Hopkins Program to Individualize Autoimmune Disease Management (inADM)
Autoimmune diseases are diverse, both in how they manifest and in how they progress. This diversity makes it difficult for clinicians to anticipate which patients will suffer from the most severe forms of disease and, consequently, how to best treat each patient. inADM investigators envision a future where clinicians not only understand the unique disease biology and likely disease trajectory of every patient with autoimmune disease, but can also use that information to effectively guide treatment.
To achieve this vision, inADM researchers are combining prior pathobiological and clinical knowledge with emerging Big Data to discover new ways to characterize autoimmune diseases and to create innovative algorithms to predict disease progression. inADM began its efforts by studying Johns Hopkins patients with scleroderma, an autoimmune disease that results in hardening of the skin and is associated with organ complications that range widely in severity among patients. inADM investigators successfully developed a computational approach that defined new scleroderma subtypes and are currently conducting analyses to determine if immune system markers are associated with these subtypes. inADM researchers will use this knowledge to model and predict the individual disease trajectory of scleroderma patients and will adapt this model to other autoimmune diseases, including rheumatoid arthritis and lupus.
To support the refinement and dissemination of their novel measures and statistical models, inADM will establish a consortium of physicians who treat autoimmune disease. inADM also plans to create and disseminate to clinicians training modules on data collection methods to help them enrich autoimmune disease databases.
inADM has the potential to transform the management of autoimmune diseases by contributing a remarkably enhanced understanding of their biology. With better prediction of individual disease progression, clinicians will be able to make more individualized treatment decisions by, for instance, avoiding therapy for a patient whose disease is unlikely to progress. As a result, patient outcomes and safety will improve while conserving health care costs.