About the Talk

For many families living with a rare disease, the hardest part is not having a name for what is happening. Even with modern genetic testing, about half of people with rare diseases still remain undiagnosed. One reason is time: geneticists have to sort through enormous amounts of medical and genetic information, compare it against scattered databases, and keep up with new discoveries across thousands of conditions.

In this OpenAI Forum conversation, we will hear how researchers at Boston Children's Hospital used OpenAI o3 Deep Research, a publicly available research version of ChatGPT, to help reanalyze some of these difficult pediatric cases and surface new leads for expert review. The discussion will focus on the real-world promise of this work: helping scientists move faster, giving families a better chance at answers, and showing how AI can support advanced medical research while keeping geneticists and clinicians at the center of diagnosis and care.

Read the OpenAI Blog post, Using AI to help physicians diagnose rare genetic diseases affecting children.

Read the New England Journal of Medicine research paper, LLM-Assisted Reanalysis of Unsolved Rare Disease Genomes Increases Diagnostic Yield.

About the Speakers

Catherine Brownstein, MPH, PhD, Scientific Director, Manton Center for Orphan Disease Research Gene Discovery Core

Catherine Brownstein, MPH, PhD, is an Assistant Professor in Pediatrics at Harvard Medical School and a Research Associate in the Division of Genetics and Genomics at Boston Children's Hospital. As the Scientific Director for the Manton Center for Orphan Disease Research Gene Discovery Core, Dr. Brownstein has been instrumental in the elucidation of several new disease genes for conditions such as intellectual disability, bladder pain syndrome, very early onset psychosis, SIDS, and hypophosphatemic rickets. Her current work focuses on advancing the fields of genome sequencing and analysis, with an emphasis on leveraging AI to overcome barriers to diagnosis.

Alan H. Beggs, PhD, Director, Manton Center for Orphan Disease Research

Alan H. Beggs, PhD, is the Director of the Manton Center for Orphan Disease Research at Boston Children's Hospital and Sir Edwin & Lady Manton Professor of Pediatrics at Harvard Medical School. Following undergraduate studies at Cornell University, Dr. Beggs obtained his PhD in Human Genetics at Johns Hopkins University, with subsequent postdoctoral fellowship training in medical and molecular genetics at Johns Hopkins and Boston Children’s hospitals. He has general expertise in laboratory and clinical applications of genetics to human disease, and since 1992 has directed an independent research program in the Division of Genetics and Genomics. Over the years, he has used the toolset of human molecular genetics to study normal biology and pathophysiology of a variety of disorders including muscular dystrophies, cardiac arrhythmias, developmental brainstem defects, hereditary anemias, sudden infant death syndrome, and congenital myopathies. Dr. Beggs has been a standing and ad hoc member of numerous NIH study sections and grant reviewer for the Muscular Dystrophy Association and March of Dimes. He is a member of several scientific advisory boards and boards of directors for nonprofit and commercial entities.

Suyash Shringarpure, PhD, Member of Technical Staff, OpenAI

Suyash Shringarpure is a Member of Technical Staff at OpenAI, where he applies advanced AI systems to problems in life sciences and healthcare. A machine learning researcher and statistical geneticist, he brings deep expertise in genomics, computational biology, and human genetics. Suyash holds a Ph.D. in Machine Learning from Carnegie Mellon University. Following his Ph.D., he completed hist postdoctoral fellowship at Stanford University, developing machine learning methods for studying genetic ancestry and genomic privacy. Before joining OpenAI, Suyash was a Principal Scientist in Machine Learning and Computational Biology at 23andMe, where he worked on genomic risk prediction and drug target discovery.

Chris Nicholson, Member of Global Affairs Staff @ OpenAI

Chris V. Nicholson serves on OpenAI’s Global Affairs team, where he uses data and storytelling to document major AI use cases and support the company’s economic research. He co-founded the deep learning company Skymind (Y Combinator W16), which created the open-source AI framework Eclipse Deeplearning4j. He previously reported for the New York Times and Bloomberg News. Born in Montana, he now lives in the San Francisco Bay Area with his family.