RetiSEM: Generalising Causal Models for Fragmented Biomedical Data
RetiSEM: Generalising Causal Models for Fragmented Biomedical Data
Learning causal models from fragmented biomedical data is challenging because clinical, molecular, and imaging variables are often incomplete or not jointly observed. We propose RetiSEM, a domain-constrained structural equation modelling (SEM) framework for causal graph recovery and mediation analysis under limited multimodal resources. This proposed work organises variables into biologically informed blocks, applies forbidden-edge constraints, and decomposes pathway-level effects into TE, NDE, and NIE components. We evaluate RetiSEM across ten synthetic benchmark scenarios that vary in dimensionality, nonlinearity, causal depth, and pathway structure, together with a fragmented real-world setting that combines NHANES clinical variables with externally derived retinal representations. This approach achieves lower structural error and higher causal accuracy than unconstrained baselines across the synthetic benchmarks. In the real-data analysis, retinal variables behave mainly as downstream biomarker-like indicators, with smaller but detectable indirect effects. These findings support our strategy as an interpretable framework for testing structured causal hypotheses in limited-resource biomedical AI. The code and resources for this work are publicly available at: https://github.com/Inamullah-Colab/ReitSEM.
Ullah, Inam
2c299626-b972-46d0-8c15-49c240fb5395
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
12 May 2026
Ullah, Inam
2c299626-b972-46d0-8c15-49c240fb5395
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
Ullah, Inam, Razzak, Imran and Jameel, Shoaib
(2026)
RetiSEM: Generalising Causal Models for Fragmented Biomedical Data.
(doi:10.48550/ARXIV.2606.24488).
Abstract
Learning causal models from fragmented biomedical data is challenging because clinical, molecular, and imaging variables are often incomplete or not jointly observed. We propose RetiSEM, a domain-constrained structural equation modelling (SEM) framework for causal graph recovery and mediation analysis under limited multimodal resources. This proposed work organises variables into biologically informed blocks, applies forbidden-edge constraints, and decomposes pathway-level effects into TE, NDE, and NIE components. We evaluate RetiSEM across ten synthetic benchmark scenarios that vary in dimensionality, nonlinearity, causal depth, and pathway structure, together with a fragmented real-world setting that combines NHANES clinical variables with externally derived retinal representations. This approach achieves lower structural error and higher causal accuracy than unconstrained baselines across the synthetic benchmarks. In the real-data analysis, retinal variables behave mainly as downstream biomarker-like indicators, with smaller but detectable indirect effects. These findings support our strategy as an interpretable framework for testing structured causal hypotheses in limited-resource biomedical AI. The code and resources for this work are publicly available at: https://github.com/Inamullah-Colab/ReitSEM.
This record has no associated files available for download.
More information
Published date: 12 May 2026
Identifiers
Local EPrints ID: 512687
URI: https://eprints.soton.ac.uk/id/eprint/512687
PURE UUID: 1db6c22e-1abc-403d-a194-dab8f08274cc
Catalogue record
Date deposited: 15 Jul 2026 16:48
Last modified: 13 Sep 2026 15:49
Export record
Altmetrics
Contributors
Author:
Inam Ullah
Author:
Imran Razzak
Author:
Shoaib Jameel
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics