Graph representation and learning for drug administration prediction.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	Graph representation and learning for drug administration prediction.
Συγγραφείς:	Cammarasana S; CNR, IMATI, Via de Marini 6, 16149, Genova, Italy. simone.cammarasana@cnr.it., Patanè G; CNR, IMATI, Via de Marini 6, 16149, Genova, Italy.
Πηγή:	BMC medical informatics and decision making [BMC Med Inform Decis Mak] 2026 Jul 08; Vol. 26 (1). Date of Electronic Publication: 2026 Jul 08.
Τύπος έκδοσης:	Journal Article
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: BioMed Central Country of Publication: England NLM ID: 101088682 Publication Model: Electronic Cited Medium: Internet ISSN: 1472-6947 (Electronic) Linking ISSN: 14726947 NLM ISO Abbreviation: BMC Med Inform Decis Mak Subsets: MEDLINE
Imprint Name(s):	Original Publication: London : BioMed Central, [2001-
Ιατρικοί όροι (MeSH):	Pharmaceutical Preparations/administration & dosage , Representation Machine Learning, Humans ; Databases, Factual ; Graph Neural Networks
Περίληψη:	Background: The management of drug administration to patients promotes the customisation and accuracy of the treatments, reducing the risk of ineffective therapies and negative drug effects, and improving drug efficiency and management. Methods: We propose a graph representation learning model for predicting drug administration using the MIMIC-III database, which contains over 53K critical care admissions. We design a heterogeneous, weighted, directed, and multi-feature graph from patient demographics, diagnoses, and drug administration records. Our method uses a graph convolutional network to process node and edge features, predicting edge connections between patients and drugs. This choice enables us to analyse database properties, such as the relationship between drug administration and demographic classes, as well as the prediction accuracy with respect to drug occurrence. Results: We analyse the results in terms of correct, false positive, and false negative edge predictions of drug-patient administration. Our method has an accuracy of [Formula: see text] on the MIMIC-III database, with an F1-score of [Formula: see text]. We discuss the training results regarding convergence and execution time, analyse the accuracy on low-occurrence drugs, and compare our method with previous work. Conclusion: Previous work has focused primarily on query and classification tasks for feature extraction and diagnosis prediction, achieving comparable accuracy but is often limited to specific pathologies (e.g., diabetes), patient groups (e.g., pregnant women), or drug types (e.g., antibiotics). Our approach processes heterogeneous data encompassing various patient characteristics, pathologies, and drug types, providing a more comprehensive and scalable solution. (© 2026. The Author(s).)
Competing Interests:	Declarations. Ethics approval and consent to participate: The proposed work includes no ethically approved human or animal experiments. Consent for publication: Not applicable. Competing interests: The authors have no relevant financial or non-financial interests to disclose.
References:	Nat Commun. 2019 Jul 10;10(1):3045. (PMID: 31292438) Pharmacotherapy. 2001 Sep;21(9):1023-36. (PMID: 11560192) Clin Med (Lond). 2016 Oct;16(5):481-485. (PMID: 27697815) Sci Rep. 2024 Oct 26;14(1):25449. (PMID: 39455647) IEEE J Biomed Health Inform. 2024 Aug;28(8):4544-4552. (PMID: 38190664) Clin Pharmacol Ther. 2020 Jul;108(1):145-154. (PMID: 32141068) Comput Methods Programs Biomed. 2019 Aug;177:141-153. (PMID: 31319942) Biomed Res Int. 2017;2017:2858423. (PMID: 28299322) Cell Genom. 2025 Sep 10;5(9):100950. (PMID: 40675159) IEEE Trans Comput Biol Bioinform. 2025 Nov-Dec;22(6):3557-3563. (PMID: 40956729) Nat Methods. 2021 Nov;18(11):1342-1351. (PMID: 34711970) J Am Med Inform Assoc. 2014 May-Jun;21(3):448-54. (PMID: 24091648) Big Data. 2020 Oct;8(5):379-390. (PMID: 32783631) J Am Med Inform Assoc. 2014 Sep-Oct;21(5):801-7. (PMID: 24384230) JMIR Med Inform. 2020 May 21;8(5):e17645. (PMID: 32436854) Adv Sci (Weinh). 2026 Jan;13(2):e12453. (PMID: 41090528) Comput Biol Med. 2022 Nov;150:105992. (PMID: 36228466) IEEE Trans Med Imaging. 2022 Apr;41(4):757-770. (PMID: 32881682) Am Fam Physician. 2019 Jul 1;100(1):32-38. (PMID: 31259501) IEEE Trans Med Imaging. 2022 Aug;41(8):1990-2003. (PMID: 35192461) J Eval Clin Pract. 2014 Aug;20(4):411-6. (PMID: 24798301) AMIA Annu Symp Proc. 2010 Nov 13;2010:387-91. (PMID: 21347006) J Biomed Semantics. 2012 Apr 24;3 Suppl 1:S5. (PMID: 22541596) J Transl Med. 2020 Dec 7;18(1):462. (PMID: 33287854) BMJ Open. 2017 Oct 16;7(10):e016358. (PMID: 29042378) IEEE J Biomed Health Inform. 2024 Jun;28(6):3709-3720. (PMID: 38512747) J Biomed Inform. 2022 Mar;127:104000. (PMID: 35104644) J Am Med Inform Assoc. 2016 Apr;23(e1):e11-9. (PMID: 26316458) Comput Struct Biotechnol J. 2024 Jul 06;23:2924-2933. (PMID: 39963422) Int J Mach Learn Cybern. 2020;11(12):2849-2856. (PMID: 33727983) Sci Data. 2016 May 24;3:160035. (PMID: 27219127) Bioinformatics. 2018 Jul 1;34(13):i457-i466. (PMID: 29949996) J Biomed Inform. 2018 Oct;86:59-70. (PMID: 30172761) J Biomed Inform. 2015 Feb;53:73-80. (PMID: 25236952) J Am Med Inform Assoc. 2023 Apr 19;30(5):846-858. (PMID: 36794643) Comput Biol Med. 2023 Sep;163:107199. (PMID: 37421738) Brief Bioinform. 2022 Jan 17;23(1):. (PMID: 34891172) Clin Pharmacol Ther. 2013 Jun;93(6):547-55. (PMID: 23571773) Brief Bioinform. 2022 Nov 19;23(6):. (PMID: 36125202) Artif Intell Med. 2018 May;87:49-59. (PMID: 29691122)
Contributed Indexing:	Keywords: Drugs administration; Graph convolutional network; Graph learning; Graph representation; Healthcare; MIMIC-III database
Substance Nomenclature:	0 (Pharmaceutical Preparations)
Entry Date(s):	Date Created: 20260709 Date Completed: 20261002 Latest Revision: 20261005
Update Code:	20261006
PubMed Central ID:	PMC13629112
DOI:	10.1186/s12911-026-03675-y
PMID:	42420993
Βάση Δεδομένων:	MEDLINE

Full Text Finder

Περιγραφή
ISSN:	1472-6947
DOI:	10.1186/s12911-026-03675-y