Master Assignment
[M] NLP model to predict diabetes type and year of diagnosis from medical texts
Type: Master
Period: TBD
Student: (Unassigned)
If you are interested, please contact :
Data type(s): text and tabular data
Description: Clinicians treating diabetic patients often face challenges in accessing key health information, as it is scattered across the Electronic Health Record (EHR). Given the limited time during patient visits, important details like the number of years since diagnosis—often hidden in free text—and the type of diabetes, which may not be immediately clear, can be overlooked. Both factors are crucial for informed treatment decisions. This project aims to develop a system that extracts and organizes this information from a study database of around 400 diabetic patients, utilizing both free text and structured data collected since 2015.
Goal: Development of a model to predict/extract diabetes type and year of diagnosis from medical texts
Supervisors: Thomas Urgert (ZGT)