Interpretable graph-based models on multimodal biomedical data integration: a technical review and benchmarking
Alireza Sadeghi, Farshid Hajati, Ahmadreza Argha, Nigel H Lovell, Min Yang, Hamid Alinejad-Rokny · 2026
Read Interpretable graph-based models on multimodal biomedical data integration: a technical review and benchmarking by Alireza Sadeghi, Farshid Hajati, Ahmadreza Argha, Nigel H Lovell, Min Yang, Hamid Alinejad-Rokny (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13280480.txt.
Description
Alireza Sadeghi and team give a 2026 technical review of interpretable graph based models on multimodal biomedical data. Joining diverse data types is key for robust health insights. Graph models can capture complex relational structures, yet clinic uptake hinges on interpretability, or clear reasons for model calls. The review surveys such models and notes the dominant trends in the field.
Trends hold disease classification, static graph construction and post hoc explainability, or reasons given after a call. The team categorize explainable AI techniques for this work. Four methods, SHAP, saliency, sensitivity and graph masking, were benchmarked on Alzheimer disease data. Each showed strengths that complement the rest. A development flowchart and future paths close the work: dynamic graphs, knowledge integration and LLM based explainability. Trust in AI needs such maps before clinic use.
Catalog record
| CREATOR | Alireza Sadeghi, Farshid Hajati, Ahmadreza Argha, Nigel H Lovell, Min Yang, Hamid Alinejad-Rokny |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60989 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |