Although individual cancer care is standardized to a certain degree, considerable heterogeneity has been observed in healthcare delivery, uptake, and response to therapy.
These differences can have an impact on the patient journey experiences, outcomes, resource utilization, and cost of care. However, comprehensive attempts to study oncology patient populations is challenging because longitudinal data exist in multiple disparate source systems and formats, including unstructured data.
Recent advances in deep learning have raised the bar on achievable accuracy for tasks like named entity recognition, assertion status detection, entity resolution, and others, using novel healthcare-specific networks and models.
In this talk, Vishakha Sharma will share how Roche applies Spark NLP for healthcare to extract clinical knowledge from pathology, radiology, and genomics reports.