Optimizing Dose-Response Decisions in Psoriatic Arthritis via Causal Machine Learning: A Real-World Evaluation of Secukinumab Treatment
Kiltz, U.; Glassen, T.; Brandt-Juergens, J.; Kiss, F.; Peterlik, D.; Gmeiner, B.
Show 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 secuki-numab 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. 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.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Validation of patient-reported outcome measures for dactylitis, psoriatic skin and nail disease, and uveitis in patients with psoriatic arthritis in routine care 91%
- Risk-stratified monitoring for sulfasalazine toxicity: prognostic model development and validation. 90%
- Biologic agents for rheumatic diseases in the break of COVID-19: friend or foe? 89%
Similar papers in this journal
- Imbalanced Machine Learning Classification Models For Removal Biosimilar Drugs And Increased Activity In Patients With Rheumatic Diseases 92%
- Combining explainable machine learning, demographic and multi-omic data to identify precision medicine strategies for inflammatory bowel disease 91%
- A distinct four-value blood signature of pyrexia under combination therapy of malignant melanoma with BRAF/MEK-inhibitors evidenced by an algorithm-defined pyrexia score 91%
Similar papers in this journal
Similar papers in this journal
- Incidence and management of inflammatory arthritis in England before and during the COVID-19 pandemic: a population-level cohort study using OpenSAFELY 90%
- Risk of severe COVID-19 outcomes associated with immune-mediated inflammatory diseases and immune modifying therapies: a nationwide cohort study in the OpenSAFELY platform 88%
- Versus Arthritis Musculoskeletal Disorders Research Advisory Group Priority Setting Exercise Protocol 88%
Similar papers in this journal
- Biologic Drug Survival in Psoriasis: A Systematic Review & Comparative Meta-Analysis 93%
- Timing COVID-19 - Synchronization of longitudinal patient data to the underlying disease progression using CRP as a temporal marker 88%
- Relationship Between Patient Sex and Serum Tumor Necrosis Factor Antagonist Drug and Anti-Drug Antibody Concentrations in Inflammatory Bowel Disease; A Nationwide Cohort Study 88%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.