scholarly journals Prediction of the Impact of Physical Exercise on Knee Osteoarthritis Patients using Kinematic Signal Analysis and Decision Trees

Author(s):  
M. Mezghani ◽  
N. Hagemeister ◽  
M. Kouki ◽  
Y. Ouakrim ◽  
A. Fuentes ◽  
...  
2021 ◽  
Vol 11 (2) ◽  
pp. 834
Author(s):  
Marwa Mezghani ◽  
Nicola Hagemeister ◽  
Youssef Ouakrim ◽  
Alix Cagnin ◽  
Alexandre Fuentes ◽  
...  

Measuring knee biomechanics provides valuable clinical information for defining patient-specific treatment options, including patient-oriented physical exercise programs. It can be done by a knee kinesiography test measuring the three-dimensional rotation angles (3D kinematics) during walking, thus providing objective knowledge about knee function in dynamic and weight-bearing conditions. The purpose of this study was to assess whether 3D kinematics can be efficiently used to predict the impact of a physical exercise program on the condition of knee osteoarthritis (OA) patients. The prediction was based on 3D knee kinematic data, namely flexion/extension, adduction/abduction and external/internal rotation angles collected during a treadmill walking session at baseline. These measurements are quantifiable information suitable to develop automatic and objective methods for personalized computer-aided treatment systems. The dataset included 221 patients who followed a personalized therapeutic physical exercise program for 6 months and were then assigned to one of two classes, Improved condition (I) and not-Improved condition (nI). A 10% improvement in pain was needed at the 6-month follow-up compared to baseline to be in the improved group. The developed model was able to predict I and nI with 84.4% accuracy for men and 75.5% for women using a decision tree classifier trained with 3D knee kinematic data taken at baseline and a 10-fold validation procedure. The models showed that men with an impaired control of their varus thrust and a higher pain level at baseline, and women with a greater amplitude of internal tibia rotation were more likely to report improvements in their pain level after 6 months of exercises. Results support the effectiveness of decision trees and the relevance of 3D kinematic data to objectively predict knee OA patients’ response to a treatment consisting of a physical exercise program.


2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 1337.2-1337
Author(s):  
T. W. Swinnen ◽  
M. Willems ◽  
I. Jonkers ◽  
F. P. Luyten ◽  
J. Vanrenterghem ◽  
...  

Background:The personal and societal burden of knee osteoarthritis (KOA) urges the research community to identify factors that predict its onset and progression. A mechanistic understanding of disease is currently lacking but needed to develop targeted interventions. Traditionally, risk factors for KOA are termed ‘local’ to the joint or ‘systemic’ referring to whole-body systems. There are however clear indications in the scientific literature that contextual factors such as socioeconomic position merit further scientific scrutiny, in order to justify a more biopsychosocial view on risk factors in KOA.Objectives:The aims of this systematic literature review were to assess the inclusion of socioeconomic factors in KOA research and to identify the impact of socioeconomic factors on pain and function in KOA.Methods:Major bibliographic databases, namely Medline, Embase, CINAHL, Web of Science and Cochrane, were independently screened by two reviewers (plus one to resolve conflicts) to identify research articles dealing with socioeconomic factors in the KOA population without arthroplasty. Included studies had to quantify the relationship between socioeconomic factors and pain or function. Main exclusion criteria were: a qualitative design, subject age below 16 years and articles not written in English or Dutch. Methodological quality was assessed via the Cochrane risk of bias tools for randomized (ROB-II) and non-randomized intervention studies (ROBIN-I) and the Newcastle-Ottawa Scale for assessing the quality of non-randomised studies. Due to heterogeneity of studies with respect to outcomes assessed and analyses performed, no meta-analysis was performed.Results:Following de-duplication, 7639 articles were available for screening (120 conflicts resolved without a third reader). In 4112 articles, the KOA population was confirmed. 1906 (25%) were excluded because of knee arthroplasty and 1621 (21%) because of other issues related to the population definition. Socioeconomic factors could not be identified in 4058 (53%) papers and were adjusted for in 211 (3%) articles. In the remaining papers covering pain (n=110) and/or function (n=81), education (62%) and race (37%) were most frequently assessed as socioeconomic factors. A huge variety of mainly dichotomous or ordinal socioeconomic outcomes was found without further methodological justification nor sensitivity analysis to unravel the impact of selected categories. Although the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) was the most popular instrument to assess pain and function, data pooling was not possible as socioeconomic factors estimates were part of multilevel models in most studies. Overall results showed that lower education and African American race were consistent predictors of pain and poor function, but those effects diminished or disappeared when psychological aspects (e.g. discrimination) or poverty estimates were taken into account. When function was assessed using self-reported outcomes, the impact of socioeconomic factors was more clear versus performance-based instruments. Quality of research was low to moderate and the moderating or mediating impact of socioeconomic factors on intervention effects in KOA is understudied.Conclusion:Research on contextual socioeconomic factors in KOA is insufficiently addressed and their assessment is highly variable methodologically. Following this systematic literature review, we can highlight the importance of implementing a standardised and feasible set of socioeconomic outcomes in KOA trials1, as well as the importance of public availability of research databases including these factors. Future research should prioritise the underlying mechanisms in the effect of especially education and race on pain and function and assess its impact on intervention effects to fuel novel (non-)pharmacological approaches in KOA.References:[1]Smith TO et al. The OMERACT-OARSI Core Domain Set for Measurement in Clinical Trials of Hip and/or Knee Osteoarthritis J Rheumatol 2019. 46:981–9.Disclosure of Interests:None declared.


