The podcast discusses how Sorcero uses AI to make medical research more understandable. They explain the challenges faced by Medical Affairs Teams in keeping up with new information. The speakers also explore the use of AI to improve accessibility and communication in healthcare. Additionally, they discuss attribution in Stack Overflow's JNI world and express frustration with filling out forms at doctors' offices.
AI can make medical papers up to 700x more readable, helping to bridge the gap in accessibility for the global population.
Source Sarrow uses a hybrid approach to AI, combining symbolic and non-symbolic methodologies, and leverages ontologies extensively to ensure accuracy and explainability in processing healthcare data.
Deep dives
Source Sarrow: Using AI to Improve Healthcare
Source Sarrow is an AI analytics and insights company focused on the healthcare life sciences space. They use AI to compute and analyze large volumes of healthcare data more efficiently. Their platform supports better decision making by doctors and helps patient advocacy groups advocate for better treatment. They work with third-party scientific information, clinical trial data, and conversational data to pinpoint how to treat specific patient populations. They take a hybrid approach to AI, using both symbolic and non-symbolic approaches, and leverage human expertise to ensure accuracy and validity of the output. They have a global database and support multiple languages, and they have separate customer-specific databases. They also have complex ETL pipelines to manage their diverse data sources.
Improving Medical Publications with AI
Source Sarrow's intelligent publication monitoring product helps customers monitor publications in their therapeutic area. It has had a positive impact on AstraZeneca's oncology team, equipping them with essential safety and efficacy data. They use AI and generative models to simplify the understanding of complex medical publications, generating plain language summaries (PLS) that are more readable than what's in the market. They also have a feedback mechanism for customers to validate and improve the accuracy of the output. Their platform supports multilingual capabilities and a global dataset, allowing customers to access researchers and data from around the globe.
AI-driven Data Analysis and Enrichment
Source Sarrow leverages AI to analyze and enrich healthcare data, including clinical trials, open data, and customer data. They apply multiple machine learning and AI techniques to process and derive insights from diverse and high-dimensional data sources. They focus on simplifying data through plain language summaries (PLS) and use generative AI to automate the generation of PLS, producing highly readable summaries that are comprehensible to physicians and patients. They employ a hybrid approach to AI, combining symbolic and non-symbolic methodologies, and leverage ontologies extensively to ensure accuracy, transparency, and explainability. They also have a complex data infrastructure with ETL pipelines to manage their data sources and maintain compliance with privacy and regulatory requirements.
Sorcero uses a mix of natural language processing, generative AI, and even more old school symbolic AI, where they craft their own ontologies, to try and ingest that river of new medical data and make it easier to search and comprehend.
Less than 0.2% of the global population can read a medical paper! AI can help make these dense works up to 700x more readable.
Medical Affairs Teams are the groups inside big pharmaceutical companies that helps surface the right information to health providers. It’s hard for them to keep up with the thousands of new articles and research papers being published each month, much less unpack that information.