Classification criteria funded by the National Institutes of Health will facilitate clinical research for new therapies.
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 more than 30 diseases characterized by inflammation inside the eye.
Together, these diseases are the 5th leading cause of blindness in the United States. 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.
According to Douglas A. Jabs, MD, MBA, the SUN project leader and professor of epidemiology and ophthalmology, Johns Hopkins Bloomberg School of Public Health, Baltimore, in the past, clinical research in the field of uveitis has been hampered by the lack of widely-accepted and validated diagnostic criteria.
"These classification criteria are a major step forward for epidemiological studies, translational studies, pathogenesis research, outcomes research, and clinical trials,” he said in a statement. “They hopefully will yield better disease-specific approaches to diagnosis and treatment."
According to the NIH, in uveitis, inflammation can be seen in the anterior chamber (anterior uveitis), vitreous (intermediate uveitis), choroid, or retina (posterior uveitis), or all of these (panuveitis). Disease course, complications of uveitis, and the effect on vision vary dependent on the specific disease. Some uveitis appears abruptly and resolves. But many cases are recurrent or chronic, requiring long-term therapy. Symptoms may include floaters, vision loss, pain, and light sensitivity. Uveitis can strike at any age and can have a major impact on quality of life.
Until recently, classification of uveitis was based on the primary location of inflammation. However, types of uveitis affecting the same anatomic location can have different causes, courses, prognoses, and treatment needs. Previous work by the SUN Working Group demonstrated that even uveitis experts can disagree on diagnosis, making apples-to-apples comparisons difficult when conducting clinical research.
"The agreement among uveitis experts on the diagnosis of individual diseases was modest at best,” Jabs added. “So, we set off to try to provide clarity, using informatics, formal consensus techniques, and technology to assist in classifying each uveitic disease.”
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 researchers used machine learning, a type of artificial intelligence, to help them identify the important characteristics that distinguished each disease.
According to the NIH, 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.
Moreover, 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 NIH noted that 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.
"The SUN Working Group is excited about this unprecedented effort coming to fruition and the publication of this work, as it should provide the basis for future clinical research in the field of uveitis." Jabs concluded.
For ophthalmologists, increasing the knowledge base about uveitis is important for several reasons.
“Epidemiologic studies of uveitis frame the medical need for uveitis specialists and training programs by defining the disease scope and disease burden and helping to justify research support,” said Jennifer E. Thorne, MD, PhD, director of the Division of Ocular Immunology and Uveitis, and Cross Family Professor of Ophthalmology and Epidemiology, Wilmer Eye Institute, Johns Hopkins University of Medicine and Public Health in Baltimore, Maryland.
Published population-based studies, according to Thorne, detail the burden of visual morbidity, including blindness, societal cost, and loss of quality of life.
During the past 6 decades, 4 major epidemiologic studies have been undertaken by Rochester, Minnesota (1962), the Northwest Veterans Affairs (VA) Centers in Oregon and Washington (2008), and 2 by Kaiser Permanente in California (2004) and Hawaii (2013) that reported the incidence and prevalence of uveitis in the United States.
Moreover, Thorne said she believes that the growth of large insurance databases and the IRIS database will result in additional studies.
In the 4 studies, the incidence rates of uveitis increased with age in each of the studies per 100,000 person-years and ranged from 17.4 in Minnesota, 24.9 in Hawaii, 25.6 in the Northwest VA study, and 52.4 in California.
The active prevalence of uveitis in the United States per 100,000 persons also increased with age, except in the Northwest VA study. The prevalence rates were 57.5 and 58.0 in Hawaiian studies (2006 and 2007), 69.0 in the Northwest VA study, and 114.5 in California.
Thorne said uveitis is a leading cause of visual impairment.
“In the US, the disease is estimated to be the fifth- or sixth-leading cause of blindness, accounting for 10% to 15% of cases of blindness,” she said.
In a separate report, findings in LOUVRE 2, a French postmarketing, prospective, observational study, confirm the real-world efficacy of the dexamethasone 0.7 mg intravitreal implant (Ozurdex, Allergan) for treating relatively long-standing non-infectious posterior segment uveitis.
The findings also provide insight into the characteristics of patients ophthalmologists choose for treatment with the sustained-release corticosteroid implant, according to Bahram Bodaghi, MD, PhD.
“Noninfectious posterior segment uveitis [NIPU] is the least common form of uveitis, yet it is the most vision-threatening form,” he said. “In addition to its potential to cause sudden/severe vision loss, it can be associated with painful symptoms. Because of its sequelae, NIPU can lead to a marked decrease in quality of life.”
According to investigators, a dexamethasone implant may be key to treating non-infectious posterior segment uveitis.