Stratifying heart failure patients with graph neural network and transformer using Electronic Health Records to optimize drug response prediction.

Autor:	Chowdhury S; Department of Artificial Intelligence and Informatics Research, Mayo Clinic, Rochester, MN 55902, United States., Chen Y; Department of Biochemistry and Molecular Biology, Mayo Clinic, Rochester, MN 55902, United States., Li P; Division of Cardiology, Pauley Heart Center, Virginia Commonwealth University, Richmond, VA 23219, United States., Rajaganapathy S; Department of Artificial Intelligence and Informatics Research, Mayo Clinic, Rochester, MN 55902, United States., Wen A; McWilliams School of Biomedical Informatics, University of Texas Health Science Center, Houston, TX 77030, United States., Ma X; Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55902, United States., Dai Q; Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55902, United States., Yu Y; Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55902, United States., Fu S; McWilliams School of Biomedical Informatics, University of Texas Health Science Center, Houston, TX 77030, United States., Jiang X; McWilliams School of Biomedical Informatics, University of Texas Health Science Center, Houston, TX 77030, United States., He Z; School of Information, Florida State University, Tallahassee, FL 32306, United States., Sohn S; Department of Artificial Intelligence and Informatics Research, Mayo Clinic, Rochester, MN 55902, United States., Liu X; Department of Cardiovascular Medicine, Mayo Clinic, La Crosse, WI 54601, United States., Bielinski SJ; Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55902, United States., Chamberlain AM; Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN 55902, United States.; Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55902, United States., Cerhan JR; Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55902, United States., Zong N; Department of Artificial Intelligence and Informatics Research, Mayo Clinic, Rochester, MN 55902, United States.
Jazyk:	angličtina
Zdroj:	Journal of the American Medical Informatics Association : JAMIA [J Am Med Inform Assoc] 2024 Aug 01; Vol. 31 (8), pp. 1671-1681.
DOI:	10.1093/jamia/ocae137
Abstrakt:	Objectives: Heart failure (HF) impacts millions of patients worldwide, yet the variability in treatment responses remains a major challenge for healthcare professionals. The current treatment strategies, largely derived from population based evidence, often fail to consider the unique characteristics of individual patients, resulting in suboptimal outcomes. This study aims to develop computational models that are patient-specific in predicting treatment outcomes, by utilizing a large Electronic Health Records (EHR) database. The goal is to improve drug response predictions by identifying specific HF patient subgroups that are likely to benefit from existing HF medications. Materials and Methods: A novel, graph-based model capable of predicting treatment responses, combining Graph Neural Network and Transformer was developed. This method differs from conventional approaches by transforming a patient's EHR data into a graph structure. By defining patient subgroups based on this representation via K-Means Clustering, we were able to enhance the performance of drug response predictions. Results: Leveraging EHR data from 11 627 Mayo Clinic HF patients, our model significantly outperformed traditional models in predicting drug response using NT-proBNP as a HF biomarker across five medication categories (best RMSE of 0.0043). Four distinct patient subgroups were identified with differential characteristics and outcomes, demonstrating superior predictive capabilities over existing HF subtypes (best mean RMSE of 0.0032). Discussion: These results highlight the power of graph-based modeling of EHR in improving HF treatment strategies. The stratification of patients sheds light on particular patient segments that could benefit more significantly from tailored response predictions. Conclusions: Longitudinal EHR data have the potential to enhance personalized prognostic predictions through the application of graph-based AI techniques. (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu