Caitlyn Schulz

Engineered a real-time Machine Learning pipeline for intrapartum fetal heart rate (CTG) analysis. Designed and fine-tuned Deep Learning architectures, specifically Transformers and LSTMs, to enhance Clinical Decision Support Systems (CDSS). Led the research, writing, and submission of the publication: "Integrating Clinical Parameters and Cardiotocograms for Real-Time Alerting".

Developed a novel approach for real-time CTG interpretation, which served as the foundation for my Master's thesis. Trained Machine Learning models for automated CTG analysis utilizing real-world patient data. Collaborated closely with medical professionals in an interdisciplinary team, focusing on data acquisition, requirements analysis, and the clinical interpretation of results.

Part of my participation in the "DigiStrucMed" program (Dept. of Obstetrics and Gynecology). Clinical observation in delivery room and maternity wards. Requirement analysis for computerized Clinical Decision Support Systems (CDSS) in everyday clinical settings.

Contributed to research and teaching activities in the field of Medical Informatics. Served as a Teaching Assistant for the lectures "Assistierende Gesundheitstechnologien A" and "Bild- und Signalerzeugung in der Biomedizin".

Field of Study: Medical Informatics Master's Thesis: „Computerized interpretation of fetal heart rate during labor including clinical parameters“ (Grade: 1,0)

Field of Study: Medical Informatics Bachelor's Thesis: „Analyse der Genauigkeit von Single-Frame und Multi-Frame Pose Estimation Algorithmen bei Bewegungen im EKG-Sessel“ (Grade: 1,3)