Applied public-private research enabling osteoarthritis clinical headway


About 595 million people worldwide were living with osteoarthritis (OA) in 2020 – a leap of 132.2% since 1990. According to the WHO, more than 344 million people could benefit from rehabilitation, but the drugs that we rely on to treat OA have not changed much in the last twenty years. One reason for this is that it is very hard to tell if a new drug is working or not, so most pharmaceutical companies have reduced or abandoned drug development.

Osteoarthritis presents itself across a spectrum. While one person with OA might experience a small degree of pain moving their knee, another might be unable to walk. It is clear that there should not be a “one size fits all” treatment for OA. Yet within traditional clinical trial settings, it has been common practice to accept all osteoarthritis patients for the same treatment within a clinical trial even though they may present with wildly different symptoms.

This is especially important to remedy because some osteoarthritis treatments – if given to the wrong group – can actually accelerate the progress of this disease. For instance, injecting corticosteroids directly into the knee is a common treatment for OA, but it has been shown to rapidly worsen the condition of some patients. For those patients, treatment with hyaluronic acid (a therapeutic class referred to as ‘viscosupplements’) may be preferable. Although viscosupplements do not tend to tackle pain as effectively as corticosteroids, they work differently by lubricating and cushioning the joint space which may impart a protective effect..

The APPROACH project sought to improve the success rate in osteoarthritis clinical trials by categorising patient profiles into phenotypes. If investigations examine just one phenotype of patients per clinical trial, there might be better results and more targeted, effective therapies may emerge. They collected a wide range of data on more than 10 000 patients and then used bioinformatics and machine learning to analyse it.

Identifying endotypes

The APPROACH project successfully identified three endotypes (i.e. three subgroups with similar molecular characteristics): one which had low tissue turnover and low levels of repair, one which showed more structural damage, and a third which featured systemic inflammation including joint tissue and cartilage degradation. In the future, trials could be conducted that look at just one of these subtypes in order to find a more specific and accurate treatment. This could also impact on the success of clinical trials for osteoarthritis treatment more generally.

Collecting data on more than 10 000 patients

The project amassed a wide range of data thanks to the enthusiastic participation of osteoarthritis patients. Although the project specifically looked at the knee, data was also collected that may be relevant for future studies on hand and hip joint arthritis.

The data collected by the project is available via an integrated bioinformatics platform that functions as a repository of clinical data, biomarker data, images, as well as storage of bio-samples from a broad spectrum of OA patients. The platform is fully accessible via FairPLUS, highlighting a synergy between two IMI projects.

The bioinformatics team that took part in the project were not knowledgeable about osteoarthritis in the beginning, which was an advantage as it meant that there was an internal control preventing bias in the data. For instance, at the start of the project the bioinformatics team were given the data and the machine learning tools rendered predictions. The team working on the machine learning portion of the project had no way of knowing whether the predictions were realistic or not, which meant that they were “double-blind” in a way that the osteoarthritis researchers could not be.

The algorithms developed as part of the APPROACH project were successful in identifying osteoarthritis patients based on a minimum amount of clinical parameters aimed at predicting the likelihood of disease progression within two years. These algorithms combined information on clinical factors, gait, biochemical data, omic and image-based analysis and will be further refined going forwards.

How the data were gathered

Most patients spent at least one full day with the researchers, where they underwent a battery of tests, from gait and motion analyses to urine and blood tests to MRIs and CTs. While the biochemical parameters were gleaned from the urine and blood samples offered by the participants, imaging techniques were very important for these analyses. While an X-ray will only tell a researcher about the bone, MRI and CT scans show damage in the tissues surrounding the bones which can give clues as to which subgroup the patient belongs to.

The gait analyses were carried out by a SME called Dynamic Metrics. Usually such analyses have to be carried out in large labs with specialist equipment, but Dynamic Metrics developed an app which could compute a wide range of data about a person’s gait from just a few small sensors strapped with Velcro around a person’s legs. The data is not as complete as more formal analyses, but it provided the researchers with a wide breadth of information which could be included in the bioinformatics platform without a high cost and without taking up too much of the patients’ time.

What the future holds

The APPROACH consortium partners continue to analyse the data and publications arising from the project are being released regularly. Although the bulk of the work is done, it’s estimated that there is about ten years’ worth of data within the APPROACH datasets still waiting to be analysed. Some of the project’s results will be utilised in another new Horizon project, which is currently awaiting funding, that will examine how to make existing therapies better using stratified patient data. Importantly, the foundation and findings provided by the APPROACH consortium are also expected to foster successful development of the next wave of therapeutics for OA patients.

Achievements & News

Machine learning models outperform traditional selection methods for recruiting osteoarthritis trial patients

Knee osteoarthritis occurs when cartilage in the knee gradually wears away, resulting in pain and stiffness. When running clinical trials for new treatments for osteoarthritis, researchers need to ensure they include the right patients, i.e. people whose condition is likely to get worse during the trial. ###This is because the condition of many trial participants does not change much during the trial anyway, making it hard to assess how effective a treatment is.

When researchers from the APPROACH project were selecting patients for a study to uncover biomarkers of osteoarthritis progression, they wanted to make sure they could select patients who will progress during the observation period.

