Real World Data Curation

Extract structured facts from free-text clinical notes and reports, clean and link patient data, and generate better evidence to improve treatments and guidelines

Case Study:

Automated and Explainable Deep Learning for Clinical Language Understanding at Roche

Unstructured free-text medical notes are the only source for many critical facts in healthcare.

As a result, accurate NLP is a critical component of many healthcare AI applications like clinical decision support, clinical pathway recommendation, cohort selection, patient risk, or abnormality detection.

Recent advances in deep learning for NLP have enabled a new level of accuracy and scalability for clinical language understanding, making a broad set of applications possible for the first time.

This case study shows how Roche uses Spark NLP for Healthcare to extract & normalize tumor characteristics from free-text pathology and radiology reports.

In Oncology, thousands of pages of text can be accumulated for each patient, often over several years. Reading diverse reports and putting the facts together in a timeline is at the core of any real-world data collection effort.

Why John Snow Labs?

01

Accuracy

Peer-Reviewed state-of-the-art accuracy

Learn More

Keeps Improving with novel research for 4 years straight

Learn More

02

Healthcare Expertise

250+ Pre-Trained Healthcare Specific NLP Models

Learn More

Medical doctors and pharmacists involved in every project

Learn More

03

Extensible

Train and Tune your own models on your own data

Learn More

Support every medical document, including scanned images

Learn More

Proven Success

We help 5 of the top 10 global pharmaceutical companies make RWD and RWE a reality

Using Spark NLP to Enable Real-World Evidence (RWE) and Clinical Decision Support in Oncology
Applying State-of-the-art Natural Language Processing for Personalized Healthcare