OM1 expands real-world evidence in dermatology by launching a dataset for hidradenitis suppurativa

OM1 announces addition of a dataset for hidradenitis suppurativa to its dermatology network of enriched real-world data, expanding real-world evidence in dermatology. 

Real-world data (RWD) technology company OM1 has announced it has added an enriched real-world dataset for the chronic inflammatory skin condition hidradenitis suppurativa (HS) to its growing dermatology RWD network. Elucidation of real-world evidence (RWE) trends and insights from the dataset, developed from 26,000 medical records of people living with HS over a decade, has the potential to enhance patient diagnosis and treatment personalization and outcomes.  

OM1 has already established an array of industry-leading enriched real-world datasets across a diversity of chronic medical conditions. This latest addition of a HS dataset to its dermatology network closely follows the recent expansion of its mental health and neuroscience RWD network with the release of a curated dataset for Parkinson’s disease and, earlier in 2023, datasets for schizophrenia and bipolar disorder.  

HS is a debilitating, chronic and recurrent inflammatory skin disease that has a profound effect on a person’s mental and social health. It is associated with multiple somatic and psychiatric comorbidities, such as obesity, anxiety, depression and polycystic ovary syndrome, and is frequently misdiagnosed, with sufferers sometimes living with the disease for over a decade before correct diagnosis.  

“People are going years without an accurate diagnosis of their dermatological conditions, resulting in a worsening of both the disease and the patient’s mental health,” said Stefan Weiss, MD, MBA, FAAD, MD of Dermatology at OM1. “Uncovering trends and insights on disease progression to aid in patient identification and treatment personalization is one of the most important steps we can take to improve patient outcomes.” 

A significant feature of OM1’s dataset enrichment is that they have leveraged machine learning to generate estimations across the dataset of Hurley Stage, the industry’s grading system for classifying the extent of HS. The dataset is built off 26,000 healthcare records of people living with HS over the last decade. The potential of the valuable estimated Hurley Stage component can now be wielded within analyses in combination with data gathered from electronic medical records, including demographics, geography, comorbidities, treatments and provider specialty, complemented by unstructured data derived from medical claims and physician notes (e.g., detail of anatomic location and disease manifestation).  

It is hoped the clinical insights from the new dataset will enable stakeholders across the healthcare ecosystem to better understand HS disease, empowering improved diagnosis, accelerated research and development of specialized and targeted treatment plans, enhancing patient care and outcomes.