Boston, MA, May 14, 2019 – ConcertAI, a next-generation integrated Real-World Data, AI and technology company for precision evidence, announced today that it will present research findings based on an AI model that can correctly identify 32% more cases of metastatic breast cancer compared to simple database queries with traditional business rules in a poster at the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) 2019 annual meeting being held May 18–22 in New Orleans.
ConcertAI’s research is an important step in demonstrating the validity and use of AI models in life sciences studies and has been selected as a semi-finalist for the Research Poster Presentation Award.
The AI model was trained, tested and validated using structured EHR data of 32,000 breast cancer patients. Clinical validation was carried out against a set of approximately 6,000 patients whose data was manually curated by expert oncology nurses. The model had high rates of precision and recall on a dataset which had ~20-30% metastatic patients.
“This work demonstrates the feasibility of extracting missing metadata using hundreds of other sparsely populated data points representing the patient’s medical journey, which would otherwise not be possible using simple business rules”, said Smita Agrawal, Ph.D., Senior Director of Product Management at ConcertAI and the research abstract’s primary author. “This opens up the possibility of creating richer datasets from structured EHR data which would be significantly more useful in clinical research.”
Potential impacts for life sciences research are significant. The AI model could be used to quickly identify eligible patients for clinical trials or retrospective outcomes science studies – saving substantial time and resources when compared to traditional, manual abstraction processes currently used to achieve the same insights.
“This abstract shows the utility of highly validated, precise AI models in life sciences and clinical research,” said Jeff Elton, Ph.D., CEO of ConcertAI. “Models like this rapidly enhance and expand existing RWD to finally give researchers a much wider pool of eligible patients with whom to design clinical trials. Such models will bring a speed and scale to the entire life sciences R&D pipeline so more successful studies can be conducted faster, bringing needed therapeutic innovations to patients more quickly.”
Details of the presentation are below. The full abstract can be accessed on the ISPOR website.
Poster Code and Session Title: PPM11, “Using Artificial Intelligence to Improve Capture of Metastatic Breast Cancer Status in Electronic Health Records.”
Topic: Medical Technologies, Methodological & Statistical Research
Date: Wednesday, May 22, 2019
Display Hours: 9:30 AM – 2:00 PM
Poster Author Discussion Hour: 12:45 PM – 1:45 PM
Session Location: K9