journal article·2025-01Open access

Precision Adverse Drug Reactions Prediction with Heterogeneous Graph Neural Network

Yang Gao, Xiang Zhang, Zhongquan Sun, Payal Chandak, Jiajun Bu, Haishuai Wang

Advanced Science· Volume 12· Issue 4

Abstract

Abstract Accurate prediction of Adverse Drug Reactions (ADRs) at the patient level is essential for ensuring patient safety and optimizing healthcare outcomes. Traditional machine learning‐based methods primarily focus on predicting potential ADRs for drugs, but they often fall short of capturing the complexity of individual demographics and the variations in ADRs experienced by different people. In this study, a novel framework called Precise Adverse Drug Reaction (PreciseADR) for patient‐level ADR prediction is proposed. The approach effectively integrates relations between patients and ADRs, and harnesses the power of heterogeneous Graph Neural Networks (GNNs) to address the limitations of traditional methods. Specifically, a heterogeneous graph representation of patients is constructed, encompassing nodes that represent patients, diseases, drugs, and ADRs. By leveraging edges in the graph, crucial connections are captured such as a patient being affected by diseases, taking specific drugs, and experiencing ADRs. Next, a GNN‐based model is utilized to learn latent representations of the patient nodes and facilitate the propagation of information throughout the graph structure. By employing patient embeddings that consider their diseases and drugs, potential ADRs can be accurately predicted. The PreciseADR is dedicated to effectively capturing both local and global dependencies within the heterogeneous graph, allowing for the identification of subtle patterns and interactions that play a significant role in ADRs. To evaluate the performance of the approach, extensive experiments are conducted on a large‐scale real‐world healthcare dataset with adverse reports from the FDA Adverse Event Reporting System (FAERS). Experimental results demonstrate that the PreciseADR achieves superior predictive performance in identifying patient‐level ADRs, surpassing the strongest baseline by 3.2% in AUC score and by 4.9% in Hit@10.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Pharmacovigilance and Adverse Drug Reactions · Computational Drug Discovery Methods · Pharmaceutical Practices and Patient Outcomes

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Hepatobiliary and Pancreatic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou 310009 China

College of Computer Science Zhejiang University Hangzhou 310058 China

Department of Computer Science The University of North Carolina at Charlotte Charlotte NC 28223‐0001 USA

Harvard‐MIT Health Sciences and Technology Cambridge MA 02139 USA

Shanghai Artificial Intelligence Laboratory Shanghai 200232 China

Funding

National Key Research and Development Program of China · National Natural Science Foundation of China

References (59)

