Eight-year trajectories of changes in health-related quality of life in knee osteoarthritis: Data from the Osteoarthritis Initiative (OAI)

Background Knee osteoarthritis (OA) worsens health-related quality of life (HRQoL) but the symptom pathway varies from person to person. We aimed to identify groups of people with knee OA or at its increased risk whose HRQoL changed similarly. Our secondary aim was to evaluate if patient-related characteristics, incidence of knee replacement (KR) and prevalence of pain medication use differed between the identified HRQoL trajectory groups. Methods Eight-year follow-up data of 3053 persons with mild knee OA or at increased risk were obtained from the public Osteoarthritis Initiative (OAI) database. Group-based trajectory modeling was used to identify patterns of experiencing a decrease of >= 10 points (Minimal Important Change, MIC) in the Quality of Life subscale of the Knee injury and Osteoarthritis Outcome Score compared to baseline. Multinomial logistic regression, Cox regression and generalized estimating equation models were used to study secondary aims. Results Four HRQoL trajectory groups were identified. Persons in the 'no change' group (62.9%) experienced no worsening in HRQoL. 'Rapidly' (9.5%) and 'slowly' worsening (17.1%) groups displayed an increasing probability of experiencing the MIC in HRQoL. The fourth group (10.4%) had 'improving' HRQoL. Female gender, higher body mass index, smoking, knee pain, and lower income at baseline were associated with belonging to the 'rapidly worsening' group. People in 'rapidly' (hazard ratio (HR) 6.2, 95% confidence interval (CI) 3.6-10.7) and 'slowly' worsening (HR 3.4, 95% CI 2.0-5.9) groups had an increased risk of requiring knee replacement. Pain medication was more rarely used in the 'no change' than in the other groups. Conclusions HRQoL worsening was associated with several risk factors; surgical and pharmacological interventions were more common in the poorer HRQoL trajectory groups indicating that HRQoL does reflect the need for OA treatment. These findings may have implications for targeting interventions to specific knee OA patient groups.