Author(s):  
Valentina Bucciarelli ◽  
Francesco Bianco ◽  
Francesco Mucedola ◽  
Andrea Di Blasio ◽  
Pascal Izzicupo ◽  
...  

Background: Menopause is associated with negative cardiovascular adaptations related to estrogen depletion, which could be counteracted by physical exercise (PhE). However, the impact of total adherence-rate (TA) to PhE and sedentary time (SedT) on cardiometabolic profile in this population has not been elucidated. Methods: For 13-weeks, 43 women (57.1 ± 4.7 years) participated in a 4-days-a-week moderate-intensity walking training. They underwent laboratory, anthropometric and echocardiographic assessment, before and after training (T0–T1). Spontaneous physical activity (PhA) was assessed with a portable multisensory device. The sample was divided according to TA to PhE program: <70% (n = 17) and ≥70% (n = 26). Results: TA ≥ 70% group experienced a significant T1 improvement of relative wall thickness (RWT), diastolic function, VO2max, cortisol, cortisol/dehydroandrostenedione-sulphate ratio and serum glucose. After adjusting for SedT and 10-min bouts of spontaneous moderate-to-vigorous PhA, TA ≥ 70% showed the most significant absolute change of RWT and diastolic function, body mass index, weight and cortisol. TA ≥ 70% was major predictor of RWT and cortisol improvement. Conclusions: In a group of untrained, postmenopausal women, a high TA to a 13-weeks aerobic PhE program confers a better improvement in cardiometabolic profile, regardless of SedT and PhA levels.


2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 107.1-108
Author(s):  
K. Zobbe ◽  
S. M. Nielsen ◽  
R. Christensen ◽  
A. Overgaard ◽  
H. Gudbergsen ◽  
...  

