The candidates will be integrated in the section of Applied AI and Data Science (AID), as part of the Maersk Mc-Kinney Moller Institute, and will interact with a dynamic group of researchers working in interdisciplinary teams on developing potent solutions to societal challenges.
In AID we combine expertise in artificial intelligence, statistical machine learning, and data science to improve people's health and protect our environment. In our research, we aim to develop methods for data-driven solutions in the medical and renewable energy sectors, by striving to improve the way of handling and gaining insight from data. Thereby we create knowledge and value for our collaborators across the public health and private industrial sectors.
Job description The successful candidate will contribute actively to the research activities of the group, by applying different artificial intelligence and data science approaches towards the improvement of medical prognostic and diagnostic accuracy, personalized treatment and clinical decision making. More specifically, the successful candidate will be working on two commenced projects on: (i) early detection of liver fibrosis, and (ii) prostate cancer, in collaboration with Odense University Hospital.
Project I: Early detection of advanced liver fibrosis
Early detection of advanced liver fibrosis is very time-consuming and costly, as there are no obvious symptoms or easy diagnostic tools that accurately reflect the outcome. Through combining personal health information (e.g. weight, height, body mass index) with blood analyses and liver function tests data, we aim to develop an intelligent algorithm with high accuracy to detect liver fibrosis at an early stage of the disease.
Project II: Prostate cancer
The purpose of this project is to use non-conventional statistical methods to detect indicators in the past medical history able to predict the emergence of metastases in prostate cancer patients. The final aim is to develop a clinical decision tool able to determine the treatment with the greatest benefit to the patient.