To do this, they took data from two long-term knee osteoarthritis studies to identify the best performing machine learning models. They found that the model-based selection outperforms the conventional inclusion criteria, reducing by 20–25% the number of patients who show no progression. This result could lead to more efficient clinical trials. Their findings are published in the journal Scientific Reports.

Find out more

A quick, cheap and non-invasive way to measure osteoarthritis

The APPROACH project has found that a commercially-available motion-measuring technology could be used to gauge the extent of osteoarthritis as an alternative or add-on to existing diagnostic options.###

There are a number of ways that osteoarthritis (OA) progression can be measured, including x-rays, MRIs, and questionnaires, but all come with drawbacks. APPROACH studied whether a commercially-available technology called GaitSmart® could offer added value in the evaluation of knee osteoarthritis as a non-invasive, inexpensive and flexible alternative or add-on to help doctors make a diagnosis. The GaitSmart® system involves attaching six sensors to a person’s body and having them walk 15-20m at their own speed. The sensors feed data to a laptop which analyses the results. The whole process takes about 10-15 minutes and is easy to transport and set up.

GaitSmart® was found to measure different features of OA as well as offer more information than what can be gathered through a survey. It was also found that GaitSmart® can offer additional information on the severity of tissue damage as seen on conventional x-rays.

According to the project, GaitSmart® could ultimately be used in a primary care setting, where a patient presenting with suspected knee osteoarthritis could have the test carried out by a healthcare assistant, with a report made available to the GP prior to consultation. The system also allows patients to be more invested in their progress as the changes in the report are easy to identify.

Find out more

APPROACH screens first patient

IMI osteoarthritis project APPROACH has screened the first patient in a clinical study on osteoarthritis of the knee that will pave the way for more personalised treatments for the disease. Over the next two years, 300 patients across Europe will undergo assessments on pain, mobility, cartilage and bone condition, and inflammation. ###Information gathered will help the project to identify biological markers (biomarkers) of disease progression. ‘Currently, all osteoarthritis patients are treated the same. The quality of clinical trials and personalised treatments by doctors will improve tremendously when disease subtypes can be diagnosed. Biomarkers will help to push this forward,’ said Anne Karien Marijnissen, coordinator of the APPROACH clinical study. The project’s seven-strong Patient Council was influential in the set up of the clinical study, collaborating on communications and study design (especially with reference to the burden on study participants) and reviewing the research protocol and patient informed consent forms.


  Show participants on map
EFPIA companies
  • Glaxosmithkline Research And Development LTD., Brentford, Middlesex, United Kingdom
  • Institut De Recherches Internationales Servier Iris, Suresnes, France
  • Merck Kommanditgesellschaft Auf Aktien, Darmstadt, Germany
Universities, research organisations, public bodies, non-profit groups
  • Academisch Ziekenhuis Leiden, Leiden, Netherlands
  • Arthritis Research UK, Chesterfield, United Kingdom
  • Assistance Publique Hopitaux De Paris, Paris, France
  • Centre National De La Recherche Scientifique Cnrs, Paris, France
  • Diakonhjemmet Sykehus As, Oslo, Norway
  • Friedrich-Alexander-Universitaet Erlangen-Nuernberg, Erlangen, Germany
  • Lunds Universitet, Lund, Sweden
  • Oulun Yliopisto, Oulu, Finland
  • Servizo Galego De Saude, Santiago de Compostela, Spain
  • Stichting Lygature, Utrecht, Netherlands
  • Universitair Medisch Centrum Utrecht, Utrecht, Netherlands
  • Universitatsklinikum Erlangen, Erlangen, Germany
  • University Of Leeds, Leeds, United Kingdom
  • University Of Newcastle Upon Tyne, Newcastle upon Tyne, United Kingdom
Small and medium-sized enterprises (SMEs)
  • Artialis SA, Liège (Sart-Tilman), Belgium
  • Dynamic Metrics Limited, Luton, United Kingdom
  • Nordic Bioscience Compound Development A/S, Herlev, Denmark
Patient organisations
  • Stichting Nationaal Reumafonds, Amsterdam, Netherlands
Third parties
  • Universite Paris Cite, Paris, France
Non EFPIA companies
  • Immunodiagnostic Systems Holdings PLC, Boldon, United Kingdom

NameEU funding in €
Academisch Ziekenhuis Leiden712 510
Artialis SA250 000
Assistance Publique Hopitaux De Paris141 050
Centre National De La Recherche Scientifique Cnrs23 000
Diakonhjemmet Sykehus As179 540
Dynamic Metrics Limited185 000
Friedrich-Alexander-Universitaet Erlangen-Nuernberg125 000
Hemics B.V. (left the project)180 000
Lunds Universitet179 000
Medizinische Universitaet Wien (left the project)49 000
Nordic Bioscience Compound Development A/S76 000
Oulun Yliopisto214 000
Servizo Galego De Saude464 000
Stichting Lygature651 000
Stichting Nationaal Reumafonds32 105
Universitair Medisch Centrum Utrecht3 133 262
Universitatsklinikum Erlangen35 000
University Of Leeds150 000
University Of Newcastle Upon Tyne585 000
University Of Surrey (left the project)133 533
Third parties
NameFunding in €
Universite Paris Cite2 000
Total Cost7 500 000