Oracle’s Cerner Enviza and FDA Collaborate on NLP-AI Drug Safety Tools
Oracle company Cerner Enviza and John Snow Labs are collaborating with the FDA to develop artificial intelligence (AI) tools that assess the safety of drugs. These tools will extract unstructured data from electronic health records (EHRs) and use machine learning to fill in the gaps in epidemiological knowledge.
The project is dubbed MOSAIC-NLP (Multi-source Observational Safety Study for Advanced Information Classification Using NLP models). It will take place over two years and is part of the FDA’s ‘Sentinel Initiative’, a system for digitally monitoring the safety of FDA-regulated medical products.
The cooperation aims to address the obstacles that manual clinical data analysis creates for understanding patient outcomes at the population level.
- Orion Granted €10m to Build AI-Based ‘Research Ecosystem’ in Finland
- Leading Perspectives on Using AI Tools to Drive Drug Design
- Alphabet’s Calico and Terray Tx Announce Partnership to Tackle Age Related Disease
"Development and evaluation of tools that can enhance our ability to utilize unstructured EHR data is a key strategic priority for the Sentinel Innovation Center. We look forward to this new relationship and exciting initiative led by Cerner Enviza," said Rishi Desai, Executive Leadership Team Member at Sentinel Innovation Center.
Artificial intelligence will be used in combination with natural language processing (NLP) technologies, tools which aim to make computational sense of prose written and spoken by humans. Collaborator John Snow Labs is a provider for this field, its ‘Spark NLP’ model library being widely used in the industry.
The partners will continue to study side-effects on mental health by the asthma drug montelukast, which the FDA requires to have a boxed warning. The Sentinel System had previously provided data which contributed to the FDA’s observational study into the drug.
Montelukast had reports of suicidal thoughts and actions from patients. After the study, the FDA concluded that it should not be used as a first choice treatment and required the boxed warning, the FDA’s most prominent warning for medical products.
Mike Kelly, Global Head at Cerner Enviza, said that “Connected technologies and unified data can accelerate innovation and, in turn, help providers realize better recommendations and outcomes for their patients."
Get your weekly dose of industry news?here?and keep up to date with the latest?‘Industry Spotlight’ posts.?For other Discovery content, please visit the?Discovery Content Portal.
