🔍 New Publication Alert! Understanding the Real Prevalence of Interstitial Lung Disease in Rheumatoid Arthritis Patients
In the realm of rare diseases, accurately estimating prevalence is a significant challenge. Literature suggests a wide prevalence range for interstitial lung disease associated with Rheumatoid Arthritis (RA) - from 1% to 60%. This vast variability poses real-world difficulties in diagnosis, treatment planning, and resource allocation, impacting patient care and research focus.
📊 Our recent study, published in RMD Open, leverages machine learning and big data to shed light on this issue. By analyzing a cohort of 14,000 RA patients, we've derived reliable real-world data, estimating that this condition affects 1 in every 20 patients. This finding narrows the prevalence gap and provides a clearer target for healthcare providers and researchers.
This work was made possible through collaboration with esteemed institutions and colleagues, including various Spanish hospitals, the innovative team at SAVANA Med, and the support of Bristol Myers Squibb (BMS) and Sandra Orta. I extend my heartfelt gratitude to @Jose Andres Roman Ivorra, Ignacio H. Medrano and Diego Benavent Nuñez for their significant contributions and unwavering commitment to this project.
📝 Our findings underscore the power of technology in transforming medical research and patient care. Dive into our publication to explore how big data and machine learning are unveiling the real face of rare disease prevalence: https://lnkd.in/dZ-Gdd8n
#RheumatoidArthritis #InterstitialLungDisease #MachineLearning #BigData #MedicalResearch #BMSiberia #HealthcareInnovation #SAVANAMed
📌 Fascinating, thought-provoking insights! Through significant reading on the commercial applications of 'synthetic research respondents' (as similar concept) we know there are challenges using AI at present, because LLM AI tools like ChatGPT are biased in a number of ways (e.g. wanting to please the user). However, modelling patients this way, created with real-world patient variables, appears to be a novel approach with plenty going for it. Great post! 🚀