The main focus of this work will be to design and perform robust, large-scale retrospective analysis of multi-modal health data, as well as claims databases, for high-impact clinical questions. Key areas of interest are: predictive modeling for disease outcomes and personalized therapeutic recommendations, working with common data model EHR standards (e.g., OMOP), multi-modal (e.g., genomics, imaging, and clinical data) deep learning for clinical decision support, unsupervised learning to discover biologically-relevant disease subtypes, transforming real-world data to real-world evidence for supporting regulatory decisions, cost and comparative effectiveness for medicine in practice, and methods development to facilitate a learning health system, among others. We have an interest in many disease domains including nephrology, cardiology, radiology, psychiatry, and others.
The candidates will have the opportunity to develop their own research projects and to lead or participate in local as well as international collaborations. The postdoctoral fellow will join a dynamic team of data scientists, computer scientists, geneticists, and clinicians and participate in unique opportunities perform large-scale epidemiological surveys using unique data resources with the goal to directly impact patients’ lives.
The candidate will have the opportunity to work with unparalleled data and computational resources.
Access to >8 million patient EHR in the Mount Sinai Data Warehouse
The BioMe Biobank Program with >30,000 patients with whole exome sequencing data linked to longitudinal clinical data
High-performance computing cluster as well as internal servers
Various types of imaging data (e.g., MRI, x-ray).
The ideal candidates will have the following background:
PhD, MD, or MD/PhD in a quantitative science-related field (e.g., biomedical informatics, clinical informatics, machine learning, biostatistics, genetics, etc.)
Significant experience in machine learning techniques, ideally with published work and/or code available. Expertise with deep learning frameworks is preferred (e.g., Tensorflow, PyTorch, Keras).
Prior research using electronic health records or claims data sources preferred.
Expertise with programming and statistical software experience in R and/or Python.
Excellent publication track record.
Strong communication and presentation skills with fluency in spoken and written English.
We offer competitive compensation, a vibrant/supportive work environment, and a series of perks as outlined below.
Information on the Post-doctoral Training Program
Incoming postdoctoral fellows are eligible for affordable Mount Sinai Housing within walking distance of the medical school and a range of amenities
Visa sponsorship on a case-by-case basis.