MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare
Predicting a patient's future health condition by analyzing their Electronic Health Records (EHRs) is a trending subject in the intelligent medical field, which can help clinicians prescribe safely and effectively, and also make more accurate diagnoses. Benefiting from powerful feature extracti...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171200 |
| _version_ | 1811682625955299328 |
|---|---|
| author | Wu, Jialun He, Kai Mao, Rui Li, Chen Cambria, Erik |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Wu, Jialun He, Kai Mao, Rui Li, Chen Cambria, Erik |
| author_sort | Wu, Jialun |
| collection | NTU |
| description | Predicting a patient's future health condition by analyzing their Electronic Health Records (EHRs) is a trending subject in the intelligent medical field, which can help clinicians prescribe safely and effectively, and also make more accurate diagnoses. Benefiting from powerful feature extraction capabilities, graph representation learning can capture complex relationships and achieve promising performance in many clinical prediction tasks. However, existing works either exclusively consider single domain knowledge with an independent task or do not fully capitalize on domain knowledge that can provide more predictive signals in the code encoding stage. Moreover, the heterogeneous and high-dimensional nature of EHR data leads to a deficiency of hardly encoding implicit high-order correlations. To address these limitations, we proposed a knowledge-guided Multi-viEw hyperGrAph predictive framework (MEGACare) for diagnosis prediction and medication recommendation. Our MEGACare leveraged multi-faceted medical knowledge, including ontology structure, code description, and molecular information to enhance medical code presentations. Furthermore, we constructed an EHR hypergraph and a multi-view learning framework to capture the high-order correlation between patient visits and medical codes. Specifically, we propose three perspectives around the pairwise relationship between patient visits and medical codes to comprehensively learn patient representation and enhance the robustness of our framework. We evaluated our MEGACare framework against a set of state-of-the-art methods for two clinical outcome prediction tasks in the public MIMIC-III dataset, and the results showed that our proposed framework was superior to the baseline methods. |
| first_indexed | 2024-10-01T03:59:49Z |
| format | Journal Article |
| id | ntu-10356/171200 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:59:49Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1712002023-10-17T04:57:48Z MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare Wu, Jialun He, Kai Mao, Rui Li, Chen Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Electronic Health Record Healthcare Predicting a patient's future health condition by analyzing their Electronic Health Records (EHRs) is a trending subject in the intelligent medical field, which can help clinicians prescribe safely and effectively, and also make more accurate diagnoses. Benefiting from powerful feature extraction capabilities, graph representation learning can capture complex relationships and achieve promising performance in many clinical prediction tasks. However, existing works either exclusively consider single domain knowledge with an independent task or do not fully capitalize on domain knowledge that can provide more predictive signals in the code encoding stage. Moreover, the heterogeneous and high-dimensional nature of EHR data leads to a deficiency of hardly encoding implicit high-order correlations. To address these limitations, we proposed a knowledge-guided Multi-viEw hyperGrAph predictive framework (MEGACare) for diagnosis prediction and medication recommendation. Our MEGACare leveraged multi-faceted medical knowledge, including ontology structure, code description, and molecular information to enhance medical code presentations. Furthermore, we constructed an EHR hypergraph and a multi-view learning framework to capture the high-order correlation between patient visits and medical codes. Specifically, we propose three perspectives around the pairwise relationship between patient visits and medical codes to comprehensively learn patient representation and enhance the robustness of our framework. We evaluated our MEGACare framework against a set of state-of-the-art methods for two clinical outcome prediction tasks in the public MIMIC-III dataset, and the results showed that our proposed framework was superior to the baseline methods. Agency for Science, Technology and Research (A*STAR) National Research Foundation (NRF) This work has been supported by the Innovative Research Group of the National Natural Science Foundation of China (61721002); The National Natural Science Foundation of China under Grant (62106191); The Key Research and Development Program of Ningxia Hui Nationality Autonomous Region (2022BEG02025); The Key Research and Development Program of Shaanxi Province (2021GXLH-Z-095); The National Research Foundation Singapore under AI Singapore Programme (Award Number: AISG-GC-2019-001-2A and AISG2-TC-2022-004); The RIE2025 Industry Alignment Fund (I2101E0002 – Cisco-NUS Accelerated Digital Economy Corporate Laboratory). 2023-10-17T04:57:48Z 2023-10-17T04:57:48Z 2023 Journal Article Wu, J., He, K., Mao, R., Li, C. & Cambria, E. (2023). MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare. Information Fusion, 100, 101939-. https://dx.doi.org/10.1016/j.inffus.2023.101939 1566-2535 https://hdl.handle.net/10356/171200 10.1016/j.inffus.2023.101939 2-s2.0-85166338703 100 101939 en AISG-GC-2019-001-2A AISG2-TC-2022-004 I2101E0002 Information Fusion © 2023 Elsevier B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Electronic Health Record Healthcare Wu, Jialun He, Kai Mao, Rui Li, Chen Cambria, Erik MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare |
| title | MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare |
| title_full | MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare |
| title_fullStr | MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare |
| title_full_unstemmed | MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare |
| title_short | MEGACare: knowledge-guided multi-view hypergraph predictive framework for healthcare |
| title_sort | megacare knowledge guided multi view hypergraph predictive framework for healthcare |
| topic | Engineering::Computer science and engineering Electronic Health Record Healthcare |
| url | https://hdl.handle.net/10356/171200 |
| work_keys_str_mv | AT wujialun megacareknowledgeguidedmultiviewhypergraphpredictiveframeworkforhealthcare AT hekai megacareknowledgeguidedmultiviewhypergraphpredictiveframeworkforhealthcare AT maorui megacareknowledgeguidedmultiviewhypergraphpredictiveframeworkforhealthcare AT lichen megacareknowledgeguidedmultiviewhypergraphpredictiveframeworkforhealthcare AT cambriaerik megacareknowledgeguidedmultiviewhypergraphpredictiveframeworkforhealthcare |