Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation
Early detection of mortality in intensive care units (ICUs) is significant to improve patient survival. Since heterogeneous data can be collected from the intensive care unit, there are meaningful static features (e.g., ICU type, gender, and ethnicity) that can enhance the performance of early detec...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9852224/ |
| _version_ | 1798037121062141952 |
|---|---|
| author | Yunseob Shin Yunwon Tae Yeha Lee |
| author_facet | Yunseob Shin Yunwon Tae Yeha Lee |
| author_sort | Yunseob Shin |
| collection | DOAJ |
| description | Early detection of mortality in intensive care units (ICUs) is significant to improve patient survival. Since heterogeneous data can be collected from the intensive care unit, there are meaningful static features (e.g., ICU type, gender, and ethnicity) that can enhance the performance of early detection of mortality. Although the characteristics of physiological representation for each patient can be different by static features, recently proposed mortality prediction models overlook these features and only rely on a one-size-fits-all model. In this paper, we propose a simple yet effective domain encoder named G-DAM (Graph-Domain Aggregation Module) that relies on a relational graph between each static feature to adapt to patient groups and capture the relationship. We show the importance of utilizing static features to predict ICU mortality through extensive experimental results. The experimental results demonstrate that our proposed G-DAM outperforms existing baseline methods not only in the major domains with dense populations but also in the minor domains with sparse populations. The ablative study also shows different sequential models can perform better combined with G-DAM. |
| first_indexed | 2024-04-11T21:22:16Z |
| format | Article |
| id | doaj.art-72b0d83f11dc48e88c11377bd22b0a37 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T21:22:16Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-72b0d83f11dc48e88c11377bd22b0a372022-12-22T04:02:34ZengIEEEIEEE Access2169-35362022-01-0110844058441610.1109/ACCESS.2022.31972979852224Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain AggregationYunseob Shin0https://orcid.org/0000-0002-1955-1908Yunwon Tae1https://orcid.org/0000-0002-3845-592XYeha Lee2Vuno Inc., Seoul, South KoreaVuno Inc., Seoul, South KoreaVuno Inc., Seoul, South KoreaEarly detection of mortality in intensive care units (ICUs) is significant to improve patient survival. Since heterogeneous data can be collected from the intensive care unit, there are meaningful static features (e.g., ICU type, gender, and ethnicity) that can enhance the performance of early detection of mortality. Although the characteristics of physiological representation for each patient can be different by static features, recently proposed mortality prediction models overlook these features and only rely on a one-size-fits-all model. In this paper, we propose a simple yet effective domain encoder named G-DAM (Graph-Domain Aggregation Module) that relies on a relational graph between each static feature to adapt to patient groups and capture the relationship. We show the importance of utilizing static features to predict ICU mortality through extensive experimental results. The experimental results demonstrate that our proposed G-DAM outperforms existing baseline methods not only in the major domains with dense populations but also in the minor domains with sparse populations. The ablative study also shows different sequential models can perform better combined with G-DAM.https://ieeexplore.ieee.org/document/9852224/Mortality predictionclinical predictionmachine learningclassificationelectronic health recordsrelational graph |
| spellingShingle | Yunseob Shin Yunwon Tae Yeha Lee Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation IEEE Access Mortality prediction clinical prediction machine learning classification electronic health records relational graph |
| title | Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation |
| title_full | Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation |
| title_fullStr | Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation |
| title_full_unstemmed | Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation |
| title_short | Improving Mortality Prediction in ICU by Learning Long-Tailed Population of Patients Through Graph-Domain Aggregation |
| title_sort | improving mortality prediction in icu by learning long tailed population of patients through graph domain aggregation |
| topic | Mortality prediction clinical prediction machine learning classification electronic health records relational graph |
| url | https://ieeexplore.ieee.org/document/9852224/ |
| work_keys_str_mv | AT yunseobshin improvingmortalitypredictioninicubylearninglongtailedpopulationofpatientsthroughgraphdomainaggregation AT yunwontae improvingmortalitypredictioninicubylearninglongtailedpopulationofpatientsthroughgraphdomainaggregation AT yehalee improvingmortalitypredictioninicubylearninglongtailedpopulationofpatientsthroughgraphdomainaggregation |