Development of a web-based platform implementing novel Predictor of Skin Sensitization for Medical Devices (PreSS/MD) - PROJECT SUMMARY
Medical devices have been documented to contain toxic chemicals that can leach and cause acute contact
dermatitis (ACD) after repeated exposure or prolonged contact of the skin to these toxins. ACD is credited for
10-15% of all occupational illnesses and is also the second highest reported occupational hazard. Given its
prevalence, ACD is also a great public health burden with combined yearly costs of up to $1 billion, which spans
including medical costs, worker’s compensation and lost working time due to workplace absence. To this end,
the U.S. Food and Drug Administration has mandated that all medical devices must be evaluated for possible
skin sensitization using in vivo animal assays, which includes the Guinea pig maximization test (GPMT).
Although GPMT tests provide valuable data on the skin sensitization effects of potential toxins, these assays are
time-consuming and expensive. Moreover, the Interagency Coordinating Committee on the Validation of
Alternative Methods (ICCVAM) recently published a Strategic Roadmap, calling for the development of
alternative approaches to reduce animal testing of chemical and medical agents. Thus, there is a stated need to
modernize safety evaluation of medical devices to reduce animal testing and shorten the regulatory review time,
which would ultimately bring safer devices to the market faster. To address this unmet need, the key objectives
of our FDA Phase I SBIR project are to (i) produce rigorously validated computational models for the
GPMT assay integrating data obtained in human, mouse, and in vitro assays; and (ii) integrate these
models into a software product termed PreSS/MD (Predictor of Skin Sensitization for Medical Devices).
Our specific aims for this study include: 1) collecting, curating, and integrating the largest publicly available
dataset for GMPT; 2) creating and validating novel computational models for GMPT data; 3) developing the
PreSS/MD web server to allow users to make predictions of skin sensitization potential in medical devices. We
will also develop a model for mixtures, including compounds tested jointly in different concentrations, using an
approach that we developed previously. Finally, we will implement novel approaches to help users of our
PreSS/MD platform interpret the developed models in terms of key chemical features responsible for skin
sensitization. In addition, we will employ biomedical knowledge graphs to elucidate Adverse Outcome Pathways
(AOPs) for skin sensitizers. Successful execution of this Phase I project will yield in the development of
PreSS/MD as a centralized resource to evaluate the skin sensitization potential for medical devices. We expect
this software-as-a-service web server platform will be of great value for companies and sponsors seeking
regulatory approval of medical devices.
