Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity
Predicting the risk of mortality of hospitalized patients in the ICU is essential for timely identification of high-risk patients and formulate and adjustment of treatment strategies when patients are hospitalized. Traditional machine learning methods usually ignore the similarity between patients a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-07-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023685?viewType=HTML |
| _version_ | 1797739778868772864 |
|---|---|
| author | Manfu Ma Penghui Sun Yong Li Weilong Huo |
| author_facet | Manfu Ma Penghui Sun Yong Li Weilong Huo |
| author_sort | Manfu Ma |
| collection | DOAJ |
| description | Predicting the risk of mortality of hospitalized patients in the ICU is essential for timely identification of high-risk patients and formulate and adjustment of treatment strategies when patients are hospitalized. Traditional machine learning methods usually ignore the similarity between patients and make it difficult to uncover the hidden relationships between patients, resulting in poor accuracy of prediction models. In this paper, we propose a new model named PS-DGAT to solve the above problem. First, we construct a patient-weighted similarity network by calculating the similarity of patient clinical data to represent the similarity relationship between patients; second, we fill in the missing features and reconstruct the patient similarity network based on the data of neighboring patients in the network; finally, from the reconstructed patient similarity network after feature completion, we use the dynamic attention mechanism to extract and learn the structural features of the nodes to obtain a vector representation of each patient node in the low-dimensional embedding The vector representation of each patient node in the low-dimensional embedding space is used to achieve patient mortality risk prediction. The experimental results show that the accuracy is improved by about 1.8% compared with the basic GAT and about 8% compared with the traditional machine learning methods. |
| first_indexed | 2024-03-12T14:03:05Z |
| format | Article |
| id | doaj.art-bd1d6d2f0421488db8cbe860ecad5579 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-03-12T14:03:05Z |
| publishDate | 2023-07-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-bd1d6d2f0421488db8cbe860ecad55792023-08-22T01:22:35ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-07-01208153261534410.3934/mbe.2023685Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarityManfu Ma 0Penghui Sun1Yong Li2Weilong Huo 31. College of Computer Science and Engineering, Northwest Normal University, 967 Anning East Road, Lanzhou 730070, China1. College of Computer Science and Engineering, Northwest Normal University, 967 Anning East Road, Lanzhou 730070, China1. College of Computer Science and Engineering, Northwest Normal University, 967 Anning East Road, Lanzhou 730070, China2. College of Traffic and Transportation, Lanzhou Jiaotong University, 88 Anning West Road, Lanzhou 730070, ChinaPredicting the risk of mortality of hospitalized patients in the ICU is essential for timely identification of high-risk patients and formulate and adjustment of treatment strategies when patients are hospitalized. Traditional machine learning methods usually ignore the similarity between patients and make it difficult to uncover the hidden relationships between patients, resulting in poor accuracy of prediction models. In this paper, we propose a new model named PS-DGAT to solve the above problem. First, we construct a patient-weighted similarity network by calculating the similarity of patient clinical data to represent the similarity relationship between patients; second, we fill in the missing features and reconstruct the patient similarity network based on the data of neighboring patients in the network; finally, from the reconstructed patient similarity network after feature completion, we use the dynamic attention mechanism to extract and learn the structural features of the nodes to obtain a vector representation of each patient node in the low-dimensional embedding The vector representation of each patient node in the low-dimensional embedding space is used to achieve patient mortality risk prediction. The experimental results show that the accuracy is improved by about 1.8% compared with the basic GAT and about 8% compared with the traditional machine learning methods.https://www.aimspress.com/article/doi/10.3934/mbe.2023685?viewType=HTMLpatient similarity networkgraph neural networkmissing value fillingmortality risk prediction |
| spellingShingle | Manfu Ma Penghui Sun Yong Li Weilong Huo Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity Mathematical Biosciences and Engineering patient similarity network graph neural network missing value filling mortality risk prediction |
| title | Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity |
| title_full | Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity |
| title_fullStr | Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity |
| title_full_unstemmed | Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity |
| title_short | Predicting the risk of mortality in ICU patients based on dynamic graph attention network of patient similarity |
| title_sort | predicting the risk of mortality in icu patients based on dynamic graph attention network of patient similarity |
| topic | patient similarity network graph neural network missing value filling mortality risk prediction |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023685?viewType=HTML |
| work_keys_str_mv | AT manfuma predictingtheriskofmortalityinicupatientsbasedondynamicgraphattentionnetworkofpatientsimilarity AT penghuisun predictingtheriskofmortalityinicupatientsbasedondynamicgraphattentionnetworkofpatientsimilarity AT yongli predictingtheriskofmortalityinicupatientsbasedondynamicgraphattentionnetworkofpatientsimilarity AT weilonghuo predictingtheriskofmortalityinicupatientsbasedondynamicgraphattentionnetworkofpatientsimilarity |