Federated Causal Discovery in Medicine: Trends, Opportunities, and Challenges
Abstract
Exponential growth and continued digitisation have accelerated the adoption of data-driven and evidence-based approaches in medicine. This includes deciphering associations, including potential causal associations, from multivariate observational biomedical data under certain implicit assumptions. Such an evidence approach marks the shift from classical hypothesis testing to discovery and hypothesis generation. Widespread adoption of common data models has especially accelerated collaborative approaches in medicine while transitioning from centralised to federated architectures that facilitate discovery without the explicit sharing of sensitive medical data. This perspective provides an overview of causal discovery from observational data with a focus on federated learning. Specifically, it outlines the trends, opportunities, and challenges of federated causal discovery in medicine. While medical research has traditionally relied on the hierarchy of evidence generated from the evidence pyramid, the ability of federated causal discovery to facilitate evidence generation collaboratively from heterogeneous sources is expected to enhance the generalizability and transportability of findings while addressing sample size considerations—a critical aspect for its successful and widespread adoption in medicine.
Related
- Opportunities and Challenges for Promoting Sustainable Diets within "Food is Medicine" Programs in the United States: A Qualitative Research Study.
- Tumor microenvironment-driven immune evasion in triple-negative breast cancer: mechanisms, clinical challenges, and therapeutic opportunities
- Grounding meaning in social and emotional experience: Challenges and opportunities
- Central Nervous System Reservoirs and HIV Cure: Therapeutic Opportunities and Challenges.
- Pharmacological Modulators of TCTP: Opportunities and Challenges for Drug Repurposing
BibTeX
@article{rocchi2026federated,
title = {{Federated Causal Discovery in Medicine: Trends, Opportunities, and Challenges}},
author = {Niccolò Rocchi and Marco Scutari and Alessio Zanga and Radha Nagarajan and Fabio Stella},
journal = {Frontiers in Digital Health},
year = {2026},
month = jul,
doi = {10.3389/fdgth.2026.1846020},
url = {https://hal.science/hal-05388288v2},
note = {CC BY-SA 4.0},
}
RIS
TY - JOUR
TI - Federated Causal Discovery in Medicine: Trends, Opportunities, and Challenges
AU - Niccolò Rocchi
AU - Marco Scutari
AU - Alessio Zanga
AU - Radha Nagarajan
AU - Fabio Stella
PY - 2026
DA - 2026/07/17
JO - Frontiers in Digital Health
DO - 10.3389/fdgth.2026.1846020
UR - https://hal.science/hal-05388288v2
AB - Exponential growth and continued digitisation have accelerated the adoption of data-driven and evidence-based approaches in medicine. This includes deciphering associations, including potential causal associations, from multivariate observational biomedical data under certain implicit assumptions. Such an evidence approach marks the shift from classical hypothesis testing to discovery and hypothesis generation. Widespread adoption of common data models has especially accelerated collaborative approaches in medicine while transitioning from centralised to federated architectures that facilitate discovery without the explicit sharing of sensitive medical data. This perspective provides an overview of causal discovery from observational data with a focus on federated learning. Specifically, it outlines the trends, opportunities, and challenges of federated causal discovery in medicine. While medical research has traditionally relied on the hierarchy of evidence generated from the evidence pyramid, the ability of federated causal discovery to facilitate evidence generation collaboratively from heterogeneous sources is expected to enhance the generalizability and transportability of findings while addressing sample size considerations—a critical aspect for its successful and widespread adoption in medicine.
SN - 2673-253X
ER -