International Coalition Classifies 25 Subtypes of Uveitis, An Inflammatory Eye Disease
An international coalition of eye researchers used machine learning to develop classification criteria for 25 of the most common types of uveitis, a collection of over 30 diseases characterized by inflammation inside the eye.
The Standardization of Uveitis Nomenclature (SUN) Working Group, funded by the National Eye Institute (NEI), published its classification criteria in the American Journal of Ophthalmology. NEI is part of the National Institutes of Health.
The SUN Working Group, a team of nearly 100 international uveitis experts from more than 20 countries and 60 clinical centers, worked together throughout the project, which was conducted in four phases: informatics, case collection, case selection, and machine learning.
The informatics phase involved standardizing language to describe each type of uveitis and the mapping of terms to individual diseases. In the case collection phase, the team entered 5,766 cases into a database, averaging 100-250 of each uveitis type.
During the case selection phase, committees of nine uveitis experts reviewed the cases and used formal consensus techniques to determine whether they were a specific identifiable disease. Only cases with a more than 75% agreement among experts were included in the final database.
The resulting cases (4,046) were put through machine learning using multiple approaches on a subset of the cases (“training set”) and the performance of the criteria determined on a second subset of the cases (the “validation set”).
The overall performance of the criteria was over 90% within uveitic class, suggesting that the criteria can be used in clinical and translational research. The final step was approval of the proposed criteria by the SUN Working Group.
Uveitis is a collection of over 30 diseases that are characterized by inflammation inside the eye. As a whole, these diseases are the fifth leading cause of blindness in the United States.
Historically, uveitis was classified on the location of the inflammation; however, this posed a challenge to ophthalmologists creating treatment plans as various types may affect the same anatomic location, but with differing causes, prognoses, and courses. As a result, the SUN Working Group stepped in.
“In the past, clinical research in the field of uveitis has been hampered by the lack of widely-accepted and validated diagnostic criteria,” said Douglas A. Jabs, MD, MBA, the SUN project leader and professor of epidemiology and ophthalmology at Johns Hopkins Bloomberg School of Public Health, Baltimore.
“These classification criteria are a major step forward for epidemiological studies, translational studies, pathogenesis research, outcomes research, and clinical trials. They hopefully will yield better disease-specific approaches to diagnosis and treatment.
Creating criteria for uveitis classification
Pulling from the expertise of nearly 100 international uveitis experts from more than 20 nations and 60 clinical centers, the SUN Working group designed the new classification criteria after completing informatics, case collection and selection, and machine learning.
Informatics revolved around standardizing descriptive language of uveitis, which varies across individual diseases.
Once appropriate terminology was determined, the group moved onto case collection and selection, which involved entering 5766 cases into a database, with approximately 100-250 cases per uveitis type.
The team split into committees of nine experts to review the cases and determined whether each case constituted a specific identifiable disease. To move into the final database, each case needed 75% consensus.
Once the uveitis experts whittled the database down to 4046 cases, they began the phase of machine learning, a type of artificial intelligence.
The research team combined a training set of multiple approaches on a subset of the cases with a validation set of the performance of the criteria determined on a second subset of the cases.
Overall, the AI system categorized over 90% within uveitic class, providing hope for implementation in clinical and translational research.