Expertise Needed for the 2027 BDSIL

The Biomedical Data Science Innovation Lab (BDSIL) invites late-stage postdoctoral fellows and early-career faculty investigators with important questions in cardiology and heart health - questions that could benefit from new data science methods, interdisciplinary collaboration, or more effective use of complex biomedical data. Cardiovascular research draws on many kinds of evidence: genomic and other molecular data; cardiac imaging; electrocardiography and other physiologic signals; electronic health records; clinical laboratory results; wearable and mobile health measurements; and information about patients’ environments, behaviors, and access to care. Integrating these sources can help researchers characterize cardiovascular health and disease, identify risk factors and biomarkers, understand disease progression and treatment response, and develop better ways to predict and improve outcomes. These data are often collected at different times, scales, and levels of detail. Their analysis may require methods for data harmonization, statistical modeling, machine learning, causal inference, longitudinal analysis, prediction, and clear visualization. BDSIL will bring together biomedical and data science investigators to develop promising research questions and approaches in cardiovascular science. Applicants do not need to work with every data type, or to have an existing data science collaborator. They should bring a well-defined cardiovascular question and an interest in working across disciplines.

In this context:

“Biomedical" expertise can involve but are not limited to:

Investigators from basic, translational, clinical, and population health research are encouraged to apply. The following areas illustrate the range of expertise that can contribute to the Lab:

  • Investigators with experience in neurobiology and neurochemistry who have research questions involving the role of the brain and central nervous system which might benefit from data science solutions.

  • Investigators who have research questions relating to human or animal behavior and psychology which may be genetically influenced.

  • Investigators who have research questions involving multi-omics emerging from advances in biology and computational medicine or data science, including moral discernment as it relates to medical policy and practice.

  • Investigators who have research questions looking at the underlying biological mechanisms important to our fundamental understanding of biology.  Specifically, this includes geneticists and investigators working to collect genomic, transcriptomic, metabolomic, etc., datatypes.

  • Investigators involving patient samples, comparisons between disease phenotypes, cross-sectional studies, as well as the assessment of longitudinal time courses of treatment outcomes.

  • Investigators who have broad ranging questions on the influence that ecology, biodiversity, and the environment that have on the implications for genetic illnesses and the application of data science.

  • Investigators who have research questions involving the health distribution and determinants within communities, regions, etc. to positively impact health services, access, and disease outcomes.

  • Investigators who have research questions relating to complex data mining and analysis relating biomedical data from health and disease. Data including but limited to medical imaging, microscopy, genomic, metabolomics, electrophysiology, electronic health records, mobile health data, wearables/sensors, as well as  geospatial location data.

  • Investigators who have research questions relating to the well-being of humans and their ability to cope with stresses, engage and contribute to their individual communities.

  • Investigators who have experience and/or training in public health, medicine, pharmacy, economics, and demography with research questions that intersect with biomedical data science.  Also encouraged, are investigators interested in how policies shape these outcomes and how efforts address needed changes to harness big data initiatives to improve health outcomes.

  • Individuals with experience in university-level education and instruction in biomedical science who possess a deep understanding of the intricate workings of the human body and its various systems. They are faculty members equipped with comprehensive knowledge in areas such as anatomy, physiology, genetics, and pharmacology, allowing them to contribute to cutting-edge research, healthcare advancements, and clinical practice. Such experts play a pivotal role in undergraduate and graduate teaching, research on, diagnosing, and treating diseases, as well as seeking to push the boundaries of medical innovation through the use of data science approaches.

"Quantitative" expertise can involve but are not limited to:

Data and computationally-focused late-stage post-doc or early-stage junior faculty level investigators having research questions in novel quantitative methods, data analytics, statistical modeling, machine learning, and data visualization.   This is important since spatial multi-omics depends upon massive quantities of regionally-specific data from the body. Facility with advanced mathematics, programming languages, and high-performance computing are particular areas of strength we wish to engage.  These areas also include:

  • Investigators with mathematical approaches applicable to issues in biomedical applications. For instance, the development and deployment of novel PDE methods, complex geometry, non-linear dynamics, as well as their applications in clinical biomedical systems for patient monitoring, the meta-analytic examination of medical records, and electronic health records.

  • Those working to develop artificial intelligent systems for clinical decision making. For instance, generative models, convolutional neural networks (CNNs), clinical support systems, agent-based applications, algorithm designs, Large-Language Models (LLMs), decision trees, emergent networks, etc. 

  • Investigators with experience in statistical methodologies, multivariate analysis, Bayesian inference, distributional theory, calculus, and approaches to improve project direction and statistical significance. Investigators with experience in clinical trials and developing projects based at the population level are encouraged. 

  • Investigators with computational expertise and research questions that involve developing novel software tools and workflows to harness big data capabilities, especially biomedical data types.

  • Investigators with the knowledge and expertise to apply appropriate machine learning models and visualization of results.

  • Those working in the process of converting written or spoken language to useful, digitized data and on tasks like information extraction and machine translation.

  • Investigators with a solid foundation in advanced mathematics and interest in approaching problems from a theoretically-driven point of view seeking work with biomedical investigators in creating novel mathematical models that will be tested and further developed based. 

  • Investigators with the knowledge to account for disparities, provenance and metadata annotations that are crucial to link datasets that span rural/urban communities, geography, and environments.