Student for Dynamic AI-driven thrombosis risk prediction in ICU patients

Afdeling

Stage, afstuderen en scriptie

Werkomgeving

With over 13,000 employees, UMCG is the largest employer in the Northern Netherlands. UMCG is a matrix organization in which the core tasks of patient care, education, training, and research are organized into clusters and cross-functional units.
In this project you will work in a clinical research environment closely related to the ICU, focused on improving prediction of patient outcomes through predictive modelling. This project builds on earlier work in thrombosis prediction.
What is the problem?
Thrombosis is a common and serious complication in hospitalized patients. Although prophylactic treatment with low dose anticoagulants can effectively prevent thrombosis, it may also cause harm through bleeding. Therefore, predicting who is at risk of developing thrombosis is a key first step in order to apply individualized prevention.
Current prediction models rely mainly on structured data and static snapshots (usually at hospital admission) whereas large amounts of valuable unstructured clinical EHR data that would in theory be able to describe the clinical course and thus improve predictions, remain unused.

Functiebeschrijving

In this project, you will contribute to developing a novel pipeline for dynamic thrombosis risk prediction using electronic health record (EHR) data. Depending on your interests, the project can be more data engineering–focused or AI-focused.
Your tasks may include:

• Designing and building a data pipeline / platform for clinical data (raw EHR ? de-identification ? preprocessing)


• Integrating structured (e.g. lab values) and unstructured data (e.g. clinical notes, radiology reports)


• Exploring LLM (or alternative methods)-based feature extraction from unstructured data. A concrete example includes training a model to reliably classify radiology reports as VTE yes/no and if yes, where) but there are many potential use cases here, in increasing difficulty.


• Develop a dynamic, time-dependent prediction model for VTE risk


• Evaluating how inclusion of unstructured data improves prediction performance

Wat vragen wij

You're in a relevant HBO or WO program, for example in Data Science, AI or Biomedical Engineering

• Affinity with AI, data engineering, or healthcare


• Interest in working with clinical data


• Independent and proactive attitude


• Good communication skills


• Python experience

Wat bieden wij

• Internship agreement with UMCG


• Good supervision at UMCG


• Scientific working environment

Meer informatie

Neem voor meer informatie contact op met:
[email protected]

Solliciteren

Good to know: in consultation, you can partly work from home.Interested? Feel free to take some time to consider this vacancy, but don’t wait too long… We will close the vacancy once we find a suitable candidate (the closing date is fictitious). You can easily apply via the application button. After receiving your application, you will immediately receive a confirmation. We select once a week and invite suitable candidates for an interview. Is there a match? Then we will register you for the UMCG internship agreement.
Digitaal sollicitatieformulier