Hospitalization Patient Forecasting Based on Multi–Task Deep Learning
Forecasting the number of hospitalization patients is important for hospital management. The number of hospitalization patients depends on three types of patients, namely admission patients, discharged patients, and inpatients. However, previous works focused on one type of patients rather than the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2023-03-01
|
| Series: | International Journal of Applied Mathematics and Computer Science |
| Subjects: | |
| Online Access: | https://doi.org/10.34768/amcs-2023-0012 |
| _version_ | 1827968822431186944 |
|---|---|
| author | Zhou Min Huang Xiaoxiao Liu Haipeng Zheng Dingchang |
| author_facet | Zhou Min Huang Xiaoxiao Liu Haipeng Zheng Dingchang |
| author_sort | Zhou Min |
| collection | DOAJ |
| description | Forecasting the number of hospitalization patients is important for hospital management. The number of hospitalization patients depends on three types of patients, namely admission patients, discharged patients, and inpatients. However, previous works focused on one type of patients rather than the three types of patients together. In this paper, we propose a multi-task forecasting model to forecast the three types of patients simultaneously. We integrate three neural network modules into a unified model for forecasting. Besides, we extract date features of admission and discharged patient flows to improve forecasting accuracy. The algorithm is trained and evaluated on a real-world data set of a one-year daily observation of patient numbers in a hospital. We compare the performance of our model with eight baselines over two real-word data sets. The experimental results show that our approach outperforms other baseline algorithms significantly. |
| first_indexed | 2024-04-09T18:28:38Z |
| format | Article |
| id | doaj.art-56da901aea9443d0a616fa3404756008 |
| institution | Directory Open Access Journal |
| issn | 2083-8492 |
| language | English |
| last_indexed | 2024-04-09T18:28:38Z |
| publishDate | 2023-03-01 |
| publisher | Sciendo |
| record_format | Article |
| series | International Journal of Applied Mathematics and Computer Science |
| spelling | doaj.art-56da901aea9443d0a616fa34047560082023-04-11T17:28:19ZengSciendoInternational Journal of Applied Mathematics and Computer Science2083-84922023-03-0133115116210.34768/amcs-2023-0012Hospitalization Patient Forecasting Based on Multi–Task Deep LearningZhou Min0Huang Xiaoxiao1Liu Haipeng2Zheng Dingchang31The First Affiliated Hospital, Zhejiang University School of Medicine, No.79 Qingchun Rd., 310003, Hangzhou, China1The First Affiliated Hospital, Zhejiang University School of Medicine, No.79 Qingchun Rd., 310003, Hangzhou, China2Research Centre for Intelligent Healthcare, Coventry University, Priory Street, CV1 5FB, Coventry, UK2Research Centre for Intelligent Healthcare, