A machine learning approach to knee osteoarthritis phenotyping: data from the FNIH Biomarkers Consortium

Predicting Knee Joint Contact Forces During Normal Walking Using Kinematic Inputs With a Long-Short Term Neural Network

Knee joint contact forces are commonly estimated via surrogate measures (i.e., external knee adduction moments or musculoskeletal modeling). Despite its capabilities, modeling is not optimal for clinicians or persons with limited experience. The purpose of this study was to design a novel prediction method for knee joint contact forces that is simplistic in terms of required inputs. This study included marker trajectories and instrumented knee forces during normal walking from the "Grand Challenge" (n = 6) and "CAMS" (n = 2) datasets. Inverse kinematics were used to derive stance phase hip (sagittal, frontal, transverse), knee (sagittal, frontal), ankle (sagittal), and trunk (frontal) kinematics. A long-short term memory network (LSTM) was created using matlab to predict medial and lateral knee force waveforms using combinations of the kinematics. The Grand Challenge and CAMS datasets trained and tested the network, respectively. Musculoskeletal modeling forces were derived using static optimization and joint reaction tools in OpenSim. Waveform accuracy was determined as the proportion of variance and root-mean-square error between network predictions and in vivo data. The LSTM network was highly accurate for medial forces (R2 = 0.77, RMSE = 0.27 BW) and required only frontal hip and knee and sagittal hip and ankle kinematics. Modeled medial force predictions were excellent (R2 = 0.77, RMSE = 0.33 BW). Lateral force predictions were poor for both methods (LSTM R2 = 0.18, RMSE = 0.08 BW; modeling R2 = 0.21, RMSE = 0.54 BW). The designed LSTM network outperformed most reports of musculoskeletal modeling, including those reached in this study, revealing knee joint forces can accurately be predicted by using only kinematic input variables.

Characterization of clinical data for patient stratification in moderate osteoarthritis with support vector machines, regulatory network models, and verification against osteoarthritis Initiative data

Knee osteoarthritis (OA) diagnosis is based on symptoms, assessed through questionnaires such as the WOMAC. However, the inconsistency of pain recording and the discrepancy between joint phenotype and symptoms highlight the need for objective biomarkers in knee OA diagnosis. To this end, we study relationships among clinical and molecular data in a cohort of women (n = 51) with Kellgren-Lawrence grade 2-3 knee OA through a Support Vector Machine (SVM) and a regulation network model. Clinical descriptors (i.e., pain catastrophism, depression, functionality, joint pain, rigidity, sensitization and synovitis) are used to classify patients. A Youden's test is performed for each classifier to determine optimal binarization thresholds for the descriptors. Thresholds are tested against patient stratification according to baseline WOMAC data from the Osteoarthritis Initiative, and the mean accuracy is 0.97. For our cohort, the data used as SVM inputs are knee OA descriptors, synovial fluid proteomic measurements (n = 25), and transcription factor activation obtained from regulatory network model stimulated with the synovial fluid measurements. The relative weights after classification reflect input importance. The performance of each classifier is evaluated through ROC-AUC analysis. The best classifier with clinical data is pain catastrophism (AUC = 0.9), highly influenced by funcionality and pain sensetization, suggesting that kinesophobia is involved in pain perception. With synovial fluid proteins used as input, leptin strongly influences every classifier, suggesting the importance of low-grade inflammation. When transcription factors are used, the mean AUC is limited to 0.608, which can be related to the pleomorphic behaviour of osteoarthritic chondrocytes. Nevertheless, funcionality has an AUC of 0.7 with a decisive importance of FOXO downregulation. Though larger and longitudinal cohorts are needed, this unique combination of SVM and regulatory network model shall help to stratify knee OA patients more objectively.

Machine Learning Models for Prediction of Progression of Knee Osteoarthritis: A Comprehensive Analysis

Prediction of the progression of knee osteoarthritis (KOA) is a very challenging task. Early identification of risk factors plays a vital role in diagnosing KOA. Thus, machine learning models are used to predict the progression of KOA. The purpose of the present study is to find out the efficacy of various machine learning models to identify the progression of KOA. A comprehensive literature search was conducted in international databases like Google Scholar, PubMed, Web of Science, and Scopus. Studies published from the year 2010 to May 2023 on the machine learning approach to diagnose KOA were included in the study. A total of 15 studies were selected and analyzed which included machine learning as an approach to diagnose KOA. The present study found that machine learning methods are the best methods to diagnose KOA early. Various methods like deep learning, machine learning, convolutional neural network (CNN), and multi-layer perceptron showed good accuracy in diagnosing its progression. The machine learning approach has attracted significant interest from scientists and researchers and has led to a new automated approach to diagnose KOA, which will help in designing treatment approaches.

Machine learning and deep neural network-based learning in osteoarthritis knee

Osteoarthritis (OA) of the knee joint is considered the commonest musculoskeletal condition leading to marked disability for patients residing in various regions around the globe. Application of machine learning (ML) in doing research regarding OA has brought about various clinical advances viz, OA being diagnosed at preliminary stages, prediction of chances of development of OA among the population, discovering various phenotypes of OA, calculating the severity in OA structure and also discovering people with slow and fast progression of disease pathology, etc. Various publications are available regarding machine learning methods for the early detection of osteoarthritis. The key features are detected by morphology, molecular architecture, and electrical and mechanical functions. In addition, this particular technique was utilized to assess non-interfering, non-ionizing, and in-vivo techniques using magnetic resonance imaging. ML is being utilized in OA, chiefly with the formulation of large cohorts viz, the OA Initiative, a cohort observational study, the Multi-centre Osteoarthritis Study, an observational, prospective longitudinal study and the Cohort Hip & Cohort Knee, an observational cohort prospective study of both hip and knee OA. Though ML has various contributions and enhancing applications, it remains an imminent field with high potential, also with its limitations. Many more studies are to be carried out to find more about the link between machine learning and knee osteoarthritis, which would help in the improvement of making decisions clinically, and expedite the necessary interventions.

Biomarkers for osteoarthritis: Current status and future prospects

Osteoarthritis (OA) is the most common form of arthritis globally and a major cause of pain, physical disability, and loss of economic productivity, with currently no causal treatment available. This review article focuses on current research on OA biomarkers and the potential for using biomarkers in future clinical practice and clinical trials of investigational drugs. We discuss how biomarkers, specifically soluble ones, have a long path to go before reaching clinical standards of care. We also discuss how biomarkers can help in phenotyping and subtyping to achieve enhanced stratification and move toward better-designed clinical trials. We also describe how biomarkers can be used for molecular endotyping and for determining the clinical outcomes of investigational cell-based therapies. Biomarkers have the potential to be developed as surrogate end points in clinical trials and help private-public consortia and the biotechnology and pharmaceutical industries develop more effective and targeted personalized treatments and enhance clinical care for patients with OA.

Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis

Knee osteoarthritis (OA) is a prevalent and disabling disease that can develop over decades. This disease is heterogeneous and involves structural changes in the whole joint, encompassing multiple tissue types. Detecting OA before the onset of irreversible changes is crucial for early management, and this could be achieved by allowing knee tissue visualization and quantifying their changes over time. Although some imaging modalities are available for knee structure assessment, magnetic resonance imaging (MRI) is preferred. This narrative review looks at existing literature, first on MRI-developed approaches for evaluating knee articular tissues, and second on prediction using machine/deep-learning-based methodologies and MRI as input or outcome for early OA diagnosis and prognosis. A substantial number of MRI methodologies have been developed to assess several knee tissues in a semi-quantitative and quantitative fashion using manual, semi-automated and fully automated systems. This dynamic field has grown substantially since the advent of machine/deep learning. Another active area is predictive modelling using machine/deep-learning methodologies enabling robust early OA diagnosis/prognosis. Moreover, incorporating MRI markers as input/outcome in such predictive models is important for a more accurate OA structural diagnosis/prognosis. The main limitation of their usage is the ability to move them in rheumatology practice. In conclusion, MRI knee tissue determination and quantification provide early indicators for individuals at high risk of developing this disease or for patient prognosis. Such assessment of knee tissues, combined with the development of models/tools from machine/deep learning using, in addition to other parameters, MRI markers for early diagnosis/prognosis, will maximize opportunities for individualized risk assessment for use in clinical practice permitting precision medicine. Future efforts should be made to integrate such prediction models into open access, allowing early disease management to prevent or delay the OA outcome.

Knee Osteoarthritis Detection and Severity Classification Using Residual Neural Networks on Preprocessed X-ray Images

One of the most common and challenging medical conditions to deal with in old-aged people is the occurrence of knee osteoarthritis (KOA). Manual diagnosis of this disease involves observing X-ray images of the knee area and classifying it under five grades using the Kellgren-Lawrence (KL) system. This requires the physician's expertise, suitable experience, and a lot of time, and even after that the diagnosis can be prone to errors. Therefore, researchers in the ML/DL domain have employed the capabilities of deep neural network (DNN) models to identify and classify KOA images in an automated, faster, and accurate manner. To this end, we propose the application of six pretrained DNN models, namely, VGG16, VGG19, ResNet101, MobileNetV2, InceptionResNetV2, and DenseNet121 for KOA diagnosis using images obtained from the Osteoarthritis Initiative (OAI) dataset. More specifically, we perform two types of classification, namely, a binary classification, which detects the presence or absence of KOA and secondly, classifying the severity of KOA in a three-class classification. For a comparative analysis, we experiment on three datasets (Dataset I, Dataset II, and Dataset III) with five, two, and three classes of KOA images, respectively. We achieved maximum classification accuracies of 69%, 83%, and 89%, respectively, with the ResNet101 DNN model. Our results show an improved performance from the existing work in the literature.

Sex-specific effects of calving season on joint health and biomarkers in Montana ranchers

BACKGROUND

Agricultural workers have a higher incidence of osteoarthritis (OA), but the etiology behind this phenomenon is unclear. Calving season, which occurs in mid- to late-winter for ranchers, includes physical conditions that may elevate OA risk. Our primary aim was to determine whether OA biomarkers are elevated at the peak of calving season compared to pre-season, and to compare these data with joint health survey information from the subjects. Our secondary aim was to detect biomarker differences between male and female ranchers.

METHODS

During collection periods before and during calving season, male (n = 28) and female (n = 10) ranchers completed joint health surveys and provided samples of blood, urine, and saliva for biomarker analysis. Statistical analyses examined associations between mean biomarker levels and survey predictors. Ensemble cluster analysis identified groups having unique biomarker profiles.

RESULTS

The number of calvings performed by each rancher positively correlated with plasma IL-6, serum hyaluronic acid (HA) and urinary CTX-I. Thiobarbituric acid reactive substances (TBARS), a marker of oxidative stress, was significantly higher during calving season than pre-season and was also correlated with ranchers having more months per year of joint pain. We found evidence of sexual dimorphism in the biomarkers among the ranchers, with leptin being elevated and matrix metalloproteinase-3 diminished in female ranchers. The opposite was detected in males. WOMAC score was positively associated with multiple biomarkers: IL-6, IL-2, HA, leptin, C2C, asymmetric dimethylarginine, and CTX-I. These biomarkers represent enzymatic degradation, inflammation, products of joint destruction, and OA severity.

CONCLUSIONS

The positive association between number of calvings performed by each rancher (workload) and both inflammatory and joint tissue catabolism biomarkers establishes that calving season is a risk factor for OA in Montana ranchers. Consistent with the literature, we found important sex differences in OA biomarkers, with female ranchers showing elevated leptin, whereas males showed elevated MMP-3.

The application of machine learning in early diagnosis of osteoarthritis: a narrative review

Osteoarthritis (OA) is the commonest musculoskeletal disease worldwide, with an increasing prevalence due to aging. It causes joint pain and disability, decreased quality of life, and a huge burden on healthcare services for society. However, the current main diagnostic methods are not suitable for early diagnosing patients of OA. The use of machine learning (ML) in OA diagnosis has increased dramatically in the past few years. Hence, in this review article, we describe the research progress in the application of ML in the early diagnosis of OA, discuss the current trends and limitations of ML approaches, and propose future research priorities to apply the tools in the field of OA. Accurate ML-based predictive models with imaging techniques that are sensitive to early changes in OA ahead of the emergence of clinical features are expected to address the current dilemma. The diagnostic ability of the fusion model that combines multidimensional information makes patient-specific early diagnosis and prognosis estimation of OA possible in the future.

Peripheral Blood DNA Methylation-Based Machine Learning Models for Prediction of Knee Osteoarthritis Progression: Biologic Specimens and Data From the Osteoarthritis Initiative and Johnston County Osteoarthritis Project

OBJECTIVE

The lack of accurate biomarkers to predict knee osteoarthritis (OA) progression is a key unmet need in OA clinical research. The objective of this study was to develop baseline peripheral blood epigenetic biomarker models to predict knee OA progression.

METHODS

Genome-wide buffy coat DNA methylation patterns from 554 individuals from the Osteoarthritis Biomarkers Consortium (OABC) were determined using Illumina Infinium MethylationEPIC 850K arrays. Data were divided into model development and validation sets, and machine learning models were trained to classify future OA progression by knee pain, radiographic imaging, knee pain plus radiographic imaging, and any progression (pain, radiographic, or both). Parsimonious models using the top 13 CpG sites most frequently selected during development were tested on independent samples from participants in the Johnston County Osteoarthritis (JoCo OA) Project (n = 128) and a previously published Osteoarthritis Initiative (OAI) data set (n = 55).

RESULTS

Full models accurately classified future radiographic-only progression (mean ± SEM accuracy 87 ± 0.8%, area under the curve [AUC] 0.94 ± 0.004), pain-only progression (accuracy 89 ± 0.9%, AUC 0.97 ± 0.004), pain plus radiographic progression (accuracy 72 ± 0.7%, AUC 0.79 ± 0.006), and any progression (accuracy 78 ± 0.4%, AUC 0.86 ± 0.004). Pain-only and radiographic-only progressors were not distinguishable (mean ± SEM accuracy 58 ± 1%, AUC 0.62 ± 0.001). Parsimonious models showed similar performance and accurately classified future radiographic progressors in the OABC cohort and in both validation cohorts (mean ± SEM accuracy 80 ± 0.3%, AUC 0.88 ± 0.003 [using JoCo OA Project data], accuracy 80 ± 0.8%, AUC 0.89 ± 0.002 [using previous OAI data]).

CONCLUSION

Our data suggest that pain and structural progression share similar early systemic immune epigenotypes. Further studies should focus on evaluating the pathophysiologic consequences of differential DNA methylation and peripheral blood cell epigenotypes in individuals with knee OA.

Single nucleotide polymorphism genes and mitochondrial DNA haplogroups as biomarkers for early prediction of knee osteoarthritis structural progressors: use of supervised machine learning classifiers

BACKGROUND

Knee osteoarthritis is the most prevalent chronic musculoskeletal debilitating disease. Current treatments are only symptomatic, and to improve this, we need a robust prediction model to stratify patients at an early stage according to the risk of joint structure disease progression. Some genetic factors, including single nucleotide polymorphism (SNP) genes and mitochondrial (mt)DNA haplogroups/clusters, have been linked to this disease. For the first time, we aim to determine, by using machine learning, whether some SNP genes and mtDNA haplogroups/clusters alone or combined could predict early knee osteoarthritis structural progressors.

METHODS

Participants (901) were first classified for the probability of being structural progressors. Genotyping included SNP genes TP63, FTO, GNL3, DUS4L, GDF5, SUPT3H, MCF2L, and TGFA; mtDNA haplogroups H, J, T, Uk, and others; and clusters HV, TJ, KU, and C-others. They were considered for prediction with major risk factors of osteoarthritis, namely, age and body mass index (BMI). Seven supervised machine learning methodologies were evaluated. The support vector machine was used to generate gender-based models. The best input combination was assessed using sensitivity and synergy analyses. Validation was performed using tenfold cross-validation and an external cohort (TASOAC).

RESULTS

From 277 models, two were defined. Both used age and BMI in addition for the first one of the SNP genes TP63, DUS4L, GDF5, and FTO with an accuracy of 85.0%; the second profits from the association of mtDNA haplogroups and SNP genes FTO and SUPT3H with 82.5% accuracy. The highest impact was associated with the haplogroup H, the presence of CT alleles for rs8044769 at FTO, and the absence of AA for rs10948172 at SUPT3H. Validation accuracy with the cross-validation (about 95%) and the external cohort (90.5%, 85.7%, respectively) was excellent for both models.

CONCLUSIONS

This study introduces a novel source of decision support in precision medicine in which, for the first time, two models were developed consisting of (i) age, BMI, TP63, DUS4L, GDF5, and FTO and (ii) the optimum one as it has one less variable: age, BMI, mtDNA haplogroup, FTO, and SUPT3H. Such a framework is translational and would benefit patients at risk of structural progressive knee osteoarthritis.

Predicting severity of cartilage damage in a post-traumatic porcine model: Synovial fluid and gait in a support vector machine

The inflammatory response to joint injury has been thought to play a key role in the development of osteoarthritis. In this preclinical study, we hypothesized that synovial fluid presence of inflammatory cytokines, as well as altered loading on the injured leg, would be associated with greater development of macroscopic cartilage damage after an ACL injury. Thirty-six Yucatan minipigs underwent ACL transection and were randomized to: 1) no further treatment, 2) ACL reconstruction, or 3) scaffold-enhanced ACL restoration. Synovial fluid samples and gait data were obtained pre-operatively and at multiple time points post-operatively. Cytokine levels were measured using a multiplex assay. Macroscopic cartilage assessments were performed following euthanasia at 52 weeks. General estimating equation modeling found the presence of IL-1α, IL-1RA, IL-2, IL-4, IL-6, and IL-10 and MMP-2, MMP-3, MMP-12, and MMP-13 in the synovial fluid was associated with better cartilage outcomes. Higher peak pressure for the surgical hind leg and contralateral hind leg aligned with worse cartilage outcomes. A support vector machine built with synovial fluid and gait metrics also demonstrated cytokine presence was predictive of better cartilage outcomes. In conclusion, this preclinical analysis suggests that synovial fluid devoid of cytokines may be a possible indicator that cartilage is more at risk of becoming pathologic after joint injury.

Use of machine learning in osteoarthritis research: a systematic literature review

OBJECTIVE

The aim of this systematic literature review was to provide a comprehensive and exhaustive overview of the use of machine learning (ML) in the clinical care of osteoarthritis (OA).

METHODS

A systematic literature review was performed in July 2021 using MEDLINE PubMed with key words and MeSH terms. For each selected article, the number of patients, ML algorithms used, type of data analysed, validation methods and data availability were collected.

RESULTS

From 1148 screened articles, 46 were selected and analysed; most were published after 2017. Twelve articles were related to diagnosis, 7 to prediction, 4 to phenotyping, 12 to severity and 11 to progression. The number of patients included ranged from 18 to 5749. Overall, 35% of the articles described the use of deep learning And 74% imaging analyses. A total of 85% of the articles involved knee OA and 15% hip OA. No study investigated hand OA. Most of the studies involved the same cohort, with data from the OA initiative described in 46% of the articles and the MOST and Cohort Hip and Cohort Knee cohorts in 11% and 7%. Data and source codes were described as publicly available respectively in 54% and 22% of the articles. External validation was provided in only 7% of the articles.

CONCLUSION

This review proposes an up-to-date overview of ML approaches used in clinical OA research and will help to enhance its application in this field.

AI MSK clinical applications: cartilage and osteoarthritis

The advancements of artificial intelligence (AI) for osteoarthritis (OA) applications have been rapid in recent years, particularly innovations of deep learning for image classification, lesion detection, cartilage segmentation, and prediction modeling of future knee OA development. This review article focuses on AI applications in OA research, first describing machine learning (ML) techniques and workflow, followed by how these algorithms are used for OA classification tasks through imaging and non-imaging-based ML models. Deep learning applications for OA research, including analysis of both radiographs for automatic detection of OA severity, and MR images for detection of cartilage/meniscus lesions and cartilage segmentation for automatic T₂ quantification will be described. In addition, information on ML models that identify individuals at high risk of OA development will be provided. The future vision of machine learning applications in imaging of OA and cartilage hinges on implementation of AI for optimizing imaging protocols, quantitative assessment of cartilage, and automated analysis of disease burden yielding a faster and more efficient workflow for a radiologist with a higher level of reproducibility and precision. It may also provide risk assessment tools for individual patients, which is an integral part of precision medicine.

diproperm: An R Package for the DiProPerm Test

High-dimensional low sample size (HDLSS) data sets frequently emerge in many biomedical applications. The direction-projection-permutation (DiProPerm) test is a two-sample hypothesis test for comparing two high-dimensional distributions. The DiProPerm test is exact, i.e., the type I error is guaranteed to be controlled at the nominal level for any sample size, and thus is applicable in the HDLSS setting. This paper discusses the key components of the DiProPerm test, introduces the diproperm R package, and demonstrates the package on a real-world data set.

Osteoarthritis complications and the recent therapeutic approaches

The accelerated prevalence of osteoarthritis (OA) disease worldwide and the lack of convenient management led to the frequent search for unprecedented and specific treatment approaches. OA patients usually suffer from many annoying complications that negatively influence their quality of life, especially in the elderly. Articular erosions may lead eventually to the loss of joint function as a whole which occurs over time according to the risk factors presented in each case and the grade of the disease. Conventional therapies are advancing, showing most appropriate results but still greatly associated with many adverse effects and have restricted curative actions as well. Hence, novel management tools are usually required. In this review, we summarized the recent approaches in OA treatment and the role of natural products, dietary supplements and nanogold application in OA treatment to provide new research tracks for more therapeutic opportunities to those who are in care in this field.

Identification of most important features based on a fuzzy ensemble technique: Evaluation on joint space narrowing progression in knee osteoarthritis patients

OBJECTIVE

Feature selection (FS) is a crucial and at the same time challenging processing step that aims to reduce the dimensionality of complex classification or regression problems. Various techniques have been proposed in the literature to address this challenge with emphasis to medical applications. However, each one of the existing FS algorithms come with its own advantages and disadvantages introducing a certain level of bias.

MATERIALS AND METHODS

To avoid bias and alleviate the defectiveness of single feature selection results, an ensemble FS methodology is proposed in this paper that aggregates the results of several FS algorithms (filter, wrapper and embedded ones). Fuzzy logic is employed to combine multiple feature importance scores thus leading to a more robust selection of informative features. The proposed fuzzy ensemble FS methodology was applied on the problem of knee osteoarthritis (KOA) prediction with special emphasis on the progression of joint space narrowing (JSN). The proposed FS methodology was integrated into an end-to-end machine learning pipeline and a thorough experimental evaluation was conducted using data from the Osteoarthritis Initiative (OAI) database. Several classifiers were investigated for their suitability in the task of JSN prediction and the best performing model was then post-hoc analyzed by using the SHAP method.

RESULTS

The results showed that the proposed method presented a better and more stable performance in contrast to other competitive feature selection methods, leading to an average accuracy of 78.14% using XG Boost at 31 selected features. The post-hoc explainability highlighted the important features that contribute to the classification of patients with JSN progression.

CONCLUSIONS

The proposed fuzzy feature selection approach improves the performance of the predictive models by selecting a small optimal subset of features compared to popular feature selection methods.

Soluble biological markers in osteoarthritis

In recent years, markers research has focused on the structural components of cartilage matrix. Specifically, a second generation of degradation markers has been developed against type II collagen neoepitopes generated by specific enzymes. A particular effort has been made to measure the degradation of minor collagens III and X of the cartilage matrix. However, because clinical data, including longitudinal controlled studies, are very scarce, it remains unclear whether they will be useful as an alternative to or in combination with current more established collagen biological markers to assess patients with osteoarthritis (OA). In addition, new approaches using high-throughput technologies allowed to detect new types of markers and improve the knowledge about the metabolic changes linked to OA. The relative advances coming from phenotype research are a first attempt to classify the heterogeneity of OA, and several markers could improve the phenotype characterization. These phenotypes could improve the selection of patients in clinical trials limiting the size of the studies by selecting patients with OA characteristics corresponding to the metabolic pathway targeted by the molecules evaluated. In addition, the inclusion of rapid progressors only in clinical trials would facilitate the demonstration of efficacy of the investigative drug to reduce joint degradation. The combination of selective biochemical markers appears as a promising and cost-effective approach to fulfill this unmet clinical need. Among the various potential roles of biomarkers in OA, their ability to monitor drug efficacy is probably one of the most important, in association with clinical and imaging parameters. Biochemical markers have the unique property to detect changes in joint tissue metabolism within a few weeks.

Common Biochemical and Magnetic Resonance Imaging Biomarkers of Early Knee Osteoarthritis and of Exercise/Training in Athletes: A Narrative Review

Knee osteoarthritis (OA) is the most common joint disease of the world population. Although considered a disease of old age, OA also affects young individuals and, more specifically among them, those practicing knee-joint-loading sports. Predicting OA at an early stage is crucial but remains a challenge. Biomarkers that can predict early OA development will help in the design of specific therapeutic strategies for individuals and, for athletes, to avoid adverse outcomes due to exercising/training regimens. This review summarizes and compares the current knowledge of fluid and magnetic resonance imaging (MRI) biomarkers common to early knee OA and exercise/training in athletes. A variety of fluid biochemical markers have been proposed to detect knee OA at an early stage; however, few have shown similar behavior between the two studied groups. Moreover, in endurance athletes, they are often contingent on the sport involved. MRI has also demonstrated its ability for early detection of joint structural alterations in both groups. It is currently suggested that for optimal forecasting of early knee structural alterations, both fluid and MRI biomarkers should be analyzed as a panel and/or combined, rather than individually.

PREDICTION OF SYMPTOMS PROGRESSION FOR THE PATIENTS WITH KNEE OSTEOARTHRITIS BASED ON THE QUANTITATIVE STRUCTURAL FEATURES: DATA FROM THE FNIH OA BIOMARKERS CONSORTIUM

Cartilage repair can greatly alleviate the symptoms of the patients with knee osteoarthritis (KOA). However, some imaging results suggest that the patients with obvious cartilage repair may receive insignificant or even no improvement in their symptoms. This study aims to explore the possible reasons based on the structural feature of the knee joint and construct the models used to predict the progression of knee joint symptoms. 551 subjects from Osteoarthritis Biomarkers Consortium FNIH Project in the Osteoarthritis Initiative (OAI) were included and divided into training and test sets. A total of 153 structural features from five quantitative structural feature sets were included to access the structural characteristics of the knee joints. The Western Ontario and McMaster Universities (WOMAC) Osteoarthritis Index was used to evaluate the symptoms of the knee joints. A three-step feature selection method were used to screen the structural features. Finally, Naive Bayes (NB), logistic regression (LR), [Formula: see text]-nearest neighbor (KNN), support vector machine (SVM) and random forest (RF) models were constructed based on the selected features, and then compared using the receiver operating characteristic (ROC) curve. The distribution in the demographics and WOMAC symptoms scores of the participants was consistent in the training and test sets. Two demographic features and several structural features were selected using the three-step feature selection method. Among the constructed models, the models used for the progression prediction of pain, stiffness and total scores were better than that of physical function. The performance of RF model was the best while SVM model was the second best, and the performance of the remaining three models in predicting the progression of knee symptoms is indistinguishable. Structural feature-based models for the prediction of knee joint symptoms’ progression were constructed and compared. The constructed model showed good feasibility and accuracy, and may assist clinicians to predict the occurrence or progression of the knee joints symptoms in the evaluation and prognosis of cartilage repair.

Decision Support Systems in Temporomandibular Joint Osteoarthritis: A review of Data Science and Artificial Intelligence Applications

With the exponential growth of computational systems and increased patient data acquisition, dental research faces new challenges to manage a large quantity of information. For this reason, data science approaches are needed for the integrative diagnosis of multifactorial diseases, such as Temporomandibular joint (TMJ) Osteoarthritis (OA). The Data science spectrum includes data capture/acquisition, data processing with optimized web-based storage and management, data analytics involving in-depth statistical analysis, machine learning (ML) approaches, and data communication. Artificial intelligence (AI) plays a crucial role in this process. It consists of developing computational systems that can perform human intelligence tasks, such as disease diagnosis, using many features to help in the decision-making support. Patient's clinical parameters, imaging exams, and molecular data are used as the input in cross-validation tasks, and human annotation/diagnosis is also used as the gold standard to train computational learning models and automatic disease classifiers. This paper aims to review and describe AI and ML techniques to diagnose TMJ OA and data science approaches for imaging processing. We used a web-based system for multi-center data communication, algorithms integration, statistics deployment, and process the computational machine learning models. We successfully show AI and data-science applications using patients' data to improve the TMJ OA diagnosis decision-making towards personalized medicine.

New Trends in Pharmacological Treatments for Osteoarthritis

Osteoarthritis (OA) is the leading cause of function loss and disability among the elderly, with significant burden on the individual and society. It is a severe disease for its high disability rates, morbidity, costs, and increased mortality. Multifactorial etiologies contribute to the occurrence and development of OA. The heterogeneous condition poses a challenge for the development of effective treatment for OA; however, emerging treatments are promising to bring benefits for OA management in the future. This narrative review will discuss recent developments of agents for the treatment of OA, including potential disease-modifying osteoarthritis drugs (DMOADs) and novel therapeutics for pain relief. This review will focus more on drugs that have been in clinical trials, as well as attractive drugs with potential applications in preclinical research. In the past few years, it has been realized that a complex interaction of multifactorial mechanisms is involved in the pathophysiology of OA. The authors believe there is no miracle therapeutic strategy fitting for all patients. OA phenotyping would be helpful for therapy selection. A variety of potential therapeutics targeting inflammation mechanisms, cellular senescence, cartilage metabolism, subchondral bone remodeling, and the peripheral nociceptive pathways are expected to reshape the landscape of OA treatment over the next few years. Precise randomized controlled trials (RCTs) are expected to identify the safety and efficacy of novel therapies targeting specific mechanisms in OA patients with specific phenotypes.

Nuclear magnetic resonance spectroscopy of biofluids for osteoarthritis

BACKGROUND

Osteoarthritis is a common degenerative musculoskeletal disease of synovial joints. It is characterized by a metabolic imbalance resulting in articular cartilage degradation, reduced elastoviscosity of synovial fluid and an altered chondrocyte phenotype. This is often associated with reduced mobility, pain and poor quality of life. Subsequently, with an ageing world population, osteoarthritis is of increasing concern to public health. Nuclear magnetic resonance (NMR) spectroscopy can be applied to characterize the metabolomes of biofluids, determining changes associated with osteoarthritis pathology, identifying potential biomarkers of disease and alterations to metabolic pathways.

SOURCES OF DATA

A comprehensive search of PubMed and Web of Science databases using combinations of the following keywords: 'NMR Spectroscopy', 'Blood', 'Plasma', 'Serum', 'Urine', 'Synovial Fluid' and 'Osteoarthritis' for articles published from 2000 to 2020.

AREAS OF AGREEMENT

The number of urine metabolomics studies using NMR spectroscopy to investigate osteoarthritis is low, whereas the use of synovial fluid is significantly higher. Several differential metabolites have previously been identified and mapped to metabolic pathways involved in osteoarthritis pathophysiology.

AREAS OF CONTROVERSY

Conclusions are sometimes conservative or overinflated, which may reflect the variation in reporting standards. NMR metabolic experimental design may require further consideration, as do the animal models used for such studies.

GROWING POINTS

There are various aspects which require improvement within the field. These include stricter adherence to the Metabolomics Standards Initiative, inclusive of the standardization of metabolite identifications; increased utilization of integrating NMR metabolomics with other 'omic' disciplines; and increased deposition of raw experimental files into open access online repositories, allowing greater transparency and enabling additional future analyses.

AREAS TIMELY FOR DEVELOPING RESEARCH

Overall, this research area could be improved by the inclusion of more heterogeneous cohorts, reflecting varying osteoarthritis phenotypes, and larger group sizes ensuring studies are not underpowered. To correlate local and systemic environments, the use of blood for diagnostic purposes, over the collection of synovial fluid, requires increased attention. This will ultimately enable biomarkers of disease to be determined that may provide an earlier diagnosis, or provide potential therapeutic targets for osteoarthritis, ultimately improving patient prognosis.

Identifying Robust Risk Factors for Knee Osteoarthritis Progression: An Evolutionary Machine Learning Approach

Knee osteoarthritis (KOA) is a multifactorial disease which is responsible for more than 80% of the osteoarthritis disease's total burden. KOA is heterogeneous in terms of rates of progression with several different phenotypes and a large number of risk factors, which often interact with each other. A number of modifiable and non-modifiable systemic and mechanical parameters along with comorbidities as well as pain-related factors contribute to the development of KOA. Although models exist to predict the onset of the disease or discriminate between asymptotic and OA patients, there are just a few studies in the recent literature that focused on the identification of risk factors associated with KOA progression. This paper contributes to the identification of risk factors for KOA progression via a robust feature selection (FS) methodology that overcomes two crucial challenges: (i) the observed high dimensionality and heterogeneity of the available data that are obtained from the Osteoarthritis Initiative (OAI) database and (ii) a severe class imbalance problem posed by the fact that the KOA progressors class is significantly smaller than the non-progressors' class. The proposed feature selection methodology relies on a combination of evolutionary algorithms and machine learning (ML) models, leading to the selection of a relatively small feature subset of 35 risk factors that generalizes well on the whole dataset (mean accuracy of 71.25%). We investigated the effectiveness of the proposed approach in a comparative analysis with well-known FS techniques with respect to metrics related to both prediction accuracy and generalization capability. The impact of the selected risk factors on the prediction output was further investigated using SHapley Additive exPlanations (SHAP). The proposed FS methodology may contribute to the development of new, efficient risk stratification strategies and identification of risk phenotypes of each KOA patient to enable appropriate interventions.

A warning machine learning algorithm for early knee osteoarthritis structural progressor patient screening

Aim

In osteoarthritis (OA) there is a need for automated screening systems for early detection of structural progressors. We built a comprehensive machine learning (ML) model that bridges major OA risk factors and serum levels of adipokines/related inflammatory factors at baseline for early prediction of at-risk knee OA patient structural progressors over time.

Methods

The patient- and gender-based model development used baseline serum levels of six adipokines, three related inflammatory factors and their ratios (36), as well as major OA risk factors [age and bone mass index (BMI)]. Subjects (677) were selected from the Osteoarthritis Initiative (OAI) progression subcohort. The probability values of being structural progressors (PVBSP) were generated using our previously published prediction model, including five baseline structural features of the knee, i.e. two X-rays and three magnetic resonance imaging variables. To identify the most important variables amongst the 47 studied in relation to PVBSP, we employed the ML feature classification methodology. Among five supervised ML algorithms, the support vector machine (SVM) demonstrated the best accuracy and use for gender-based classifiers development. Performance and sensitivity of the models were assessed. A reproducibility analysis was performed with clinical trial OA patients.

Results

Feature selections revealed that the combination of age, BMI, and the ratios CRP/MCP-1 and leptin/CRP are the most important variables in predicting OA structural progressors in both genders. Classification accuracies for both genders in the testing stage (OAI) were >80%, with the highest sensitivity of CRP/MCP-1. Reproducibility analysis showed an accuracy ⩾92%; the ratio CRP/MCP-1 demonstrated the highest sensitivity in women and leptin/CRP in men.

Conclusion

This is the first time that such a framework was built for predicting knee OA structural progressors. Using this automated ML patient- and gender-based model, early prediction of knee structural OA progression can be performed with high accuracy using only three baseline serum biomarkers and two risk factors.

Plain language summary

Machine learning model for early knee osteoarthritis structural progression Knee osteoarthritis is a well-known debilitating disease leading to reduced mobility and quality of life - the main causes of chronic invalidity. Disease evolution can be slow and span many years; however, for some individuals, the progression/evolution can be fast. Current treatments are only symptomatic and conventional diagnosis of osteoarthritis is not very effective in early identification of patients who will progress rapidly. To improve therapeutic approaches, we need a robust prediction model to stratify osteoarthritis patients at an early stage according to risk of joint structure disease progression.We hypothesize that a prediction model using a machine learning system would enable such an early identification of individuals for whom osteoarthritis knee structure will degrade rapidly. Data were from the Osteoarthritis Initiative, a National Institute of Health (United States) databank, and the robustness and generalizability of the developed model was further evaluated using osteoarthritis patients from an external cohort. Using the supervised machine learning system (support vector machine), we developed an automated patient- and gender-based model enabling an early clinical prognosis for individuals at high risk of structural progressive osteoarthritis. In brief, this model employed at baseline (when the subject sees a physician) easily obtained features consisting of the two main osteoarthritis risk factors, age and bone mass index (BMI), in addition to the serum levels of three molecules. Two of these molecules belong to a family of factors names adipokines and one to a related inflammatory factor. In brief, the model comprising a combination of age, BMI, and the ratios CRP/MCP-1 and leptin/CRP were found very robust for both genders, and the high accuracy persists when tested with an external cohort conferring the gender-based model generalizability. This study offers a new automated system for identifying early knee osteoarthritis structural progressors, which will significantly improve clinical prognosis with real time patient monitoring.

Prediction of Joint Space Narrowing Progression in Knee Osteoarthritis Patients

Osteoarthritis is a joint disease that commonly occurs in the knee (KOA). The continuous increase in medical data regarding KOA has triggered researchers to incorporate artificial intelligence analytics for KOA prognosis or treatment. In this study, two approaches are presented to predict the progression of knee joint space narrowing (JSN) in each knee and in both knees combined. A machine learning approach is proposed with the use of multidisciplinary data from the osteoarthritis initiative database. The proposed methodology employs: (i) A clustering process to identify groups of people with progressing and non-progressing JSN; (ii) a robust feature selection (FS) process consisting of filter, wrapper, and embedded techniques that identifies the most informative risk factors; (iii) a decision making process based on the evaluation and comparison of various classification algorithms towards the selection and development of the final predictive model for JSN; and (iv) post-hoc interpretation of the features' impact on the best performing model. The results showed that bounding the JSN progression of both knees can result to more robust prediction models with a higher accuracy (83.3%) and with fewer risk factors (29) compared to the right knee (77.7%, 88 risk factors) and the left knee (78.3%, 164 risk factors), separately.

Diagnosis and Treatment of Hip and Knee Osteoarthritis: A Review

Importance

Osteoarthritis (OA) is the most common joint disease, affecting an estimated more than 240 million people worldwide, including an estimated more than 32 million in the US. Osteoarthritis is the most frequent reason for activity limitation in adults. This Review focuses on hip and knee OA.

Observations

Osteoarthritis can involve almost any joint but typically affects the hands, knees, hips, and feet. It is characterized by pathologic changes in cartilage, bone, synovium, ligament, muscle, and periarticular fat, leading to joint dysfunction, pain, stiffness, functional limitation, and loss of valued activities, such as walking for exercise and dancing. Risk factors include age (33% of individuals older than 75 years have symptomatic and radiographic knee OA), female sex, obesity, genetics, and major joint injury. Persons with OA have more comorbidities and are more sedentary than those without OA. The reduced physical activity leads to a 20% higher age-adjusted mortality. Several physical examination findings are useful diagnostically, including bony enlargement in knee OA and pain elicited with internal hip rotation in hip OA. Radiographic indicators include marginal osteophytes and joint space narrowing. The cornerstones of OA management include exercises, weight loss if appropriate, and education-complemented by topical or oral nonsteroidal anti-inflammatory drugs (NSAIDs) in those without contraindications. Intra-articular steroid injections provide short-term pain relief and duloxetine has demonstrated efficacy. Opiates should be avoided. Clinical trials have shown promising results for compounds that arrest structural progression (eg, cathepsin K inhibitors, Wnt inhibitors, anabolic growth factors) or reduce OA pain (eg, nerve growth factor inhibitors). Persons with advanced symptoms and structural damage are candidates for total joint replacement. Racial and ethnic disparities persist in the use and outcomes of joint replacement.

Conclusions and Relevance

Hip and knee OA are highly prevalent and disabling. Education, exercise and weight loss are cornerstones of management, complemented by NSAIDs (for patients who are candidates), corticosteroid injections, and several adjunctive medications. For persons with advanced symptoms and structural damage, total joint replacement effectively relieves pain.

Understanding osteoarthritis pathogenesis: a multiomics system-based approach

PURPOSE OF REVIEW

Osteoarthritis is a heterogeneous, multifactorial condition regulated by complex biological interactions at multiple levels. Comprehensive understanding of these regulatory interactions is required to develop feasible advances to improve patient outcomes. Improvements in technology have made extensive genomic, transcriptomic, epigenomic, proteomic, and metabolomic profiling possible. This review summarizes findings over the past 20 months related to omics technologies in osteoarthritis and examines how using a multiomics approach is necessary for advancing our understanding of osteoarthritis as a disease to improve precision osteoarthritis treatments.

RECENT FINDINGS

Using the search terms 'genomics' or 'transcriptomics' or 'epigenomics' or 'proteomics' or 'metabolomics' and 'osteoarthritis' from January 1, 2018 to August 31, 2019, we identified advances in omics approaches applied to osteoarthritis. Trends include untargeted whole genome, transcriptome, proteome, and metabolome analyses leading to identification of novel molecular signatures, cell subpopulations and multiomics validation approaches.

SUMMARY

To address the complexity of osteoarthritis, integration of multitissue analyses by multiomics approaches with the inclusion of longitudinal clinical data is necessary for a comprehensive understanding of the disease process, and for appropriate development of efficacious diagnostics, prognostics, and biotherapeutics.

Multivariable modeling of biomarker data from the phase 1 Foundation for the NIH Osteoarthritis Biomarkers Consortium

OBJECTIVE

To determine the optimal combination of imaging and biochemical biomarkers to predict knee osteoarthritis (OA) progression.

METHODS

Nested case-control study from the FNIH OA Biomarkers Consortium of participants with Kellgren-Lawrence grade 1-3 and complete biomarker data (n=539 to 550). Cases were knees with radiographic and pain progression between 24-48 months from baseline. Radiographic progression only was assessed in secondary analyses. Biomarkers (baseline and 24-month changes) with p<0.10 in univariate analysis were selected, including MRI (quantitative (Q) cartilage thickness and volume; semi-quantitative (SQ) MRI markers; bone shape and area; Q meniscal volume), radiographic (trabecular bone texture (TBT)), and serum and/or urine biochemical markers. Multivariable logistic regression models were built using three different step-wise selection methods (complex vs. parsimonious models).

RESULTS

Among baseline biomarkers, the number of locations affected by osteophytes (SQ), Q central medial femoral and central lateral femoral cartilage thickness, patellar bone shape, and SQ Hoffa-synovitis predicted progression in most models (C-statistics 0.641-0.671). 24-month changes in SQ MRI markers (effusion-synovitis, meniscal morphology, and cartilage damage), Q central medial femoral cartilage thickness, Q medial tibial cartilage volume, Q lateral patellofemoral bone area, horizontal TBT (intercept term), and urine NTX-I predicted progression in most models (C-statistics 0.680-0.724). A different combination of imaging and biochemical biomarkers (baseline and 24-month change) predicted radiographic progression only, with higher C-statistics (0.716-0.832).

CONCLUSION

This study highlights the combination of biomarkers with potential prognostic utility in OA disease-modifying trials. Properly qualified, these biomarkers could be used to enrich future trials with participants likely to progress.

Identification of tissue-dependent proteins in knee OA synovial fluid

OBJECTIVE

For many proteins from osteoarthritic synovial fluid, their intra-articular tissue of origin remains unknown. In this study we performed comparative proteomics to identify osteoarthritis-specific and joint tissue-dependent secreted proteins that may serve as candidates for osteoarthritis biomarker development on a tissue-specific basis.

DESIGN

Protein secretomes of cartilage, synovium, Hoffa's fat pad and meniscus from knee osteoarthritis patients were determined using liquid chromatography tandem mass spectrometry, followed by label-free quantification. Validation of tissue-dependent protein species was conducted by ELISA on independent samples. Differential proteomes of osteoarthritic and non-osteoarthritic knee synovial fluids were obtained via similar proteomics approach, followed by ELISA validation.

RESULTS

Proteomics revealed 64 proteins highly secreted from cartilage, 94 from synovium, 37 from Hoffa's fat pad and 21 from meniscus. Proteomic analyses of osteoarthritic vs non-osteoarthritic knee synovial fluid revealed 70 proteins with a relatively higher abundance and 264 proteins with a relatively lower abundance in osteoarthritic synovial fluid. Of the 70 higher abundance proteins, 23 were amongst the most highly expressed in the secretomes of a specific intra-articular tissue measured. Tissue-dependent release was validated for SLPI, C8, CLU, FN1, RARRES2, MATN3, MMP3 and TNC. Abundance in synovial fluid of tissue-dependent proteins was validated for IGF2, AHSG, FN1, CFB, KNG and C8.

CONCLUSIONS

We identified proteins with a tissue-dependent release from intra-articular human knee OA tissues. A number of these proteins also had an osteoarthritis-specific abundance in knee synovial fluid. These proteins may serve as novel candidates for osteoarthritis biomarker development on a tissue-specific basis.

