<p>Scientific evidence demonstrates a strong relation between gait abnormalities and osteoarthritis, highlighting the need for a gait quality index for rapid osteoarthritis monitoring. Using a dataset on hip osteoarthritis, including 80 healthy individuals and 106 patients classified by Kellgren–Lawrence (KL) grading scale with pre- and post-arthroplasty surgery data, we introduced a linear model and a Hip Osteoarthritis Index (HOI) based on two kinematic features: (1) hip-knee angular velocity area and (2) hip maximum angular velocity. Additionally, we employed multi-layer perceptron (MLP) and deep recurrent neural network (RNN) models to evaluate the efficacy of our linear model. For healthy-patient, affected-unaffected leg, and severity grades classifications the accuracy of all models ranged around <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="85" /> </InlineMediaObject> <EquationSource Format="TEX">\(86.5\pm 2.5\%\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="85" /> </InlineMediaObject> <EquationSource Format="TEX">\(89.5\pm 1.5\%\)</EquationSource> </InlineEquation>, and <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq3.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="85" /> </InlineMediaObject> <EquationSource Format="TEX">\(40.5\pm 1.5\%\)</EquationSource> </InlineEquation>, respectively, with no significant differences (<InlineEquation ID="IEq4"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq4.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="62" /> </InlineMediaObject> <EquationSource Format="TEX">\(p>0.16\)</EquationSource> </InlineEquation>). HOI is highly correlated with KL grades (<InlineEquation ID="IEq5"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq5.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="60" /> </InlineMediaObject> <EquationSource Format="TEX">\(r=0.76\)</EquationSource> </InlineEquation>) and affected-unaffected leg of patients (<InlineEquation ID="IEq6"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq6.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="60" /> </InlineMediaObject> <EquationSource Format="TEX">\(r=0.69\)</EquationSource> </InlineEquation>). HOI differences (<InlineEquation ID="IEq7"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq7.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="77" /> </InlineMediaObject> <EquationSource Format="TEX">\(p^<0.002\)</EquationSource> </InlineEquation>) were significant for (1) healthy and patients (pre-/post-surgery and affected/unaffected legs), (2) pre- and post-surgery of affected legs across severity grades, and (3) affected and unaffected legs, pre-surgery. Post-surgery, the gait pattern became more symmetric, with no significant HOI difference between affected and unaffected legs (<InlineEquation ID="IEq8"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq8.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="69" /> </InlineMediaObject> <EquationSource Format="TEX">\(p=0.052\)</EquationSource> </InlineEquation>). The affected legs’ HOI moves toward healthy individuals (<InlineEquation ID="IEq9"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_10074_Article_IEq9.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="85" /> </InlineMediaObject> <EquationSource Format="TEX">\(p^<0.0001\)</EquationSource> </InlineEquation>), indicating a more natural gait. The comparable results of the models, along with significant HOI differences between healthy and patients, pre- and post-surgery, and affected and unaffected legs, as well as the high correlation of HOI with KL grades, suggest HOI as an ideal candidate for hip osteoarthritis assessment.</p>

Development of a hip osteoarthritis index for gait quality assessment: a data-driven comparative study

期刊论文
出版模式：

开放获取
发表日期：

2025年8月5日

查看全文

Kamyar Rahmani,
Mansour Davoudi,
Mohammad Sajjad Alamdar,
Rezvan Nasiri

摘要

Scientific evidence demonstrates a strong relation between gait abnormalities and osteoarthritis, highlighting the need for a gait quality index for rapid osteoarthritis monitoring. Using a dataset on hip osteoarthritis, including 80 healthy individuals and 106 patients classified by Kellgren–Lawrence (KL) grading scale with pre- and post-arthroplasty surgery data, we introduced a linear model and a Hip Osteoarthritis Index (HOI) based on two kinematic features: (1) hip-knee angular velocity area and (2) hip maximum angular velocity. Additionally, we employed multi-layer perceptron (MLP) and deep recurrent neural network (RNN) models to evaluate the efficacy of our linear model. For healthy-patient, affected-unaffected leg, and severity grades classifications the accuracy of all models ranged around \(86.5\pm 2.5\%\) , \(89.5\pm 1.5\%\) , and \(40.5\pm 1.5\%\) , respectively, with no significant differences ( \(p>0.16\) ). HOI is highly correlated with KL grades ( \(r=0.76\) ) and affected-unaffected leg of patients ( \(r=0.69\) ). HOI differences ( \(p^*<0.002\) ) were significant for (1) healthy and patients (pre-/post-surgery and affected/unaffected legs), (2) pre- and post-surgery of affected legs across severity grades, and (3) affected and unaffected legs, pre-surgery. Post-surgery, the gait pattern became more symmetric, with no significant HOI difference between affected and unaffected legs ( \(p=0.052\) ). The affected legs’ HOI moves toward healthy individuals ( \(p^*<0.0001\) ), indicating a more natural gait. The comparable results of the models, along with significant HOI differences between healthy and patients, pre- and post-surgery, and affected and unaffected legs, as well as the high correlation of HOI with KL grades, suggest HOI as an ideal candidate for hip osteoarthritis assessment.