APPROACH researchers find strong indications for differential phenotypes in osteoarthritis

This biomarker clustering analysis can be used to stratify patients with OA into groups with distinct molecular endotypes, the researchers propose. This approach could potentially drive OA clinical trials stratification and serve as the basis for precision medicine strategies for OA progression in the future.

Title

Osteoarthritis endotype discovery via clustering of biochemical marker data

Authors

Federico Angelini, Paweł Widera, Ali Mobasheri, Joseph Blair, André Struglics, Melanie Uebelhoer, Yves Henrotin, Anne CA Marijnissen, Margreet Kloppenburg, Francisco J Blanco, Ida K Haugen, Francis Berenbaum, Christoph Ladel, Jonathan Larkin, Anne C Bay-Jensen, Jaume Bacardit

The full article is available here.

Background

There is an unmet need for new therapies that target the underlying pathology in osteoarthritis (OA). Computational methods based on unsupervised machine learning have the potential to stratify OA cohorts into subsets that correspond to distinct molecular endotypes.

Objectives

Osteoarthritis (OA) patient stratification is an important challenge to design tailored treatments and drive drug development. Biochemical markers reflecting joint tissue turnover were measured in the IMI-APPROACH cohort at baseline and analysed using a machine learning approach in order to study OA-dominant phenotypes driven by the endotype-related clusters and discover the driving features and their disease-context meaning.

Methods

Data quality assessment was performed to design appropriate data preprocessing techniques. The k-means clustering algorithm was used to find dominant subgroups of patients based on the biochemical markers data. Classification models were trained to predict cluster membership, and Explainable AI techniques were used to interpret these to reveal the driving factors behind each cluster and identify phenotypes. Statistical analysis was performed to compare differences between clusters with respect to other markers in the IMI-APPROACH cohort and the longitudinal disease progression.

Results

Three dominant endotypes were found, associated with three phenotypes: C1) low tissue turnover (low repair and articular cartilage/subchondral bone turnover), C2) structural damage (high bone formation/resorption, cartilage degradation) and C3) systemic inflammation (joint tissue degradation, inflammation, cartilage degradation). The method achieved consistent results in the FNIH/OAI cohort. C1 had the highest proportion of non-progressors. C2 was mostly linked to longitudinal structural progression, and C3 was linked to sustained or progressive pain.

Image: Radar plot showing the median biomarker concentrations for each cluster. When the difference between the medians is statistically different, it is marked with a circle (instead of a dot). The axes show values between the 10% and 90% quantile and are expressed as percentages. The black arcs on the outside show the pathology associated with each biomarker.

(Credit: Jaume Bacardit; plot taken from the paper with permission)

Conclusion

This work supports the existence of differential phenotypes in OA. The biomarker approach could potentially drive stratification for OA clinical trials and contribute to precision medicine strategies for OA progression in the future.