Gene Hunting with o1-pro: Reasoning about Rare Diseases with ChatGPT Pro Grantee Dr. Catherine Brownstein
Digest
This podcast features Dr. Brownstein, a "gene hunter," discussing the challenges and advancements in rare disease diagnosis. She highlights the surprisingly high prevalence of rare diseases and the arduous diagnostic journey patients face. The conversation explores the impact of decreased genetic sequencing costs, creating an information overload for specialists. Dr. Brownstein details her team's multidisciplinary approach, utilizing genomic pipelines, phenotype ontologies (HPO codes), and various genetic testing methods. A significant portion focuses on the increasing role of AI, particularly large language models (LLMs), in summarizing research, analyzing data, and generating hypotheses. The potential of AI to improve patient experiences, streamline workflows, and create predictive models is discussed, alongside challenges like data sharing and accessibility. The podcast concludes with plans for a year-long progress review and emphasizes the importance of AI in accelerating rare disease research and diagnosis. Dr. Brownstein's work is supported by the CHET GPT Pro Grant.
Outlines
The Prevalence of Rare Diseases and the Diagnostic Challenge
Dr. Brownstein introduces the high prevalence of rare diseases and the difficulties in diagnosis, describing her role in diagnosing previously unexplained cases using genetic analysis.
The Patient's Diagnostic Journey and Multidisciplinary Approach
The podcast details the lengthy and complex process patients undergo to receive a diagnosis, highlighting the multidisciplinary approach employed by Dr. Brownstein's team, including genetic testing and re-analysis.
Genetic Sequencing: Accessibility and Challenges
The discussion covers the dramatic cost reduction in genetic sequencing, its increased accessibility, and the resulting challenges of processing vast amounts of data.
Multidisciplinary Workflow and Data Analysis
The podcast explains the workflow of a multidisciplinary team analyzing cases, including the use of genomic pipelines, phenotype ontologies (HPO codes), and new technologies like RNA-seq.
AI's Current Role in Rare Disease Research
Dr. Brownstein discusses the use of large language models (LLMs) in summarizing articles, analyzing genes, and detecting anomalies, highlighting time savings and hypothesis generation.
The Future of AI in Rare Disease Diagnosis and Data Sharing
The conversation explores the future applications of AI, including improved patient experiences, streamlined workflows, and predictive models, while addressing challenges in data sharing and accessibility.
Progress Review and Closing Remarks
The podcast concludes with plans for a future progress review, thanks the guest, and reiterates the guest's credentials and contact information.
Keywords
Rare Diseases
Diseases affecting a small population, posing significant diagnostic challenges.
Genetic Sequencing
Determining the order of nucleotides in DNA; cost reduction has increased accessibility but also data overload.
Large Language Models (LLMs)
AI models used in rare disease research for literature summarization, data analysis, and hypothesis generation.
Phenotype Ontology (HPO)
Standardized vocabulary for describing disease characteristics, aiding in analysis and comparison.
Diagnostic Odyssey
The prolonged and frustrating process of obtaining a rare disease diagnosis.
AI-assisted Gene Discovery
Utilizing AI to identify genes associated with rare diseases, improving diagnostic accuracy.
AI in Healthcare
Application of AI in medical research, diagnosis, and treatment.
CHET GPT Pro Grant
A grant supporting AI-driven projects in healthcare.
Q&A
What are the biggest challenges in diagnosing rare diseases, and how can AI help overcome them?
Challenges include rarity, genetic complexity, and vast research literature. AI can help by summarizing research, efficiently analyzing genomic data, and generating hypotheses faster.
How has the decreasing cost of genetic sequencing impacted rare disease research?
Lower costs have increased accessibility, leading to more data but also information overload for specialists. AI can help manage this.
What is Dr. Brownstein's experience with using LLMs in her research?
She uses LLMs to summarize research, analyze data, and generate hypotheses, but acknowledges limitations like potential inaccuracies and the need for fact-checking.
What is the importance of data sharing in rare disease research?
Data sharing is crucial for identifying patterns and making discoveries, but barriers include investigator reluctance, lack of standardized formats, and logistical challenges.
What is Dr. Brownstein's vision for the future of AI in rare disease research?
She envisions AI becoming more integrated into daily workflows, improving diagnostic accuracy, shortening the diagnostic odyssey, and democratizing access to genetic information.
What grant did the guest receive?
The guest received the CHET GPT Pro Grant.
