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

Abstract

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.

Epidemiology of osteoarthritis: literature update 2022–2023

“…Models used in this study were able to accurately predict future radiographic and/or pain progression between two and five years from single blood samples collected at baseline. The authors also note that prediction remained high when models were reduced to a smaller number of genomic regions, suggesting that more expensive and larger genome sequencing methods may not be necessary to retain accuracy [33 ▪▪ ]. This study's promising results indicate the viability of more cost-effective methods for accurate OA progression and symptom prediction models, which could be useful tools for determining participant inclusion criteria for DMOAD clinical trials.…”

“…Of note, this study used two entirely independent cohorts, including one from the Johnston County OA Project and one from a previous OAI methylation dataset for external validation of their tested prediction model. Models using OABC data had robust performance in predicting radiographic progression [area under the curve (AUC): 0.94 ± 0.004] and pain progression (AUC 0.97 ± 0.004) [33 ▪▪ ]. Models used in this study were able to accurately predict future radiographic and/or pain progression between two and five years from single blood samples collected at baseline.…”

“…The availability of large image repositories has spurred an increase in research using artificial intelligence (AI) to study OA diagnosis and outcome prediction [23]. A number of reviews [24–26,27 ▪ ,28] have described the current state of AI and OA research, so we will only detail a few recent studies here [29–32,33 ▪▪ ]. A new study using data from the OAI investigated the relationship between MRI-based three-dimensional texture of the infrapatellar fat pad (IPFP) and the future development of knee OA among knees with KL grade ≤1 across 48-months of follow-up [29].…”

“…Dunn et al tested the use of peripheral blood epigenetic biomarker data in elastic net models to predict knee OA progression using data from the Osteoarthritis Biomarkers Consortium (OABC) [33 ▪▪ ]. Of note, this study used two entirely independent cohorts, including one from the Johnston County OA Project and one from a previous OAI methylation dataset for external validation of their tested prediction model.…”