Publications from: Integrating Machine Learning with Multiscale Modeling for Biomedical, Biological, and Behavioral Systems (2019 ML-MSM)

Integrating Machine Learning with Multiscale Modeling for Biomedical, Biological, and Behavioral Systems (2019 ML-MSM)

to

Bethesda, Maryland (NIH Campus)

Meeting perspective paper

A review article based upon perspectives from this meeting in October 2019 has been published in NPJ Digital Medicine.

Read the meeting perspective paper here.

Citation: Integrating machine learning and multiscale modeling-perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences. Alber M, Buganza Tepole A, Cannon WR, De S, Dura-Bernal S, Garikipati K, Karniadakis G, Lytton WW, Perdikaris P, Petzold L, Kuhl E. NPJ Digit Med. 2019 Nov 25.

 

Follow-up paper

Multiscale Modeling Meets Machine Learning: What Can We Learn?

 

Co-Chairs:  Suvranu De and Ellen Kuhl

october meeting posterWith breakthrough technology developments throughout the past decades, biomedical, biological, and behavioral research is now collecting more data than ever before. There is a critical need for time- and cost-efficient strategies to analyze and interpret those data. Multiscale modeling has advanced to one of the most successful strategies to integrate data across the scales and offer mechanistic insights; yet, multiscale modeling alone often fails to efficiently combine large data sets from several different sources. Machine learning is a powerful technique that can guide model building, accelerate multiscale and multiphysics computational algorithms, train models to learn from data, identify patterns, and inform decision making. While traditional machine learning tools perform these tasks with minimal human intervention, this meeting focuses on integrating machine learning methods with multiscale modeling methods guided by the fundamental principles of mathematics and physics. The objective of this meeting is to identify the perspectives, challenges, and opportunities of integrating machine learning with multiscale modeling (ML-MSM) in biomedical, biological, and behavioral systems. Specifically, we will address four approaches within ML-MSM modeling: ordinary differential equation based, partial differential equation based, theory-driven, and purely data-driven approaches. Attendees will discuss these approaches in the context of developing Digital Twins and addressing Human Safety

The meeting will feature keynote speakers describing multiple domain approaches to developing Digital Twins and addressing Human Safety.  Theme sessions on the four modeling approaches will present the current state-of-the-art ML-MSM integration.  The audience will actively participate in panel discussions, poster sessions, and breakout sessions to further distill these discussions to shape the future of machine learning with multiscale modeling with new challenges and opportunities.

Scientists addressing challenges in biomedical, biological, and behavioral systems, researchers from engineering, mathematics, physics, computer sciences, industry, and regulatory agencies are encouraged to attend!

Hosted by the Interagency Modeling and Analysis Group (IMAG) and the Multiscale Modeling (MSM) Consortium

Meeting date
Meeting location
NIH Main Campus Bethesda, MD
Journal publication information (if applicable)
Alber, M., Buganza Tepole, A., Cannon, W.R. et al. Integrating machine learning and multiscale modeling—perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences. npj Digit. Med. 2, 115 (2019) doi:10.1038/s41746-019-0193-y