± SCIENCE Today’s artificial intelligence still faces two major challenges. One is that, in most industries, data exist…+ SCIENCE Deep learning takes on protein folding In 1972, Anfinsen won a Nobel prize for demonstrating a connection bet…± SCIENCE Significance Deep neural networks are currently the most successful machine-learning technique for solving a…+ SCIENCE Deep learning allows computational models that are composed of multiple processing layers to learn representa…+ HEALTH For the task of analyzing survival data to derive risk factors associated with mortality, physicians, researc…+ SCIENCE Artificial intelligence (AI) coupled with promising machine learning (ML) techniques well known from computer…+ SCIENCE Deep learning is revolutionizing many areas of science and technology, especially image, text, and speech rec…+ SCIENCE Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized dif…
TruaceTracing the truth around AIMonday, July 13, 2026
Subscribe
Science·G Space·Evidence-backed gain·Published 2026-07-13

Integrating machine learning and multiscale modeling-perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences

Fueled by breakthrough technology developments, the biological, biomedical, and behavioral sciences are now collecting more data than ever before. There is a critical need for time- and cost-efficient strategies to analyze and interpret these data to advance human health. The recent rise of machine learning as a powerful technique to integrate multimodality, multifidelity data, and reveal correlations between intertwined phenomena presents a special opportunity in this regard. However, machine learning alone ign…

TRV-2026-0204Peer-reviewedPermanent record — cite & verify
Integrating machine learning and multiscale modeling-perspectives, challenges, and opportunities in the biological, biomedical, and behavioral sciences

"Doctor's Hospital" by Cindy Funk is licensed under CC BY 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by/2.0/.

The quick read

Published in November 2019, this perspective review argues that breakthrough data collection in biology and medicine requires new analysis strategies. The authors contend that machine learning and multiscale modeling are complementary and demonstrate how their integration can produce physics-aware predictive models that handle massive, heterogeneous datasets.

The integration matters because it could improve understanding of disease mechanisms and inform target identification and treatment decisions for human health. What remains uncertain are the open questions and implementation challenges across ODE, PDE, data-driven and theory-driven methods that the authors say need to be addressed to realize robust applications.

Main points
  • Biological, biomedical, and behavioral sciences are collecting more data than ever before, creating need for time- and cost-efficient analysis strategies.
  • Machine learning alone ignores fundamental laws of physics and can produce ill-posed or non-physical solutions, while multiscale modeling alone often fails to efficiently combine large heterogeneous datasets.
  • Authors review integration across ordinary differential equations, partial differential equations, data-driven approaches, and theory-driven approaches leveraging applied mathematics, computer science, and medicine.
Gain

Combining machine learning with multiscale modeling creates robust predictive models that integrate underlying physics to manage ill-posed problems and can provide insights into disease mechanisms and treatment strategies.

The rundown

The article frames a data-rich moment in the biological, biomedical, and behavioral sciences and argues that neither machine learning nor multiscale modeling alone is sufficient. It proposes their integration to handle multimodality, multifidelity data while respecting physical laws.

It organizes discussion around four topical areas: ordinary differential equations, partial differential equations, data-driven approaches, and theory-driven approaches, drawing on expertise from applied mathematics, computer science, computational biology, biophysics, biomechanics, engineering mechanics, experimentation, and medicine.

Sources

Reader signal

How should this claim be treated?

The debate