawals, and AE-related study withdrawals. Results A total of 35 randomized controlled trials with 38 group comparisons comprising 8,078 unique patients (IAHA: 4,295, IA saline: 3,783) were included in the meta-analysis. Comparing IAHA with IA saline over a median of 6 months follow-up, there were no differences in the risk of AEs (42.4% vs. 39.7%, risk ratio [RR] = 1.01, 95% CI = 0.96-1.07, P = 0.61), SAEs (1.8% vs. 1.2%, RR = 1.44, 95% CI = 0.91-2.26, P=0.12), study withdrawals (12.3% vs. 12.7%, RR = 0.99, 95% CI = 0.87-1.12, P = 0.83), or AE-related study withdrawals (2.7% vs. 2.1%, RR = 1.37, 95% CI = 0.97-1.93, P = 0.08). Local AEs, all of which were nonserious, were more common with IAHA vs. IA saline (14.5% vs. 11.7%, RR = 1.21, 95% CI = 1.07-1.36, P = 0.003) and typically resolved within days. Conclusion IAHA was shown to be safe for use in patients with symptomatic knee OA. Compared with IA saline, IAHA is associated with an increased risk of nonserious, transient local reactions. There was no evidence to suggest any additional safety risks of IAHA.

Relative Efficacy of Intra-articular Injections in the Treatment of Knee Osteoarthritis: A Systematic Review and Network Meta-analysis

2021 ◽  
pp. 036354652110296
Author(s):  
Harsh Singh ◽  
Derrick M. Knapik ◽  
Evan M. Polce ◽  
Carlo K. Eikani ◽  
Amanda H. Bjornstad ◽  
...  
Keyword(s):  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Systematic Reviews ◽  
Meta Analysis ◽  
Effect Sizes ◽  
Controlled Trials ◽  
Cochrane Central Register ◽  
Knee Oa ◽  
Symptomatic Knee

Background: In younger patients and those without severe degenerative changes, the efficacy of intra-articular (IA) injections as a nonoperative modality for treating symptomatic knee osteoarthritis (OA)–related pain while maintaining function has become a subject of increasing interest. Purpose: To assess and compare the efficacy of different IA injections used for the treatment of knee OA, including hyaluronic acid (HA), corticosteroids (CS), platelet-rich plasma (PRP), and plasma rich in growth factors (PRGF), with a minimum 6-month patient follow-up. Study Design: Meta-analysis of randomized controlled trials; Level of evidence, 1. Methods: A systematic review was performed according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines using the following databases: PubMed/MEDLINE, Scopus, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Google Scholar. Mean or mean change from baseline and standard deviation for outcome scores regarding pain and function were recorded at the 6-month follow-up and converted to either a 0 to 100 visual analog scale score for pain or a 0 to 100 Western Ontario and McMaster Universities Osteoarthritis Index score for function. A frequentist network meta-analysis model was developed to compare the effects of HA, CS, PRP, PRGF, and placebo on patient-reported outcomes. Results: All IA treatments except CS were found to result in a statistically significant improvement in outcomes when compared with placebo. PRP demonstrated a clinically meaningful difference in function-related improvement when compared with CS and placebo due to large effect sizes. Studies evaluating outcomes of PRGF reported significant improvement when compared with placebo due to large effect sizes, whereas a potential clinically significant difference was detected in the same comparison parameters in pain evaluation. With regard to improvements in pain, function, and both combined, PRP was found to possess the highest probability of efficacy, followed by PRGF, HA, CS, and placebo. Conclusion: PRP yielded improved outcomes when compared with PRGF, HA, CS, and placebo for the treatment of symptomatic knee OA at a minimum 6-month follow-up. Further investigations evaluating different IA and other nonoperative treatment options for patients with knee OA are warranted to better understand the true clinical efficacy and long-term outcomes of nonsurgical OA management.

scholarly journals Effects of mechanical interventions in the management of knee osteoarthritis: protocol for an OA Trial Bank systematic review and individual participant data meta-analysis

BMJ Open ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. e043026
Author(s):  
Erin M Macri ◽  
Michael Callaghan ◽  
Marienke van Middelkoop ◽  
Miriam Hattle ◽  
Sita M A Bierma-Zeinstra
Keyword(s):  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Broad Class ◽  
Meta Analysis ◽  
Individual Participant Data ◽  
Knee Oa ◽  
International Regulations ◽  
Individual Participant ◽  
Registration Number ◽  
Mechanical Intervention

