Some parts of this content are currently available in German only.

AI Enrichment Methods for Medical Technology Expansion of healthcare AI functionalities

The Institute of Medical Engineering, working alongside Shenkar (School of Industrial Engineering & Management), is at the forefront of innovation in the field of healthcare AI. This collaboration focuses on the design, development, implementation, and execution of experiments involving cutting-edge AI technologies, including Machine Learning (ML) models, Automated Machine Learning (AutoML), and others. The goal is to enhance the capabilities of AI in healthcare, thereby improving decision-making processes and expanding the functionalities of AI systems within the sector.

Digitales Bild Dataengineering

Innovation of AI procedures to enrich the Healthcare decision-making process via improved data analysis functionalities

AI methods are extensively applied across various services and applications, particularly in Medical Technology. The proliferation of data, coupled with the necessity to cleanse the data of anomalies, errors, null values, biases, and other irregularities, poses a significant challenge in analyzing high quality data to derive accurate predictions. This process becomes critically important in the Healthcare sector, where decisions can be life-saving. In such a context, every piece of input and method used can have a profound impact.

Datennetz

The collaboration between Prof. Dr. Fabian Ille, head of the Competence Center in Biomedical Space Research and Medical Engineering, Vincent Salvadori from the Institute of Medical Engineering, and Dr. Oded Koren, who leads the "Management of Digital Systems" specialization at Shenkar (School of Industrial Engineering & Management), is dedicated to achieving groundbreaking advancements in AI. Their objectives include innovating new AI models through the application of AutoML domains, as well as exploring initiatives in quantum computing. The ultimate goal is to enhance data analysis and prediction models through innovative classification methods, clustering procedures, combination functionalities, and beyond.

This collaborative effort is characterized by the design, implementation, and experimentation with various research datasets to evaluate the effectiveness and advancements offered by these new techniques compared to the traditional AI/ML methodologies currently in use. The aim is to refine AI/ML model predictions and outcomes, thereby bolstering confidence in decision-making processes within the Medical Technology sector. Ultimately, this initiative seeks to develop superior AI models that serve the needs and aspirations of the Medical Technology community, driving forward innovation and precision in healthcare.