Student for developing machine learning models improving sepsis prediction

Would you like to actively contribute to the development of machine learning models to improve sepsis prediction by integrating biomarkers and clinical data?

Are you interested in complex logics and able to translate raw data into algorithms?

Can you build bridges between the needs of the patient and data science?

In that case, we would like to invite you to read on!

Student for developing machine learning models improving sepsis prediction

Your role

You will analyze and preprocess clinical datasets (e.g., patient records, vital signs) and work with biomarker data to identify predictive patterns. You will develop and evaluate machine learning models for early sepsis detection. During your internship, you will collaborate with clinicians and researchers to interpret results. You will conclude your internship by presenting findings in reports and/or scientific presentations.

Working environment

Sepsis, a life-threatening condition resulting from the body's extreme response to an infection, remains a significant challenge in acute care. Despite medical advancements, sepsis continues to have high morbidity and mortality rates. Consequently, sepsis research is crucial in developing effective treatments and improving patient outcomes. Researchers in this field focus on understanding the pathophysiology, early diagnosis, and innovative treatments to combat this severe condition.

Recognition of early sepsis is critical to allow timely initiation of adequate treatment: antibiotics and supportive care. We use big data to develop novel algorithms to improve early recognition of sepsis and identify which patients benefits the most from which therapy (personalized medicine) using deep learning. To facilitate this kind of research, we have set up the Acutelines data-biobank at the ED of the UMCG. The purpose of the Acutelines data-biobank is to improve prevention, recognition and treatment of acute conditions. A trained team of researchers screens all patients entering the ED, followed by data and biomaterial collection depending on broad selection criteria. In addition to demographic and medical data from the electronic patient file, we collect and store biomaterials (blood, urine, stool) for biomarker discovery, take a photograph of the face to predict deterioration using computer vision techniques, and record continuous electrophysiological waveforms (i.e. ECG, PPG, EMG) to identify features predictive of deterioration. In the current project, we will focus on developing machine learning models to improve sepsis prediction by integrating biomarkers and clinical data.

What are we looking for?

You are currently a student at a university (of applied sciences) pursuing a degree with a focus on data science, such as Data Science, Artificial Intelligence, Biomedical Engineering, or a related field.

• You have basic knowledge of machine learning techniques (e.g., regression, classification, neural networks)
• You have experience with Python (e.g., pandas, scikit-learn, PyTorch or TensorFlow)
• You are interested in healthcare applications and clinical data analysis
• You have strong analytical and problem-solving skills

Preferred qualifications:

• Experience working with medical or clinical datasets
• Familiarity with time-series analysis
• Visual Studio Code user

What do we offer?

• Internship contract with the UMCG
• Good supervision/guidance in the UMCG
• Embedding of acute research, including Acutelines
• Scientific working environment
• Places with flexi-places, equipped with a PC

Good to know: in consultation, you can partly work from home.