Show source-provided references
1. 10.1016/j.patter.2020.10010810.1016/j.patter.2020.100108 ↗
2. 10.1038/s41467-020-18305-y10.1038/s41467-020-18305-y ↗
3. 10.1016/j.eclinm.2019.10.00110.1016/j.eclinm.2019.10.001 ↗
4. Duong T. A. · Lancet · 2017 · 4 · 390
5. 10.3389/fddsv.2021.76879210.3389/fddsv.2021.768792 ↗
6. https://www.fda.gov/drugs/drug‐interactions‐labeling/preventable‐adverse‐drug‐reactions‐focus‐drug‐interactions
7. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3853675/
8. 10.1016/j.drudis.2018.01.03910.1016/j.drudis.2018.01.039 ↗
9. 10.1016/j.drudis.2019.07.00610.1016/j.drudis.2019.07.006 ↗
10. 10.3390/diseases903005510.3390/diseases9030055 ↗
11. 10.1038/s43588-021-00138-410.1038/s43588-021-00138-4 ↗
12. 10.1038/s41598-022-06611-y10.1038/s41598-022-06611-y ↗
13. 10.1007/s40264-018-0713-810.1007/s40264-018-0713-8 ↗
14. 10.1109/TCBB.2018.282702910.1109/TCBB.2018.2827029 ↗
15. 10.1016/j.isci.2023.10818310.1016/j.isci.2023.108183 ↗
16. 10.2196/1101610.2196/11016 ↗
17. Qin D. · Adv. Neural Inform. Process. Syst. · 2022 · 35
18. H.Wang L.Chi Z.Zhao Proc. 31st ACM Int. Conf. Inform. Knowl. Manag. ACM New York2022 pp.5004–5008.10.1145/3511808.3557210 ↗
19. 10.1109/TNB.2022.314795710.1109/TNB.2022.3147957 ↗
20. X.Yue Z.Wang J.Huang S.Parthasarathy S.Moosavinasab Y.Huang S. M.Lin W.Zhang P.Zhang H.Sun arXiv preprint arXiv:1906.050172019.
21. 10.2196/2475410.2196/24754 ↗
22. H.Wang Y.Gao X.Zheng P.Zhang H.Chen J.Bu arXiv preprint arXiv:2310.014362023.
23. O. C.Uner R.Gokberk Cinbis O.Tastan A. E.Cicek Biorxiv2019.
24. 10.1016/j.jbi.2022.10409810.1016/j.jbi.2022.104098 ↗
25. 10.1038/s42003-023-05243-w10.1038/s42003-023-05243-w ↗
26. Hu Z. · Proc. Web Conf. · 2020
27. 10.1046/j.1528-1157.43.s.3.5.x10.1046/j.1528-1157.43.s.3.5.x ↗
28. A.Vaswani N.Shazeer N.Parmar J.Uszkoreit L.Jones A. N.Gomez L.Kaiser I.Polosukhin Proc. NeurIPS Curran Associates Inc New York2017.
29. S. Ö.Arik T.Pfister Proc. AAAI Conf. Artif. Intell. Vol.35 2021 pp.6679–6687.10.1609/aaai.v35i8.16826 ↗
30. Y.Cheng R.Hu H.Ying X.Shi J.Wu W.Lin Thirty‐Eighth Proc. AAAI Conf. Artif. Intell 2024 pp.11516–11524.10.1609/aaai.v38i10.29033 ↗
31. T. N.Kipf M.Welling inICLR 2017.
32. P.Velickovic G.Cucurull A.Casanova A.Romero P.Liò Y.Bengio inICLR 2018.
33. W. L.Hamilton Z.Ying J.Leskovec inProc. of NeurIPS 2017.
34. M.Chen Z.Wei Z.Huang B.Ding Y.Li PMLR 2020.
35. D.Bo X.Wang C.Shi H.Shen Proc. AAAI Conf. Artif. Intell. 2021.
36. S.Brody U.Alon E.Yahav inProc. of ICLR. 2022.
37. Bianchi F. M. · IEEE Trans. Pattern Anal. Mach. Intell. · 2022 · 44 · 3496
38. 10.1038/sdata.2014.3210.1038/sdata.2014.32 ↗
39. 10.1038/s41586-023-06139-910.1038/s41586-023-06139-9 ↗
40. 10.1016/j.crmeth.2024.10073310.1016/j.crmeth.2024.100733 ↗
41. Z.Ying D.Bourgeois J.You M.Zitnik J.Leskovec Vol.32 Curran Associates Inc New York2019.
42. L.Wang A.Adiga J.Chen A.Sadilek S.Venkatramanan M.Marathe inProceedings of the AAAI conference on artificial intelligence vol.36 2022 pp.12191–12199.10.1609/aaai.v36i11.21479 ↗
43. S.Chithrananda G.Grand B.Ramsundar arXiv preprint arXiv:2010.098852020.
44. 10.1021/acs.jcim.1c0146710.1021/acs.jcim.1c01467 ↗
45. 10.1093/bib/bbad38510.1093/bib/bbad385 ↗
46. 10.1093/bioinformatics/bty29410.1093/bioinformatics/bty294 ↗
47. X.Qin T.Kakar S.Wunnava E. A.Rundensteiner L.Cao inProc. of KDD Halifax NS Canada2017.
48. Zhu J. · Exp. Syst. Appl. · 2023 · 215 · 17
49. Bate A. · Drug Saf. · 2002
50. 10.1016/j.drudis.2008.12.01210.1016/j.drudis.2008.12.012 ↗
51. Hochberg A. · Clin. Pharmacol. Toxicol. · 2009 · 85 · 600
52. I.Karlsson J.Zhao L.Asker H.Boström inConference on Artificial Intelligence in Medicine in Europe 2013.
53. 10.1136/amiajnl-2012-00111910.1136/amiajnl-2012-001119 ↗
54. 10.1002/pds.213910.1002/pds.2139 ↗
55. Yoon D. · Clin. Pharmacol. Toxicol. · 2012 · 91 · 467
56. https://fis.fda.gov/extensions/FPD‐QDE‐FAERS/FPD‐QDE‐FAERS.html
57. T.‐Y.Lin P.Goyal R.Girshick K.He P.Dollár 2017 IEEE International Conference on Computer Vision (ICCV) IEEE Venice Italy2017.
58. A.Oord Y.Li O.Vinyals arXiv preprint arXiv:1807.037482018.
59. M.Schlichtkrull T.Kipf P.Bloem R. V.Berg I.Titov M.Welling arXiv:1703.061032018.