Data-Driven Discovery Initiatives

In January 2019, aligning with the UM System Research Strategic Initiative, MUII launches four initiatives with seed funding up to $200K per initiative annually for next five year to achieve $30M 5-year expenditure in informatics and data science related research and training programs by 2023. This program aims to build a comprehensive profile through new extramural research grants (multiple R01's and a P- or U- centergrant by 2023), training projects (multiple T32's, NLM T15, and NSF NRT), and entrepreneurship (patent applications, licensing, and startups.) The seed funding derives mainly from the revenue generation of MUII's executive MS program and partnership with other entities, such as industry, government, and private foundations. Potentially, signature projects could go up to $750k for two years through the Tier 2 funding from UM system's Strategic Initiative Program. These four initiatives will empower campus-wide and system-wide data-driven researchers to seek large-scale and multi-investigator funding and provide a data competency training program for all disciplines.

Initiatives

Latest Events

Precision Medicine

Leaders

Dr. Dmitriy Shin

Dr. Richard Hammer

Dr. Jeffrey Bryan

Overview

Data-Driven Precision Medicine research initiative, sponsored by MU Informatics Institute, is aimed to establish and expand data-driven precision medicine research at MU by undertaking increased effort to bring extramural funding through facilitation of new data science informatics ideas and projects.

The DDPM research themes are centered around cancer, cardiovascular and neurological diseases. The DDPM research themes can be broadly broken, but not limited, into the following categories.

  • Development of novel computational methods and informatics pipelines that infer patient-specific biological processes in a high-explanatory fashion
  • Development of novel computational methods and informatics pipelines that translate genomic findings into clinical practice
  • Development of informatics tools and software that facilitate usage of biomedical knowledge for translational precision medicine applications
  • Development of novel methods in biomedical imaging informatics for precision medicine analytics

DDPM initiative is expected to make a broader impact on MU data-driven biomedical research and education by spanning various research activities such as informatics Ideas Clubs, Hackathon activities, colloquium series, curriculum development, campus-wide forums and journal clubs for data-driven precision medicine. Finally, we expect DDPM to greatly facilitate increase in data-driven research MU expenditure through a comprehensive profile of new extramural research grants to multiple NIH R01’s and a P- or U- center grant (by 2023), training projects via multiple NIH NLM T32’s, NLM T15, and NSF NRT, and entrepreneurship (patent applications, licensing, and startups) and collaboration with industrial partners (GE HealthCare and Roche Diagnostics).

Agriculture

Leaders

Dr. Derek Anderson

Dr. Guilherme DeSouza

Dr. Felix Fritschi

Overview

Agriculture is an integral part of life, civilization, and economy, with applications ranging from food to medicine. Current estimates put thrusts like precision agriculture at 4 billion USD with an estimated compound annual growth rate of 13%. The data driven Agriculture (DDAg) seeks to foster innovation in (g1) sensors and novel platforms, (g2) eXplainable artificial intelligence (XAI), and (g3) data translation for implementation in agriculture. These goals address the spectrum of sensing to visualization, decisions, and actions, with an emphasis on trustworthy and transparent human-in- and human-over-the-loop solutions. The DDAg Initiative aims to increase MU cross- and inter-disciplinary activities in (g1)-(g3) by funding internal seed projects, connecting faculty, educating students, exploring curriculum options, and resources to increase external visibility and funding.

Behavior and Social Science

Leaders

Dr. Eileen Avery

Dr. Clintin Davis-Stober

Overview

The goal of the Tiger Choice: Computational Social and Decision Sciences project is to develop an interdisciplinary, university-wide, computational and data sciences center that specializes in the decision sciences, with a particular focus on health and public health. Understanding, modeling, and predicting individual choice is a challenging, yet fundamental aspect of human behavior that touches our everyday lives. Because it focuses on the broader context in which individual decisions are made, decision science is unique in the way it draws scholars from across disciplines. Tiger Choice will bring together researchers from fields including Psychology, Sociology, Public Policy, Social Work, Communications, Health Management, Informatics, Health Sciences, Family and Community Medicine, and Engineering. This group aims to investigate a wide range of questions; e.g., (i) how patients and doctors can make better end-of-life decisions in medical care, (ii) a clearer understanding of how individuals with alcohol use disorder make risky decisions, and (iii) how lawmakers can make effective policy decisions to reduce drug dependency. The long-term goal of the Tiger Choice group would be to submit center-level grants within a five-year span. We aim to develop the necessary infrastructure to house big-data projects along with scholars with cutting-edge computational and informatics tools to analyze such data.

Rural and Population Health

Leaders

Dr. Dale Fitch

Dr. Sonal Patil

Dr. Lori Popejoy

Overview

Data Driven Rural and Population Health (DDRPH) will establish and expand data-driven rural and population health at MU by undertaking increased efforts to bring extramural funding through facilitation of new data science informatics ideas and projects. The DDRPH research themes are centered on chronic diseases and conditions that have a strong correlation with Social Determinants of Health (SDOH). The DDRPH research themes can be broadly broken, but not limited, into the following categories.
• Development of novel computational methods and informatics to identify actionable SDOH related to specific chronic healthcare conditions
• Incorporate SDOH decision making into clinical practice via the electronic health record
• Development of informatics tools and software that facilitate usage of SDOH into the community healthcare delivery process
• Develop new methods (e.g., apps) to feed health outcome data back into the SDOH models and the electronic healthcare record