IntroductionKnee osteoarthritis (OA) is a prevalent and disabling musculoskeletal condition. Biomechanical factors may play a key role in the aetiology of knee OA, therefore, a broad class of interventions involves the application or wear of devices designed to mechanically support knees with OA. These include gait aids, bracing, taping, orthotics and footwear. The literature regarding efficacy of mechanical interventions has been conflicting or inconclusive, and this may be because certain subgroups with knee OA respond better to mechanical interventions. Our primary aim is to identify subgroups with knee OA who respond favourably to mechanical interventions.Methods and analysisWe will conduct a systematic review to identify randomised clinical trials of any mechanical intervention for the treatment of knee OA. We will invite lead authors of eligible studies to share individual participant data (IPD). We will perform an IPD meta-analysis for each type of mechanical intervention to evaluate efficacy, with our main outcome being pain. Where IPD are not available, this will be achieved using aggregate data. We will then evaluate five potential treatment effect modifiers using a two-stage approach. If data permit, we will also evaluate whether biomechanics mediate the effects of mechanical interventions on pain in knee OA.Ethics and disseminationNo new data will be collected in this study. We will adhere to institutional, national and international regulations regarding the secure and confidential sharing of IPD, addressing ethics as indicated. We will disseminate findings via international conferences, open-source publication in peer-reviewed journals and summaries posted on websites serving the public and clinicians.PROSPERO registration numberCRD42020155466.

scholarly journals What’s the rate of knee osteoarthritis 10 years after anterior cruciate ligament injury? An updated systematic review

2019 ◽  
Vol 53 (18) ◽  
pp. 1162-1167 ◽  
Author(s):  
Marthe Mehus Lie ◽  
May Arna Risberg ◽  
Kjersti Storheim ◽  
Lars Engebretsen ◽  
Britt Elin Øiestad
Keyword(s):  
Systematic Review ◽  
Anterior Cruciate Ligament ◽  
Knee Osteoarthritis ◽  
Methodological Quality ◽  
Cruciate Ligament ◽  
Acl Tear ◽  
Knee Oa ◽  
Symptomatic Knee ◽  
Anterior Cruciate

BackgroundThis updated systematic review reports data from 2009 on the prevalence, and risk factors, for knee osteoarthritis (OA) more than 10 years after anterior cruciate ligament (ACL) tear.MethodsWe systematically searched five databases (PubMed, EMBASE, AMED, Cinahl and SPORTDiscus) for prospective and retrospective studies published after 1 August 2008. Studies were included if they investigated participants with ACL tear (isolated or in combination with medial collateral ligament and/or meniscal injuries) and reported symptomatic and/or radiographic OA at a minimum of 10 years postinjury. We used a modified version of the Downs and Black checklist for methodological quality assessment and narrative synthesis to report results. The study protocol was registered in PROSPERO.ResultsForty-one studies were included. Low methodological quality was revealed in over half of the studies. At inclusion, age ranged from 23 to 38 years, and at follow-up from 31 to 51 years. Sample sizes ranged from 18 to 780 participants. The reported radiographic OA prevalence varied between 0% and 100% >10 years after injury, regardless of follow-up time. The studies with low and high methodological quality reported a prevalence of radiographic OA between 0%–100% and 1%–80%, respectively. One study reported symptomatic knee OA for the tibiofemoral (TF) joint (35%), and one study reported symptomatic knee OA for the patellofemoral (PF) joint (15%). Meniscectomy was the only consistent risk factor determined from the data synthesis.ConclusionRadiographic knee OA varied between 0% and 100% in line with our previous systematic review from 2009. Symptomatic and radiographic knee OA was differentiated in two studies only, with a reported symptomatic OA prevalence of 35% for the TF joint and 15% for PF joint. Future cohort studies need to include measurement of symptomatic knee OA in this patient group.PROSPERO registration numberCRD42016042693.

scholarly journals US-Approved Intra-Articular Hyaluronic Acid Injections are Safe and Effective in Patients with Knee Osteoarthritis: Systematic Review and Meta-Analysis of Randomized, Saline-Controlled Trials

2013 ◽  
Vol 6 ◽  
pp. CMAMD.S12743 ◽  
Author(s):  
Larry E. Miller ◽  
Jon E. Block
Keyword(s):  
Systematic Review ◽  
Hyaluronic Acid ◽  
Knee Osteoarthritis ◽  
Knee Pain ◽  
Meta Analysis ◽  
Controlled Trials ◽  
Serious Adverse Events ◽  
Safety Outcome ◽  
Symptomatic Knee Osteoarthritis ◽  
Symptomatic Knee

We conducted a systematic review and meta-analysis of randomized saline-controlled trials to determine the safety and efficacy of US-approved intra-articular hyaluronic acid (IAHA) injections for symptomatic knee osteoarthritis. A total of 29 studies representing 4,866 unique subjects (IAHA: 2,673, saline: 2,193) were included. IAHA injection resulted in very large treatment effects between 4 and 26 weeks for knee pain and function compared to pre-injection values, with standardized mean difference (SMD) values ranging from 1.07–1.37 (all P < 0.001). Compared to saline controls, SMDs with IAHA ranged from 0.38–0.43 for knee pain and 0.32–0.34 for knee function (all P < 0.001). There were no statistically significant differences between IAHA and saline controls for any safety outcome, including serious adverse events (SAEs) ( P = 0.12), treatment-related SAEs ( P = 1.0), study withdrawal ( P = 1.0), and AE-related study withdrawal ( P = 0.46). We conclude that intra-articular injection of US-approved HA products is safe and efficacious in patients with symptomatic knee osteoarthritis.

scholarly journals Comparison of Efficacy among Three Radiofrequency Ablation Techniques for Treating Knee Osteoarthritis: A Systematic Review and Meta-Analysis

2021 ◽  
Vol 18 (14) ◽  
pp. 7424
Author(s):  
Shih-Hsiang Chou ◽  
Po-Chih Shen ◽  
Cheng-Chang Lu ◽  
Zi-Miao Liu ◽  
Yin-Chun Tien ◽  
...  
Keyword(s):  
Systematic Review ◽  
Radiofrequency Ablation ◽  
Knee Osteoarthritis ◽  
Baseline Level ◽  
Meta Analysis ◽  
Cochrane Library ◽  
Invasive Treatment ◽  
Knee Oa ◽  
Before And After

Radiofrequency ablation (RFA) was first introduced for treating knee osteoarthritis (OA) in 2010 and has emerged as a minimally invasive treatment option. Three RFA techniques have been adopted for treating knee OA, including conventional, pulsed, and cooled RFA. However, the efficacy among different RFA techniques in the treatment of knee OA is still unclear. Three electronic databases were systematically searched for relevant articles, including PubMed, Embase, and Cochrane Library. A meta-analysis of articles that investigated the use of RFA techniques in the treatment of knee OA was conducted to pool the effect size in pain before and after treatment. A total of 20 eligible articles (including 605 patients) were included for our meta-analysis. After treatment, the patients had significant improvements in pain for all three RFA techniques when compared with the baseline level for the 1, 3-, and 6-month follow-ups (p < 0.00001). However, there were no significant differences in the efficacy among the three RFA techniques for all follow-up visits (p > 0.05). The three RFA techniques demonstrated a significant improvement in pain for up to 6 months after treatment. Comparing the efficacy of the three RFA techniques in the treatment of knee OA, our results showed that no significant differences in pain relief among the three RFA techniques were observed at the 1-, 3-, 6, and 12-month follow-up visits.

scholarly journals Efficacy and safety of turmeric extracts in knee osteoarthritis: protocol for a systematic review and meta-analysis of randomised controlled trials

2020 ◽  
Author(s):  
Zhiqiang Wang ◽  
Ambrish Singh ◽  
Benny Antony
Keyword(s):  
Systematic Review ◽  
Knee Osteoarthritis ◽  
Methodological Quality ◽  
Randomised Controlled Trials ◽  
Meta Analysis ◽  
Risk Of Bias ◽  
Efficacy And Safety ◽  
Knee Oa ◽  
Randomised Controlled

AbstractTurmeric extracts have been used as a remedy for treating arthritis in traditional medicine. Recent years have witnessed the rise of different extracts from turmeric and randomised clinical trials (RCTs) evaluating the efficacy and safety of these extracts for the treatment of knee osteoarthritis (OA). This planned systematic review and meta-analysis aims to assess the efficacy and safety of turmeric extracts for the treatment of knee OA. Biomedical databases such as PubMed, Scopus, and Embase will be searched for RCTs reporting safety and efficacy of turmeric extracts for the treatment of knee OA. Cochrane risk of bias tool will be used to assess the methodological quality of the included studies, and a meta-analysis will be performed to pool the effect estimates.

Sign in / Sign up

Export Citation Format

Share Document