Show Notes
Nathan explores the cutting-edge intersection of AI and rare disease research with Dr. Catherine Brownstein of Boston Children's Hospital and Harvard Medical School. In this episode of The Cognitive Revolution, we dive into how frontier AI models are revolutionizing the diagnosis of rare diseases. Join us for an insightful conversation with a ChatGPT Pro grant winner who's pioneering the use of AI to help patients find answers faster.
Help shape our show by taking our quick listener survey at https://bit.ly/TurpentinePulse
Check out Modern Relationships, where Erik Torenberg interviews tech power couples and leading thinkers to explore how ambitious people actually make partnerships work. This season's guests include: Delian Asparouhov & Nadia Asparouhova, Kristen Berman & Phil Levin, Rob Henderson, and Liv Boeree & Igor Kurganov.
Apple: https://podcasts.apple.com/us/podcast/id1786227593
Spotify: https://open.spotify.com/show/5hJzs0gDg6lRT6r10mdpVg
YouTube: https://www.youtube.com/@ModernRelationshipsPod
SPONSORS:
Oracle Cloud Infrastructure (OCI): Oracle's next-generation cloud platform delivers blazing-fast AI and ML performance with 50% less for compute and 80% less for outbound networking compared to other cloud providers. OCI powers industry leaders like Vodafone and Thomson Reuters with secure infrastructure and application development capabilities. New U.S. customers can get their cloud bill cut in half by switching to OCI before March 31, 2024 at https://oracle.com/cognitive
NetSuite: Over 41,000 businesses trust NetSuite by Oracle, the #1 cloud ERP, to future-proof their operations. With a unified platform for accounting, financial management, inventory, and HR, NetSuite provides real-time insights and forecasting to help you make quick, informed decisions. Whether you're earning millions or hundreds of millions, NetSuite empowers you to tackle challenges and seize opportunities. Download the free CFO's guide to AI and machine learning at https://netsuite.com/cognitive
Shopify: Dreaming of starting your own business? Shopify makes it easier than ever. With customizable templates, shoppable social media posts, and their new AI sidekick, Shopify Magic, you can focus on creating great products while delegating the rest. Manage everything from shipping to payments in one place. Start your journey with a $1/month trial at https://shopify.com/cognitive and turn your 2025 dreams into reality.
Vanta: Vanta simplifies security and compliance for businesses of all sizes. Automate compliance across 35+ frameworks like SOC 2 and ISO 27001, streamline security workflows, and complete questionnaires up to 5x faster. Trusted by over 9,000 companies, Vanta helps you manage risk and prove security in real time. Get $1,000 off at https://vanta.com/revolution
CHAPTERS:
(00:00:00 ) Teaser
(00:00:56 ) About the Episode
(00:04:45 ) Rare Diseases Common
(00:06:48 ) Patient Journey
(00:12:57 ) Genome Sequencing
(00:19:39 ) Sponsors: Oracle Cloud Infrastructure (OCI) | NetSuite
(00:22:19 ) Diagnosis Process
(00:30:50 ) Data Pipelines
(00:35:51 ) Sponsors: Shopify | Vanta
(00:39:07 ) Interaction Graphs
(00:42:18 ) Data Accessibility
(00:43:42 ) AI in Pipelines
(00:45:40 ) LLM Impact
(00:48:40 ) Anomaly Detection
(00:52:07 ) Data Sharing
(00:58:49 ) Data Reform
(01:02:41 ) AI's Potential
(01:04:30 ) AI Applications
(01:06:57 ) Prompt Engineering
(01:14:51 ) Model Comparison
(01:19:16 ) Prompting Insights
(01:22:14 ) Move 37 Analogy
(01:24:34 ) Future Potential
(01:29:27 ) Future Experience
(01:32:39 ) Outro
SOCIAL LINKS:
Website: https://www.cognitiverevolution.ai
Twitter (Podcast): https://x.com/cogrev_podcast
Twitter (Nathan): https://x.com/labenz
LinkedIn: https://www.linkedin.com/in/nathanlabenz/
Youtube: https://www.youtube.com/@CognitiveRevolutionPodcast
Spotify: https://open.spotify.com/show/6yHyok3M3BjqzR0VB5MSyk
![E32: [Bonus Episode - The AI Breakdown] Can OpenAI's New GPT Training Model Solve Math and AI Alignment At the Same Time?](https://megaphone.imgix.net/podcasts/680351f6-0179-11ee-a281-5bef084f2628/image/e57b08.png?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress "E32: [Bonus Episode - The AI Breakdown] Can OpenAI's New GPT Training Model Solve Math and AI Alignment At the Same Time?")
Table of contents
United States