Identification of Risk Factors and Machine Learning-Based Prediction Models for Knee Osteoarthritis Patients

Knee Osteoarthritis (KOA) is a multifactorial disease that causes low quality of life, poor psychology and resignation from life. Furthermore, KOA is a big data problem in terms of data complexity, heterogeneity and size as it has been commonly considered in the literature with most of the reported studies being limited in the amount of information they can adequately process. The aim of this paper is: (i) To provide a robust feature selection (FS) approach that could identify important risk factors which contribute to the prediction of KOA and (ii) to develop machine learning (ML) prediction models for KOA. The current study considers multidisciplinary data from the osteoarthritis initiative (OAI) database, the available features of which come from heterogeneous sources such as questionnaire data, physical activity indexes, self-reported data about joint symptoms, disability and function as well as general health and physical exams’ data. The novelty of the proposed FS methodology lies on the combination of different well-known approaches including filter, wrapper and embedded techniques, whereas feature ranking is decided on the basis of a majority vote scheme to avoid bias. The validation of the selected factors was performed in data subgroups employing seven well-known classifiers in five different approaches. A 74.07% classification accuracy was achieved by SVM on the group of the first fifty-five selected risk factors. The effectiveness of the proposed approach was evaluated in a comparative analysis with respect to classification errors and confusion matrices to confirm its clinical relevance. The results are the basis for the development of reliable tools for the prediction of KOA progression.

The combination of an inflammatory peripheral blood gene expression and imaging biomarkers enhance prediction of radiographic progression in knee osteoarthritis

OBJECTIVE

Predictive biomarkers of progression in knee osteoarthritis are sought to enable clinical trials of structure-modifying drugs. A peripheral blood leukocyte (PBL) inflammatory gene signature, MRI-based bone marrow lesions (BML) and meniscus extrusion scores, meniscal lesions, and osteophytes on X-ray each have been shown separately to predict radiographic joint space narrowing (JSN) in subjects with symptomatic knee osteoarthritis (SKOA). In these studies, we determined whether the combination of the PBL inflammatory gene expression and these imaging findings at baseline enhanced the prognostic value of either alone.

METHODS

PBL inflammatory gene expression (increased mRNA for IL-1β, TNFα, and COX-2), routine radiographs, and 3T knee MRI were assessed in two independent populations with SKOA: an NYU cohort and the Osteoarthritis Initiative (OAI). At baseline and 24 months, subjects underwent standardized fixed-flexion knee radiographs and knee MRI. Medial JSN (mJSN) was determined as the change in medial JSW. Progressors were defined by an mJSN cut-point (≥ 0.5 mm/24 months). Models were evaluated by odds ratios (OR) and area under the receiver operating characteristic curve (AUC).

RESULTS

We validated our prior finding in these two independent (NYU and OAI) cohorts, individually and combined, that an inflammatory PBL inflammatory gene expression predicted radiographic progression of SKOA after adjustment for age, sex, and BMI. Similarly, the presence of baseline BML and meniscal lesions by MRI or semiquantitative osteophyte score on X-ray each predicted radiographic medial JSN at 24 months. The combination of the PBL inflammatory gene expression and medial BML increased the AUC from 0.66 (p = 0.004) to 0.75 (p < 0.0001) and the odds ratio from 6.31 to 19.10 (p < 0.0001) in the combined cohort of 473 subjects. The addition of osteophyte score to BML and PBL inflammatory gene expression further increased the predictive value of any single biomarker. A causal analysis demonstrated that the PBL inflammatory gene expression and BML independently influenced mJSN.

CONCLUSION

The use of the PBL inflammatory gene expression together with imaging biomarkers as combinatorial predictive biomarkers, markedly enhances the identification of radiographic progressors. The identification of the SKOA population at risk for progression will help in the future design of disease-modifying OA drug trials and personalized medicine strategies.

Setting up distinctive outcome measures for each osteoarthritis phenotype

Osteoarthritis (OA) is an evolving chronic joint disease with a huge global impact. Given the intricate nature of the etiopathogenesis and subsequent high heterogeneity in the clinical course of OA, it is crucial to discriminate between etiopathogenic endotypes and clinical phenotypes, especially in the early stages of the disease. In this sense, we propose that an OA phenotype should be properly assessed with a set of outcome measures including those specifically related to the main underlying pathophysiological mechanisms. Thus, each OA phenotype can be related to different and clinically meaningful outcomes. OA phenotyping would lead to an adequate patient stratification in well-designed clinical trials and the discovery of precise therapeutic approaches. A significant effort will be required in this field in light of inconclusive results of clinical trials of tissue-targeting agents for the treatment of OA.

Identification of the most important features of knee osteoarthritis structural progressors using machine learning methods

Objectives:

The aim was to identify the most important features of structural knee osteoarthritis (OA) progressors and classification using machine learning methods.

Methods:

Participants, features and outcomes were from the Osteoarthritis Initiative. Features were from baseline (1107), including articular knee tissues (135) assessed by quantitative magnetic resonance imaging (MRI). OA progressors were ascertained by four outcomes: cartilage volume loss in medial plateau at 48 and 96 months (Prop_CV_48M, 96M), Kellgren–Lawrence (KL) grade ⩾ 2 and medial joint space narrowing (JSN) ⩾ 1 at 48 months. Six feature selection models were used to identify the common features in each outcome. Six classification methods were applied to measure the accuracy of the selected features in classifying the subjects into progressors and non-progressors. Classification of the best features was done using an automatic machine learning interface and the area under the curve (AUC). To prioritize the top five features, sparse partial least square (sPLS) method was used.

Results:

For the classification of the best common features in each outcome, Multi-Layer Perceptron (MLP) achieved the highest AUC in Prop_CV_96M, KL and JSN (0.80, 0.88, 0.95), and Gradient Boosting Machine for Prop_CV_48M (0.70). sPLS showed the baseline top five features to predict knee OA progressors are the joint space width, mean cartilage thickness of the medial tibial plateau and sub-regions and JSN.

Conclusion:

In this comprehensive study using a large number of features (n = 1107) and MRI outcomes in addition to radiological outcomes, we identified the best features and classification methods for knee OA structural progressors. Data revealed baseline X-ray and MRI-based features could predict early OA knee progressors and that MLP is the best classification method.

Risk factors for pain and functional impairment in people with knee and hip osteoarthritis: a systematic review and meta-analysis

OBJECTIVE

To identify risk factors for pain and functional deterioration in people with knee and hip osteoarthritis (OA) to form the basis of a future 'stratification tool' for OA development or progression.

DESIGN

Systematic review and meta-analysis.

METHODS

An electronic search of the literature databases, Medline, Embase, CINAHL, and Web of Science (1990-February 2020), was conducted. Studies that identified risk factors for pain and functional deterioration to knee and hip OA were included. Where data and study heterogeneity permitted, meta-analyses presenting mean difference (MD) and ORs with corresponding 95% CIs were undertaken. Where this was not possible, a narrative analysis was undertaken. The Downs & Black tool assessed methodological quality of selected studies before data extraction. Pooled analysis outcomes were assessed and reported using the Grading of Reccomendation, Assessment, Development and Evaluation (GRADE) approach.

RESULTS

82 studies (41 810 participants) were included. On meta-analysis: there was moderate quality evidence that knee OA pain was associated with factors including: Kellgren and Lawrence≥2 (MD: 2.04, 95% CI 1.48 to 2.81; p<0.01), increasing age (MD: 1.46, 95% CI 0.26 to 2.66; p=0.02) and whole-organ MRI scoring method (WORMS) knee effusion score ≥1 (OR: 1.35, 95% CI 0.99 to 1.83; p=0.05). On narrative analysis: knee OA pain was associated with factors including WORMS meniscal damage ≥1 (OR: 1.83). Predictors of joint pain in hip OA were large acetabular bone marrow lesions (BML; OR: 5.23), chronic widespread pain (OR: 5.02) and large hip BMLs (OR: 4.43).

