Intra-person multi-task learning method for chronic-disease prediction
Abstract In the medical field, various clinical information has been accumulated to help clinicians provide personalized medicine and make better diagnoses. As chronic diseases share similar characteristics, it is possible to predict multiple chronic diseases using the accumulated data of each patie...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-28383-9 |
| _version_ | 1797945941307686912 |
|---|---|
| author | Gihyeon Kim Heeryung Lim Yunsoo Kim Oran Kwon Jang-Hwan Choi |
| author_facet | Gihyeon Kim Heeryung Lim Yunsoo Kim Oran Kwon Jang-Hwan Choi |
| author_sort | Gihyeon Kim |
| collection | DOAJ |
| description | Abstract In the medical field, various clinical information has been accumulated to help clinicians provide personalized medicine and make better diagnoses. As chronic diseases share similar characteristics, it is possible to predict multiple chronic diseases using the accumulated data of each patient. Thus, we propose an intra-person multi-task learning framework that jointly predicts the status of correlated chronic diseases and improves the model performance. Because chronic diseases occur over a long period and are affected by various factors, we considered features related to each chronic disease and the temporal relationship of the time-series data for accurate prediction. The study was carried out in three stages: (1) data preprocessing and feature selection using bidirectional recurrent imputation for time series (BRITS) and the least absolute shrinkage and selection operator (LASSO); (2) a convolutional neural network and long short-term memory (CNN-LSTM) for single-task models; and (3) a novel intra-person multi-task learning CNN-LSTM framework developed to predict multiple chronic diseases simultaneously. Our multi-task learning method between correlated chronic diseases produced a more stable and accurate system than single-task models and other baseline recurrent networks. Furthermore, the proposed model was tested using different time steps to illustrate its flexibility and generalization across multiple time steps. |
| first_indexed | 2024-04-10T21:03:00Z |
| format | Article |
| id | doaj.art-48aaca0f1a654631af1ea7421299a6ba |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-10T21:03:00Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-48aaca0f1a654631af1ea7421299a6ba2023-01-22T12:11:00ZengNature PortfolioScientific Reports2045-23222023-01-0113111010.1038/s41598-023-28383-9Intra-person multi-task learning method for chronic-disease predictionGihyeon Kim0Heeryung Lim1Yunsoo Kim2Oran Kwon3Jang-Hwan Choi4Department of Computational Medicine, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityDivision of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityDepartment of Nutritional Science and Food Management, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityDepartment of Nutritional Science and Food Management, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityDivision of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans UniversityAbstract In the medical field, various clinical information has been accumulated to help clinicians provide personalized medicine and make better diagnoses. As chronic diseases share similar characteristics, it is possible to predict multiple chronic diseases using the accumulated data of each patient. Thus, we propose an intra-person multi-task learning framework that jointly predicts the status of correlated chronic diseases and improves the model performance. Because chronic diseases occur over a long period and are affected by various factors, we considered features related to each chronic disease and the temporal relationship of the time-series data for accurate prediction. The study was carried out in three stages: (1) data preprocessing and feature selection using bidirectional recurrent imputation for time series (BRITS) and the least absolute shrinkage and selection operator (LASSO); (2) a convolutional neural network and long short-term memory (CNN-LSTM) for single-task models; and (3) a novel intra-person multi-task learning CNN-LSTM framework developed to predict multiple chronic diseases simultaneously. Our multi-task learning method between correlated chronic diseases produced a more stable and accurate system than single-task models and other baseline recurrent networks. Furthermore, the proposed model was tested using different time steps to illustrate its flexibility and generalization across multiple time steps.https://doi.org/10.1038/s41598-023-28383-9 |
| spellingShingle | Gihyeon Kim Heeryung Lim Yunsoo Kim Oran Kwon Jang-Hwan Choi Intra-person multi-task learning method for chronic-disease prediction Scientific Reports |
| title | Intra-person multi-task learning method for chronic-disease prediction |
| title_full | Intra-person multi-task learning method for chronic-disease prediction |
| title_fullStr | Intra-person multi-task learning method for chronic-disease prediction |
| title_full_unstemmed | Intra-person multi-task learning method for chronic-disease prediction |
| title_short | Intra-person multi-task learning method for chronic-disease prediction |
| title_sort | intra person multi task learning method for chronic disease prediction |
| url | https://doi.org/10.1038/s41598-023-28383-9 |
| work_keys_str_mv | AT gihyeonkim intrapersonmultitasklearningmethodforchronicdiseaseprediction AT heeryunglim intrapersonmultitasklearningmethodforchronicdiseaseprediction AT yunsookim intrapersonmultitasklearningmethodforchronicdiseaseprediction AT orankwon intrapersonmultitasklearningmethodforchronicdiseaseprediction AT janghwanchoi intrapersonmultitasklearningmethodforchronicdiseaseprediction |