Background:There is a strong association between gout and obesity. Lowering urate is the cornerstone of gout management [1] and urate levels correlate strongly with central obesity. Previous studies suggest that weight loss has a positive effect on serum urate, however, the studies are sparse and small [2].Objectives:To assess the impact of an initial low-calorie diet-induced weight loss and subsequent randomisation to the body weight-lowering drug liraglutide (a glucagon-like peptide 1 receptor agonist) or placebo on serum urate levels.Methods:In the LOSE-IT trial (NCT02905864), a randomised, double-blinded, placebo-controlled, parallel group, single-centre trial [3], 156 obese individuals with knee osteoarthritis, but without gout, were offered an initial 8-week intensive diet intervention (week -8 to 0) on Cambridge Weight Plan (800-1000 kcal/day) followed by a weight loss maintenance period in which participants were randomised to either liraglutide 3 mg/day or placebo for 52 weeks. We conducted a secondary analysis of blood samples collected at week -8, 0 and 52. The primary outcome measure was change in serum urate. We used paired t-test for the change from week -8 to 0, and for change from week 0 to 52 we used an ANCOVA model adjusted for stratification factors (sex, age category and obesity class), and the level of the outcome at baseline. Data were analysed as observed (i.e. no imputation of missing data).Results:156 individuals were randomised and 155 had blood samples taken at baseline. In the initial intensive diet intervention period (week -8 to 0) they lost a mean of 12.5 kg (95% CI -13.1 to -11.9, n 156). In the following 52 weeks, the liraglutide group lost an additional 4.1 kg (SE 1.2, n 71) whereas the control group was almost unchanged with a weight loss of 0.2 kg (SE 1.2, n 66). Looking at the main outcome of serum urate levels change, the initial intensive diet resulted in a mean decrease of 0.21 mg/dL (95% CI 0.35 to 0.07, n 155) for the entire cohort. In the following year (week 0 to 52) the liraglutide group exhibited a further mean decrease in serum urate of 0.48 mg/dL (SE 0.11, n 69), whereas the placebo group exhibited a slight decrease in mean serum urate of 0.07 mg/dL (SE 0.12, n 65) resulting in a significant between-group difference of -0.40 mg/dL (95% CI -0.69 to -0.12, n 134) – see Figure 1. Four participants in each group experienced serious adverse events; no deaths were observed.Conclusion:This secondary analysis of the LOSE-IT trial suggests that liraglutide provides a potential novel serum urate lowering drug mechanism in obese patient populations, with potential implication for gout treatment.References:[1]Richette P et al. 2016.Ann Rheum Dis2017;76:29–42.[2]Nielsen SM et al.Ann Rheum Dis2017 76(11):1870-1882.[3]Gudbergsen H et al.BMJ2019. 71–2.Disclosure of Interests:Kristian Zobbe: None declared, Sabrina Mai Nielsen: None declared, Robin Christensen: None declared, Anders Overgaard: None declared, henrik gudbergsen Speakers bureau: Pfizer 2016, Marius Henriksen: None declared, Henning Bliddal Grant/research support from: received research grant fra NOVO Nordic, Consultant of: consultant fee fra NOVO Nordic, Lene Dreyer: None declared, Lisa Stamp: None declared, Filip Krag Knop Shareholder of: Minority shareholder in Antag Therapeutics Aps, Grant/research support from: AstraZeneca, Gubra, Novo Nordisk, Sanofi and Zealand Pharma, Consultant of: Amgen, AstraZeneca, Boehringer Ingelheim, Carmot Therapeutics, Eli Lilly, MSD/Merck, Mundipharma, Novo Nordisk, Sanofi and Zealand Pharma., Speakers bureau: AstraZeneca, Bayer, Boehringer Ingelheim, Eli Lilly, MedImmune, MSD/Merck, Mundipharma, Norgine, Novo Nordisk, Sanofi and Zealand Pharma., Lars Erik Kristensen Consultant of: UCB Pharma (Advisory Board), Sannofi (Advisory Board), Abbvie (Advisory Board), Biogen (Advisory Board), Speakers bureau: AbbVie, Amgen, Biogen, Bristol-Myers Squibb, Celgene, Eli Lilly, Gilead, Forward Pharma, Janssen Pharmaceuticals, MSD, Novartis, Pfizer, and UCB Pharma


BMC Neurology ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Nazanin Razazian ◽  
Mohsen Kazeminia ◽  
Hossein Moayedi ◽  
Alireza Daneshkhah ◽  
Shamarina Shohaimi ◽  
...  

