Course Abstract

Training duration : 90 minutes

The course review case studies from real-world projects that built AI systems using Natural Language Processing (NLP) in healthcare. These case studies cover projects that deployed automated patient risk prediction, automated diagnosis, clinical guidelines, and revenue cycle optimization. He will also cover why and how NLP was used, what deep learning models and libraries were used, and what was achieved. Key takeaways for attendees will include important considerations for NLP projects including how to build domain-specific healthcare models and using NLP as part of larger and scalable machine learning and deep learning pipelines in distributed environment.

DIFFICULTY LEVEL: INTERMEDIATE

Learning Objectives

  • How to build domain-specific healthcare models

  • Using NLP as part of larger and scalable machine learning and deep learning pipelines in distributed environment.

Instructor

Instructor Bio:

Lead Data Scientist and ML Engineer at John Snow Labs

Veysel Kocaman

Veysel Kocaman is a Lead Data Scientist and ML Engineer at John Snow Labs and has a decade long industry experience. He is also pursuing his Ph.D. in CS as well as giving lectures at Leiden University (NL) and several other platforms. He holds an MS degree in Operations Research from Penn State University and is affiliated with Google as a Developer Expert in Machine Learning.

Course Outline

Module 1:  NLP at Scale and Introduction to Spark NLP 

- Foundations and basic concepts of Spark NLP 

- Building blocks of Spark NLP 

- Building text processing pipelines in Spark NLP 

Module 2: Natural Language Processing (NLP) in Healthcare 

- Solving problems with NLP in healthcare 

- Clinical pretrained modules to extract knowledge from unstructured text in healthcare domain

 - Clinical Named Entity Recognition (NER) models 

- Assertion status models to detect negativity scope 

- Entity resolvers models for medical ontologies (ICD-10, RxNorm, Snomed)

 - De-identification of sensitive data (PHI) 

Module 3: Healthcare Case Studies and Lessons Learned 

- Using NLP to better understand home health patients

 - Automated knowledge extraction from pathology and radiology reports

 - Improving patient flow forecasting at hospitals 

- Using NLP to accelerate clinical trial recruitment

Background knowledge

  • Some background in Python

  • Basic knowledge of Natural Language Processing techniques

Real-world applications

  • Extract knowledge from medical records (EHR)

  • Using NLP to recruit patients for clinical trials

  • Scalable OCR to convert medical records and images to digestible text files