CONCLUSIONS

Our study identified risk factors for clinical pain in OA by imaging measures that can assist in predicting and stratifying people with knee/hip OA. A 'stratification tool' combining verified risk factors that we have identified would allow selective stratification based on pain and structural outcomes in OA.

PROSPERO REGISTRATION NUMBER

CRD42018117643.

Osteoarthritis of the Temporomandibular Joint can be diagnosed earlier using biomarkers and machine learning

After chronic low back pain, Temporomandibular Joint (TMJ) disorders are the second most common musculoskeletal condition affecting 5 to 12% of the population, with an annual health cost estimated at $4 billion. Chronic disability in TMJ osteoarthritis (OA) increases with aging, and the main goal is to diagnosis before morphological degeneration occurs. Here, we address this challenge using advanced data science to capture, process and analyze 52 clinical, biological and high-resolution CBCT (radiomics) markers from TMJ OA patients and controls. We tested the diagnostic performance of four machine learning models: Logistic Regression, Random Forest, LightGBM, XGBoost. Headaches, Range of mouth opening without pain, Energy, Haralick Correlation, Entropy and interactions of TGF-β1 in Saliva and Headaches, VE-cadherin in Serum and Angiogenin in Saliva, VE-cadherin in Saliva and Headaches, PA1 in Saliva and Headaches, PA1 in Saliva and Range of mouth opening without pain; Gender and Muscle Soreness; Short Run Low Grey Level Emphasis and Headaches, Inverse Difference Moment and Trabecular Separation accurately diagnose early stages of this clinical condition. Our results show the XGBoost + LightGBM model with these features and interactions achieves the accuracy of 0.823, AUC 0.870, and F1-score 0.823 to diagnose the TMJ OA status. Thus, we expect to boost future studies into osteoarthritis patient-specific therapeutic interventions, and thereby improve the health of articular joints.

Differential correlation network analysis identified novel metabolomics signatures for non-responders to total joint replacement in primary osteoarthritis patients

INTRODUCTION

Up to one third of total joint replacement patients (TJR) experience poor surgical outcome.

OBJECTIVES

To identify metabolomic signatures for non-responders to TJR in primary osteoarthritis (OA) patients.

METHODS

A newly developed differential correlation network analysis method was applied to our previously published metabolomic dataset to identify metabolomic network signatures for non-responders to TJR.

RESULTS

Differential correlation networks involving 12 metabolites and 23 metabolites were identified for pain non-responders and function non-responders, respectively.

CONCLUSION

The differential networks suggest that inflammation, muscle breakdown, wound healing, and metabolic syndrome may all play roles in TJR response, warranting further investigation.

Interplay between genetics and epigenetics in osteoarthritis

Research into the molecular genetics of osteoarthritis (OA) has been substantially bolstered in the past few years by the implementation of powerful genome-wide scans that have revealed a large number of novel risk loci associated with the disease. This refreshing wave of discovery has occurred concurrently with epigenetic studies of joint tissues that have examined DNA methylation, histone modifications and regulatory RNAs. These epigenetic analyses have involved investigations of joint development, homeostasis and disease and have used both human samples and animal models. What has become apparent from a comparison of these two complementary approaches is that many OA genetic risk signals interact with, map to or correlate with epigenetic mediators. This discovery implies that epigenetic mechanisms, and their effect on gene expression, are a major conduit through which OA genetic risk polymorphisms exert their functional effects. This observation is particularly exciting as it provides mechanistic insight into OA susceptibility. Furthermore, this knowledge reveals avenues for attenuating the negative effect of risk-conferring alleles by exposing the epigenome as an exploitable target for therapeutic intervention in OA.

Use of Computational Modeling to Study Joint Degeneration: A Review

Osteoarthritis (OA), a degenerative joint disease, is the most common chronic condition of the joints, which cannot be prevented effectively. Computational modeling of joint degradation allows to estimate the patient-specific progression of OA, which can aid clinicians to estimate the most suitable time window for surgical intervention in osteoarthritic patients. This paper gives an overview of the different approaches used to model different aspects of joint degeneration, thereby focusing mostly on the knee joint. The paper starts by discussing how OA affects the different components of the joint and how these are accounted for in the models. Subsequently, it discusses the different modeling approaches that can be used to answer questions related to OA etiology, progression and treatment. These models are ordered based on their underlying assumptions and technologies: musculoskeletal models, Finite Element models, (gene) regulatory models, multiscale models and data-driven models (artificial intelligence/machine learning). Finally, it is concluded that in the future, efforts should be made to integrate the different modeling techniques into a more robust computational framework that should not only be efficient to predict OA progression but also easily allow a patient’s individualized risk assessment as screening tool for use in clinical practice.

Biomarkers in Painful Symptomatic Knee OA Demonstrate That MRI Assessed Joint Damage and Type II Collagen Degradation Products Are Linked to Disease Progression

Background

Osteoarthritis (OA) is the most prevalent arthritis worldwide, but the evolution of pain in relation to joint damage and biochemical markers are not well understood. We evaluated the relation between clinical pain measures and evoked pain in relation to structural damage and biochemical biomarkers in knee OA.

Methods

A cross-sectional study in people with knee OA and healthy controls was conducted. A total of 130 participants with advanced OA requiring total knee replacement (TKR) (n = 78), mild OA having standard care (n = 42) and non-OA controls (n = 6), with four drop-outs were assessed. Pain scoring was performed by the Western Ontario and McMaster Universities OA Index (WOMAC_P) and the Visual Analog Scale (VAS). Pain sensitization was assessed by pain pressure thresholds (PPTs). Knee magnetic resonance imaging (MRI) assessed joint damage using the MRI Knee OA Score (MOAKS). Overall MOAKS scores were created for bone marrow lesions (BMLs), cartilage degradation (CD), and effusion/Hoffa synovitis (tSyn). Type II collagen cleavage products (CTX-II) were determined by ELISA.

Results

The advanced OA group had a mean age of 68.9 ± 7.7 years and the mild group 63.1 ± 9.6. The advanced OA group had higher levels of pain, with mean WOMAC_P of 58.8 ± 21.7 compared with the mild OA group of 40.6 ± 26.0. All OA subjects had pain sensitization by PPT compared with controls (p < 0.05). WOMAC_P correlated with the total number of regions with cartilage damage (nCD) (R = 0.225, p = 0.033) and total number of BMLs (nBML) (R = 0.195, p = 0.065) using body mass index (BMI), age, and Hospital Anxiety and Depression Scale (HADS) as covariates. Levels of CTX-II correlated with tSyn (R = 0.313, p = 0.03), nBML (R = 0.252, p = 0.019), number of osteophytes (R = 0.33, p = 0.002), and nCD (R = 0.218, p = 0.042), using BMI and age as covariates. A multivariate analysis indicated that BMI and HADS were the most significant predictors of pain scores (p < 0.05).

Conclusion

People with both mild and advanced OA show features of pain sensitization. We found that increasing MRI-detected joint damage was associated with higher levels of CTX-II, suggesting that increasing disease severity can be assessed by MRI and CTX-II biomarkers to evaluate OA disease progression.

Phenotypes of osteoarthritis: current state and future implications

In the most recent years, an extraordinary research effort has emerged to disentangle osteoarthritis heterogeneity, opening new avenues for progressing with therapeutic development and unravelling the pathogenesis of this complex condition. Several phenotypes and endotypes have been proposed albeit none has been sufficiently validated for clinical or research use as yet. This review discusses the latest advances in OA phenotyping including how new modern statistical strategies based on machine learning and big data can help advance this field of research.