Back

Counterfactual Explanations for Graph Neural Networks in Patient Outcome Prediction

Chaidos, N.; Dimitriou, A.; Calzi, H.; Casiraghi, E.; Stamou, G.; Valentini, G.

2026-05-20 bioinformatics
10.64898/2026.05.18.725906 bioRxiv
Show abstract

Counterfactual Explanation (CE) algorithms have been successfully applied to uncover the main factors driving computational diagnostic and prognostic predictions on tabular medical data. Recently, a new Network Medicine paradigm has been introduced for patient diagnosis and prognosis using Patient Similarity Networks (PSNs), i.e. graphs where patients are represented as nodes and their clinical and biomolecular similarities as edges. In this context, graph-based algorithms, including Graph Neural Networks (GNNs), can provide predictions using not only individual patient features but also their relations within a network of clinically and biomolecularly similar individuals. In this work, we propose the first CE algorithm tailored to explain diagnostic and prognostic predictions within PSNs. Alongside a contrastive GNN backbone, we introduce a versatile, model-agnostic counterfactual search method compatible with any underlying classifier. Preliminary results on synthetic data and on a cohort of patients affected by the Alzheimers disease show that our algorithm is competitive both with seminal tabular based CE algorithms and GNNExplainer, a well-established method for explaining graph-based classification tasks.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

1
Bioinformatics
1061 papers in training set
Top 2%
14.8%
2
Scientific Reports
3102 papers in training set
Top 8%
9.2%
3
PLOS Computational Biology
1633 papers in training set
Top 8%
4.4%
4
Advanced Science
249 papers in training set
Top 4%
4.3%
5
Nature Communications
4913 papers in training set
Top 37%
4.0%
6
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 18%
4.0%
7
PLOS ONE
4510 papers in training set
Top 38%
3.6%
8
Bioinformatics Advances
184 papers in training set
Top 1%
3.6%
9
Medical Image Analysis
33 papers in training set
Top 0.4%
2.9%
50% of probability mass above
10
Computational and Structural Biotechnology Journal
216 papers in training set
Top 3%
2.4%
11
IEEE Journal of Biomedical and Health Informatics
34 papers in training set
Top 0.8%
2.1%
12
BMC Bioinformatics
383 papers in training set
Top 4%
2.1%
13
npj Digital Medicine
97 papers in training set
Top 2%
1.9%
14
European Journal of Human Genetics
49 papers in training set
Top 0.5%
1.9%
15
Frontiers in Genetics
197 papers in training set
Top 5%
1.7%
16
Briefings in Bioinformatics
326 papers in training set
Top 4%
1.7%
17
Patterns
70 papers in training set
Top 0.9%
1.7%
18
IEEE Transactions on Computational Biology and Bioinformatics
17 papers in training set
Top 0.2%
1.7%
19
Communications Biology
886 papers in training set
Top 11%
1.5%
20
Computers in Biology and Medicine
120 papers in training set
Top 3%
1.3%
21
IEEE Access
31 papers in training set
Top 0.5%
1.3%
22
npj Systems Biology and Applications
99 papers in training set
Top 1%
1.3%
23
Nature Machine Intelligence
61 papers in training set
Top 3%
1.2%
24
eLife
5422 papers in training set
Top 49%
1.2%
25
Artificial Intelligence in the Life Sciences
11 papers in training set
Top 0.1%
1.2%
26
Nature Medicine
117 papers in training set
Top 4%
0.9%
27
iScience
1063 papers in training set
Top 26%
0.9%
28
Nucleic Acids Research
1128 papers in training set
Top 17%
0.8%
29
NAR Genomics and Bioinformatics
214 papers in training set
Top 4%
0.8%
30
Cell Systems
167 papers in training set
Top 14%
0.6%