Many critical facts required by healthcare AI applications like patient risk prediction, cohort selection and clinical decision support are locked in unstructured free-text data. Recent advances in deep learning have raised the bar on achievable accuracy for tasks like biomedical named entity recognition, assertion status detection, entity resolution, de-identification and others. This case study presents the first industrial-grade implementation of these new results and its application at scale.
Roche is the world’s #1 company for in-vitro diagnostics and its medicines are used to treat over 130 million people each year. It’s building a clinical decision support product portfolio, starting with oncology. Roche is using Spark NLP for Healthcare to extract clinical facts from pathology and radiology reports. The case study covers the design of the deep learning pipelines used to simplify training, optimization, and inference of such domain-specific models at scale.
”Roche applies Spark NLP for healthcare to extract clinical facts from pathology reports and radiology - and simplify training, optimization, and inference of such domain-specific models at scale.
Data scientist for diagnostic information solutions at Roche
Many businesses still depend on documents stored as images—from receipts, manifests, invoices, medical reports, and ID cards snapped with mobile phone cameras to contracts, waivers, leases, forms, and audit records digitized with scanners. Extracting high-quality data from these images comes with three challenges. First is OCR, as in dealing with crumpled receipts photographed from an angle in a dimly lit room. Second is NLP, extracting normalized values and entities from the natural language text. The third is building predictors or recommendations that suggest the best next action—and in particular can deal with missing, wrong, or conflicting information generated by the previous steps.
This case study illustrates an AI system that reads millions of pages of patient information, gathered from hundreds of sources, resulting in a great variety of image formats, templates, and quality. It explores the solution architecture and key lessons learned in going from raw images to a deployed predictive workflow based on facts extracted from the scanned documents.
”The good news is that state-of-the-art deep learning techniques can now approach human accuracy in these three tasks—and do so at scale.
Chief information officer at SelectData
Answering questions accurately based on information from financial documents, which can be a hundred or more pages long, is a challenge even for human domain experts. While traditional rule-based or expression-matching techniques work for simple fields in templated documents, it is harder to infer facts based on implied statements, on the absence of certain statements, or on the combination of other facts. Answering such questions at a very high level of accuracy requires state-of-the-art deep learning techniques applied to NLP.
Spark NLP was used to augment the UiPath smart data extraction platform in order to automatically infer fuzzy, implied, and complex facts from long financial documents. This case study covers the technical challenges, the architecture of the full solution, and lessons learned that you can directly apply to your next data extraction project.
”UiPath is excited to support this technology partnership and support a seamless integration of John Snow Labs’ state-of-the-art NLP technology inside UiPath Activities. The joint capability is already providing value to business customers and is broadly applicable.
Senior Manager for partnerships and alliances at UiPath
Recruiting patients for clinical trials is a major challenge in drug development. Finding patients requires an in-depth understanding of their medical histories and current health statuses while the majority of patient data is unstructured and spread across physician notes, pathology, imaging, genomic, and other reports. For this reason, clinical trial recruitment is a slow and manual process.
This case study describes how Deep 6 uses the Spark natural language processing (NLP) platform to apply state-of-the-art deep learning to accurately extract the relevant clinical facts from unstructured text. These facts are then used in subsequent data science pipelines in constructing patients’ medical histories.