Using causal machine learning and real world data to improve dose response decision making for secukinumab in psoriatic arthritis

Abstract

Abstract Personalized treatment in psoriatic arthritis (PsA) remains challenging, particularly in guiding dose escalation decisions. We applied a causal machine learning framework to real-world data from the AQUILA study to evaluate the impact of secukinumab dose escalation (150 mg to 300 mg) on disease activity and health-related quality of life (HR-QoL). Using double machine learning, we estimated both average and patient-level conditional treatment effects (CATEs) based on 42 baseline variables, including demographics, laboratory values, disease activity, HR-QoL, comorbidities, and prior treatments. 41.4% of patients receiving the higher dose showed greater improvement in Psoriatic Arthritis Impact of Disease (PsAID) scores compared to the lower dose (mean reduction: 1.81 vs. 1.44). Subgroup analysis revealed a 28% HR-QoL gain in patients with elevated body mass index (BMI) or C-reactive protein (CRP). The model predicted that approximately 75% of patients would benefit from dose escalation. These findings demonstrate the utility and scalability of causal machine learning for quantifying individualized treatment effects and guiding personalized treatment decisions in PsA. The approach is transferable to other chronic conditions, supporting more precise, data-driven care in real-world clinical settings.