Course modules include:
- Clinical Data: Explore healthcare data types, data quality challenges, healthcare data standards, and data analysis using Pandas, while gaining an introduction to technologies such as Apache Spark, HDFS, and AWS S3.
- Clinical Notes: Learn how natural language processing (NLP) techniques such as tokenization, text cleaning, Named Entity Recognition (NER), and feature extraction can be used to analyze unstructured clinical text.
- Data Preparation: Develop practical skills in data cleaning, feature engineering, multimodal data integration, and preparing machine learning-ready datasets.
By the end of the course, learners will be able to process large-scale clinical datasets, apply Python-based tools such as Pandas and PySpark, build scalable data pipelines, integrate structured and unstructured data sources, and prepare data for machine learning and advanced healthcare analytics.
The above courses were developed by the Data Science Training Core (DSTC) and AIM-AHEAD Communications Hub. Course directors include Desta Haileselassie Hagos, PhD - Howard University, DSTC, Legand L. Burge, PhD - MPI, AIM-AHEAD Coordinating Center, DSTC, Toufeeq Syed, PhD - MPI, AIM-AHEAD Coordinating Center, Leadership Core.