2019 ◽  
Vol 31 (2) ◽  
pp. 122-137
Author(s):  
Supraja Sankaran ◽  
Kris Luyten ◽  
Dominique Hansen ◽  
Paul Dendale ◽  
Karin Coninx

Abstract Physical exercise training and medication compliance are primary components of cardiac rehabilitation. When rehabilitating independently at home, patients often fail to comply with their prescribed medication and find it challenging to interpret exercise targets or be aware of the expected efforts. Our work aims to assist cardiac patients in understanding their condition better, promoting medication adherence and motivating them to achieve their exercise targets in a tele-rehabilitation setting. We introduce a patient-centric intelligible visualization approach to present prescribed medication and exercise targets to patients. We assessed efficacy of intelligible visualizations on patients’ comprehension in two lab studies. We evaluated the impact on patient motivation and health outcomes in field studies. Patients were able to adhere to medication prescriptions, manage their physical exercises, monitor their progress and gained better self-awareness on how they achieved their rehabilitation targets. Patients confirmed that the intelligible visualizations motivated them to achieve their targets better. We observed an improvement in overall physical activity levels and health outcomes of patients. Research Highlights Presents challenges currently faced in cardiac tele-rehabilitation. Demonstrates how intelligibility was applied to two core aspects of cardiac rehabilitation- promoting medication adherence and physical exercise training. Lab., field and clinical studies to demonstrate efficacy of intelligible visualization, impact on patient motivation and resultant health outcomes. Reflection on how similar HCI approaches could be leveraged for technology-supported management of critical health conditions such as cardiac diseases.


2014 ◽  
Vol 41 (10) ◽  
pp. 2068-2077 ◽  
Author(s):  
Brian C. Focht ◽  
Matthew J. Garver ◽  
Steven T. Devor ◽  
Justin Dials ◽  
Alexander R. Lucas ◽  
...  

Objective.To compare the effects of a group-mediated cognitive behavioral exercise intervention (GMCB) with traditional center-based exercise therapy (TRAD) on objectively assessed levels of physical activity (PA) and mobility in sedentary patients with knee osteoarthritis (OA).Methods.The Improving Maintenance of Physical Activity in Knee Osteoarthritis Trial-Pilot (IMPACT-P) was a 12-month, 2-arm, single-blind, randomized controlled pilot study designed to compare the effects of GMCB and TRAD on 80 sedentary patients with knee OA with self-reported difficulty in daily activities [mean age 63.5 yrs, 84% women, mean body mass index (BMI) 32.7 kg/m2]. Objective assessments of PA (LIFECORDER Plus Accelerometer) and mobility (400-m walk) were obtained at baseline, 3 months, and 12 months by study personnel blinded to participants’ treatment assignment.Results.Intent to treat 2 (treatment: GMCB and TRAD) × 2 (time: 3 mos and 12 mos) analyses of covariance of controlling for baseline, age, sex, and BMI-adjusted change in the outcomes demonstrated that the GMCB intervention yielded significantly greater increases in PA (p < 0.01) and a nonsignificant yet more favorable improvement in mobility (p = 0.09) relative to TRAD. Partial correlation analyses also revealed that change in PA was significantly correlated with the 400-m walk performance at 3-month (r = −0.51, p < 0.01) and 12-month (r = −0.40, p < 0.01) followup assessments.Conclusion.Findings from the IMPACT-P trial suggest that the GMCB treatment resulted in significantly greater improvement in PA and nonsignificant yet more favorable change in mobility relative to TRAD.


2018 ◽  
Vol 1 (46) ◽  
pp. 11-15
Author(s):  
Jakub Szwed ◽  
Michał Kowara ◽  
Marcin Grabowski

The aim of this article is to demonstrate the impact of physical exercise on the development of arrhytmias in athletes. The studies show that this relation exist and concerns endurance sports practiced for a long time. In addition, this article contains review of the most common arrhythmias in athletes and appropriate recommendations. The time of arrhythmias onset depends on the presence of structural heart diseases. If the cardiac disorder is absent the arrhythmias appear at the age 40-50. If the structural heart diseases exist, the arrhythmias occur in young athletes and are more dangerous (can lead to sudden cardiac arrest). The most common arrhythmia in endurance athletes is atrial fibrillation. In order to avoid negative results of endurance sports, such as cardiac arrhythmias, the reliable examinations are necessary, especially to exclude structural cardiac diseases. These examinations should be undertaken before initiation of endurance sport training and routinely later, in course of follow-up.


Sign in / Sign up

Export Citation Format

Share Document