Rui Huang

Junior Data Engineer, Datawarehouse

Biography: I am a Junior Data Engineer working in the Data Warehouse department. My routine tasks include:

1. Receiving data requests, both external and internal, and generating custom data extracts.

2. Creating and overseeing data pipelines to ensure data is ingested with high quality, enabling theinformation team to generate accurate reports.

I have completed two projects under the supervision of Mr. David Fokum, Mr. Alex Brown, and Dr.Marcela Vizcaychipi. These projects focused on using ICU data to predict delirium outcomes, length of stay, and survival rates. Notably, my project on delirium was showcased at the ESICM 2022 exhibition.

Horizon Fellowship project summary: As a Junior Data Engineer in the Data Warehouse department, I frequently receive data requests regarding clinical events. These requests often necessitate extracting relevant medical notes from Cerner and creating custom SQL queries to search for keywords within free text, as the data is not readily available. This process is complex and inefficient, involving custom data ingestion, manual SQL queries, data cleansing, and exportation, all of which are time-consuming. I aim to address these complexities and inefficiencies in processing structured medical notes by using Azure AI services (natural language processing and image processing)

Estimated number of patients / staff impacted by the project: It would help with staff who need data across the trust

Goal(s) for time on the Horizon Fellowship programme: To connect with industry experts, engage in research projects, and build my portfolio. This opportunity will provide valuable connections and hands-on experience, helping me to develop the skills necessary to advance my career in data engineering and AI in the medical field. By developing a streamlined dataflow, we can enhance the efficiency, accuracy, and scalability of processing structured medical notes, ultimately improving our data management capabilities in the Data Warehouse department.