Analytics Pillar: Transforming Health Interventions

Health intervention research and implementation is one of the biggest users, as well as inspirations, of cutting-edge data science and AI methods. MIDAS collaborates with campus partners to enable the adoption of cutting-edge analytics and modeling of complex data to boost U-M’s biomedical and healthcare research. 

MIDAS Working Group on Sequential Decision Making Methodology

Aims: The focus of this MIDAS working group is to explore cutting-edge methodologies for sequential decision making with broad applications to healthcare, i.e., beyond micro-randomized trials/just-in-time adaptive interventions.

Activities: Through a series of meetings, the working group is identifying a) current and developing SDM methodologies that could be enhanced/extended by U-M researchers, and b) identifying current healthcare challenges that could be mitigated with the application of these methods. These meetings will culminate in a summer workshop where both SDM methodologists and clinical domain experts will, through presentations and working sessions, develop a number of pilot projects to pursue along with identifying data sources and potential funding opportunities.

Working Group Members: Danai Koutra (MIDAS, EECS), Jonathan Gryak (MIDAS, DCMB), Walter Dempsey (Biostats), Brian Denton (IOE), Vijay Subramanian (ECE), Ambuj Tewarj (Stats), Jenna Weins (CSE), Zhenke Wu (Biostats)

Who Will Benefit: Both SDM methodologists and clinical domain experts

Contacts: Jonathan Gryak (

Methods for Adaptive Interventions Training Workshop

Aims: a) To produce trainers with a strong grasp of the core components of adaptive interventions and available experimental tools for optimizing them. b) To produce and disseminate via a durable website a set of recommendations on how to teach/interpret the curriculum on optimizing adaptive interventions.

Activities: A workshop, to be run in Summer 2023, will be a train-the-trainer program in methods for optimizing adaptive interventions. Up to twelve individuals will receive training in these techniques. Selected participants must demonstrate a commitment to contributing to training activities (e.g., talks, workshops, courses) on adaptive interventions in the future.

Who Will Benefit: Biostatisticians, behavioral interventionists, and others who utilize adaptive interventions in their research.

Contacts: Daniel (Danny) Almirall ( and Inbal (Billie) Nahum-Shani (

NSF IUCRC : Center for Data-Driven Drug Development and Treatment Assessment (DATA)

Aims: The proposed Center for Data-Driven Drug Development and Treatment Assessment (DATA) intends to establish a center for precompetitive research into drug design, drug treatment assessment, drug repositioning, patient phenotyping, and quantitative pharmacovigilance using novel machine learning (ML) and artificial intelligence (AI) techniques. We will work with our partners from industry and state/professional organizations whose research efforts align with the proposed Center’s focus and who will be active collaborators in shaping the future paradigm of integrated and cost-effective patient care.

Activities: The Phase 1 proposal, which will establish DATA for an initial 5 year period, is currently under review by the NSF and is awaiting their decision. 

Partner Organizations: Fifteen partners have agreed to join the Center, including healthcare systems, non-profits, technology companies and pharmaceutical manufacturers, ranging in size from startups to multinational organizations.

Who Will Benefit: The proposed Center will be a hub to identify and address the complex and time-consuming nature of drug design and treatment assessment, creating solutions that not only reduce the cost associated with the drug design process, but also those that assess, monitor, and optimize treatment and overall patient health.

Contacts: Kayvan Najarian ( and Jonathan Gryak (

Bootcamp on Introductory Data Science for Biomedical Scientists

When: July 18 – 22, 2022 7am to 4:15pm

Overview: Participants will learn how to a) utilize supervised and unsupervised machine learning for clinical applications; b) employ deep learning for clinical applications; c) determine which data science/artificial intelligence techniques are appropriate for a given clinical application; and d) implement these methodologies in Python code. After completing the bootcamp, participants will be able to determine which data science/artificial intelligence techniques are appropriate for a given clinical application and apply them to their own clinical and/or research activities.

Who Will Benefit: This workshop is open to all biomedical scientists, but the content is geared towards junior faculty members and those from the public and private sector who are interested in learning about incorporating data science into their research. Please register by June 17. Later registrants will be accepted only if spots are available.

Contacts: Kayvan Najarian ( and Jonathan Gryak (