The Courant Institute of Mathematical Sciences at New York University (NYU) and the Department of Radiology at the NYU Grossman School of Medicine invite applications for two Postdoctoral Research Associates to work on projects in the interdisciplinary field of Machine Learning and Healthcare. The project’s goal is to learn unified high-dimensional distributed representations of patients using healthcare data from multiple modalities, including medical imaging, electronic health records (EHRs), and wearable sensors, among others. Furthermore, the projects will also involve exploring ways to leverage longitudinal (temporal) patient data to learn such representations.
The postdocs will work with Prof. Sumit Chopra and Prof. Daniel Sodickson. Learning accurate and useful patient representations will require working at the intersection of machine learning, signal processing, and physics-based modeling. There are many scenarios under which such representations can be learned, including using unimodal/multimodal and static/dynamic (temporal) datasets. Despite the enormous promise of machine learning applications in healthcare, the deployment of machine learning models in real clinical settings has remained elusive. The projects will also focus on exploring ways to utilize representations to derive real clinical benefits, such as improving diagnostic accuracy, speeding up image acquisition, and proposing personalized treatment plans.
Through this position, you will be a part of (and working at the intersection of) two of the most sought-after schools in their respective fields, namely the Courant Institute (a leader in applied mathematics and machine learning) and the Grossman School of Medicine (a leader in healthcare research and delivery). This opportunity will also allow you to readily deploy your research in a clinical setting within the hospital, thereby enabling you to make a real-world impact, saving and/or improving the lives of real people.
The positions are available immediately. They are full-time appointments for one year, with the possibility of renewal for up to three years. The renewal is subject to satisfactory performance and availability of funds.
