Webinar sign up
Answering natural language questions in medicine
Watch live on September 16th at 2pm EST
The ability to directly answer medical questions asked in natural language either about a single patient (“what drugs has this patient been prescribed?”) or a cohort of patients (“list stage 4 lung cancer patients with no history of smoking”) has been a longstanding healthcare industry goal, given its broad applicability across use cases like order validation, pre-authorization, cohort selection, clinical quality reporting, and real-world evidence.
While “natural language BI” systems do exist, they generally fail on clinical questions since they lack healthcare-specific models and reference knowledge. Such systems fail to infer, for example, that a patient with a T1N2M0 tumor has stage 3 lung cancer, that a patient taking Zoloft for years has a history of depression, or that an A1C lab result of 7.5 indicates diabetes.
This webinar presents a software solution, based on state-of-the-art deep learning and transfer learning research, for translating natural language questions to SQL statements. An actual case study will be a system which answers clinical questions by training domain-specific models and learning from clinical reference. This is a production-grade, trainable and scalable capability of Spark NLP Enterprise & Healthcare. Live Python notebooks will be shared to explain how you can use it in your own projects.
Presented by Prabod Rathnayaka - Graduate Research Assistant and PhD Student at La Trobe University