STM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient Networks

Geissbuhler, Damien; Bornet, Alban; Marques, Catarina; Anjos, André; Pereira, Sónia; Teodoro, Douglas

Publication

STM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient Networks

2025-06Book part

datacite.subject.fos	Ciências Médicas::Ciências da Saúde
datacite.subject.sdg	03:Saúde de Qualidade
datacite.subject.sdg	04:Educação de Qualidade
datacite.subject.sdg	17:Parcerias para a Implementação dos Objetivos
dc.contributor.author	Geissbuhler, Damien
dc.contributor.author	Bornet, Alban
dc.contributor.author	Marques, Catarina
dc.contributor.author	Anjos, André
dc.contributor.author	Pereira, Sónia
dc.contributor.author	Teodoro, Douglas
dc.date.accessioned	2025-10-06T09:38:54Z
dc.date.available	2025-10-06T09:38:54Z
dc.date.embargo	2026-10-01
dc.date.issued	2025-06
dc.date.updated	2025-10-04T23:05:30Z
dc.description	Book Series Part of the book series: Lecture Notes in Computer Science (LNAI,volume 15734)
dc.description.abstract	Hospital-acquired infections (HAIs), particularly those caused by multidrug-resistant (MDR) bacteria, pose significant risks to vulnerable patients. Accurate predictive models are important for assessing infection dynamics and informing infection prediction and control (IPC) programmes. Graph-based methods, including graph neural networks (GNNs), offer a powerful approach to model complex relationships between patients and environments but often struggle with data sparsity, irregularity, and heterogeneity. We propose the space-time-and-memory (STM)-GNN, a temporal GNN enhanced with recurrent connectivity designed to capture spatiotemporal infection dynamics. STM-GNN effectively integrates sparse, heterogeneous data combining network information from patient-environment interactions and internal memory from historical colonization and contact patterns. Using a unique IPC dataset containing clinical and environmental colonization information collected from a long-term healthcare unit, we show that STM-GNN effectively addresses the challenges of limited and irregular data in an MDR prediction task. Our model reaches 0.84 AUROC, and achieves the most balanced performance overall compared to classic machine learning algorithms, as well as temporal GNN approaches.	eng
dc.description.sponsorship
dc.description.version	info:eu-repo/semantics/accepdedVersion
dc.identifier.citation	Geissbuhler, D., Bornet, A., Marques, C., Anjos, A., Pereira, S., Teodoro, D. (2025). STM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient Networks. In: Bellazzi, R., Juarez Herrero, J.M., Sacchi, L., Zupan, B. (eds) Artificial Intelligence in Medicine. AIME 2025. Lecture Notes in Computer Science(), vol 15734. Springer, Cham. https://doi.org/10.1007/978-3-031-95838-0_16
dc.identifier.doi	10.1007/978-3-031-95838-0_16	en_US
dc.identifier.isbn	9783031958373	en_US
dc.identifier.isbn	9783031958380	en_US
dc.identifier.issn	0302-9743	en_US
dc.identifier.issn	1611-3349	en_US
dc.identifier.slug	cv-prod-4535280
dc.identifier.uri	http://hdl.handle.net/10400.8/14203
dc.language.iso	eng
dc.peerreviewed	no
dc.publisher	Springer Nature
dc.rights.uri	https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject	Hospital acquired infection
dc.subject	Temporal graph neural network
dc.title	STM-GNN: Space-Time-and-Memory Graph Neural Networks for Predicting Multi-Drug Resistance Risks in Dynamic Patient Networks	eng
dc.type	book part	en_US
dspace.entity.type	Publication
oaire.citation.endPage	169
oaire.citation.startPage	160
oaire.citation.title	Artificial Intelligence in Medicine	en_US
oaire.citation.volume	15734 LNAI
oaire.version	http://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyName	Gonçalves Pereira
person.givenName	Sónia
person.identifier	461252
person.identifier.ciencia-id	EB1F-4DB2-B0C9
person.identifier.orcid	0000-0001-8197-1850
person.identifier.rid	M-7588-2017
person.identifier.scopus-author-id	7202024712
rcaap.cv.cienciaid	8615-92D1-7858 \| Sónia Gonçalves Pereira
rcaap.rights	embargoedAccess	en_US
relation.isAuthorOfPublication	259ad2cc-f9ff-4c33-ad6d-10f5b3ff341a
relation.isAuthorOfPublication.latestForDiscovery	259ad2cc-f9ff-4c33-ad6d-10f5b3ff341a