Back to 2024 Agenda
Next Steps for BDT Idea Teams
Moderator: Gary An
Next Steps for IMAG/MSM and BDTs
Moderator: Hannah Dueck
Discussion
People are interested in having another meeting next year
Topics:
1) (Delia De Buc) Federated Learning, translational framework to "mount" DT for specific applications
2) (Tina Morrison) Developing a maturity model for digital twins, looking at each component for a particular context of use, assess maturity of each component
3) (Dan Isaacs) Digital Twin Consortium - "composability" (61 components) of a DT - expanding key elements of digital engineering, digital threads, DOD 5097 - product lifecycle realized through the digital twin, capabilities table, 12 use cases (under initiative tab) --> joint consortium WG proposed with IMAG/MSM
4) (Drew Pruitt) spending time on taxonomies, preparing for maturation
5) (Gary An) 2 things that make it hard to embed MSM into NASEM loop: 1) mathematical methods specific to VVUQ of multi-cellular MSM - essential for drug discovery, biomedical research to take molecular entities to affect the course of disease, include people from other domains; 2) bring MSM with device engineers to make non-destructive interrogate cellular/molecular milieu --> propose these 2 workshops
6) (James Glazier) bring in European efforts for discussion; toxicology (NIH-COMPLIMENTAIRE) with European efforts too (NAMS)
7) (Emek) multiple clinical trials under different names, with longitudinal measurements of patients, would be useful to have representatives of these trials to join the MSM
8) Publications/Perspective Piece/White Paper
9) Interested in creating/joining new Working Group and what topic?
Comment
I believe your point on healthy models is spot on. The question is how to offer subjects a value proposition that makes them want to donate data. Personally, I believe commercial, nonmedical devices are key to this step.
I believe your point on healthy models is spot on. The question is how to offer subjects a value proposition that makes them want to donate data. Personally, I believe commercial, nonmedical devices are key to this step.
Write you name and contact information here
I am interested in volunteering for writing publications.
Name: Sanjay Purushotham, contact: psanjay@umbc.edu
Interested in participating
Contact Info- dcabrera2@med.miami.edu and delia_debuc@multinostics.com
I am interested in participating in the position paper/white paper from this meeting.
Tien Comlekoglu
tc2fh@virginia.edu
Interested in contributing to the white paper - eric.stahlberg@nih.gov
Grace, there was no link for replying on point 9, so I am Interested in creating/joining a new Working Group. What topic? Federated learning/translational DT framework- the one I proposed earlier
I am interested in writing the meeting report or white paper.
As the owner of a Women-Owned Small Business, I am interested in collaborating with academic institutes on building a BDT talent pipeline, offering students and trainees career opportunities after they graduate, and building a Team Science-based team for the sustainable BDT development.
Zhen Xiao zhen.xiao@truvante.com
I am interested in working on a white paper, georges@ecu.edu
Contact: anirbanc@oden.utexas.edu
I would be interested in contributing to perspective piece or other publication.
Interested in creating new Working Group and what topic; songx@ohsu.edu
Hi. I am interested in:
2, 5, 8, 9
For 9: I would be interested in a VVUQ working group, and in developing a prototype BDT.
Ansu (snigchat@umbc.edu)
I am interested in 1) Delia De Buc's Federated learning topic for next meeting. My current research focuses on Federated Learning for healthcare.
9) Interested in joining/creating and participating in a working group on Federated Learning for Biomedical Digital Twins.
5) interested in participating and contributing to Gary An's workshop on mathematical methods specific to VVUQ of multi-cellular MSM
Contact: Sanjay Purushotham, psanjay@umbc.edu
interested in white paper/publication: jung-hyun.lee@downstate.edu
Pain points for Biomedical digital twins
Pain point: Evolved systems are coupled tangled hot mess with substantial heterogeneity.
Key Question: How are biomedical digital twins(BDTs) different from Digital Twins(DTs) commonly used in other fields including manufacturing and climate science?
Evolved vs manufactured vs non-evolved physical domains
Within organism and across population heterogeneity
Pain Point: Anna Karenina principle: all healthy subsystems are similar, all non-healthy subsystems diverge in their own way.
Key Question: Do we need baseline models of “healthy population” to build models of disease? What are the limitations if we don’t? How hard it is to build good baseline models?
Baseline models > easier to connect to first principles
Baseline models > easier to collect data in some cases
Pain Point: We are all similar to each other but similar in different ways.
Key Question: How should the cohort wide information should inform the BDT?
Parameterize baseline at the level of individual (interpolation)
Default priors
Cohort informed independent priors
Cohort informed manifold
Model disease with in silico perturbations (extrapolation)
Important that the models are connected to mechanistic components
Pain Point: Humans are not good at evaluating 20.000 data points. Patients and clinicians are humans Ergo…
Key Question: What is the interface between a BDT and clinical decision maker? What if the underlying model is not biologically/clinically grounded? What if the model is grounded but practically irreducible to simple causes/explanations?
Is simulation an explanation? Is UQ helpful or not for interpretability? Is interpretability different for interpolation vs. extrapolation components?
Paint Point : Humans don’t like to be poked repeatedly ( a literal pain point).
Key Question: What are the best modalities for digital twins? Imaging, liquid biopsy, wearables? Is there a way to quantify information value / collection cost ? Are there creative ways to augment limited data? How can we deal with sparse, asynchronized multi-modal, multi-scale measurements in a combined way? Baseline vs Longitudinal vs Real Time.
Pain Point: NimBio - Most people want to achieve the public good by sharing their personal biomedical data in a well protected, fair and transparent system. But a small fraction of the population can generate substantial obstacles if they are sharing-averse.
Key Question: What is the best way to advocate for best technical, social, legal and political solutions that balances public good with personal privacy. Is there an ethical way to nudge the system vs Opt-out default vs Opt-in default? (e.g. Denmark)
Pain Point: We have been in the same room for three days but we still provide divergent descriptions of common terms everytime we start explaining our point.
Key Question: How can we establish a common terminology and aspects to facilitate communication and cooperation in the field.
Common examples, use-cases definitions described using common language.