Xplain Data, together with academic partners from the United States, will present new research at ISPOR 2026 in Philadelphia.
The project,
“Object-Centric Causal Discovery in MIMIC-IV: A Paradigm Shift for Identifying Risk Factors for Hospital-Acquired Pressure Injuries in Real-World Clinical Data,”
has been accepted as a poster presentation.
The work was developed in collaboration with Andy Wilson (University of Utah), an expert in real-world data and causal inference, and Dr. Jenny Alderden (Boise State University), a specialist in pressure injuries and board member of the National Pressure Injury Advisory Panel (NPIAP).
Background
Hospital-acquired pressure injuries (HAPIs) remain a significant challenge in healthcare. Approximately 2.5 million patients in the U.S. are affected each year. They occur in 6–10% of surgical critical care patients, with a global prevalence of around 8.4%.
The economic impact is substantial, with total annual costs in the U.S. estimated between $9.1 billion and $26.8 billion, and per-patient costs ranging from $20,900 to $151,700, depending on severity.
Approach
The project applies an object-centric approach to Causal Discovery using the MIMIC-IV clinical database. This method is designed to better capture relationships between clinical entities compared to traditional tabular models, with the goal of identifying more reliable risk factors in real-world clinical data.

