Innovation

Podcast: How AI can improve insight into disease biology

A scientist explains how we’re using AI capabilities to help identify patterns in tissue and tumor samples indiscernible to the human eye

December 20, 2024

We see the potential of data science, artificial intelligence (AI) and machine learning (ML) to help investigate new areas, pathways and mechanisms that may forge new opportunities to strengthen our pipeline through enhanced insights.

In a recent episode of the Health Pulse podcast by SAS, Dr. Greg Goldmacher, associate vice president, clinical research, and head of clinical imaging and pathology at MSD, discussed how we’re using these AI capabilities, like computer vision, to improve disease biology insights and help with objective imaging analysis to identify patterns indiscernible to the human eye.

“If you have AI tools that are trained to pick up subtle early signs of disease on scans that are being done for other reasons, there’s a real opportunity there for earlier diagnosis,” said Goldmacher in the podcast episode. “If you’re going to do opportunistic screening, for example, and want to train AI for that, what you need is longitudinal data sets where you can find patients who had the disease, and then go and look for scans that they might have had in the past to use to train the disease-recognizing models.”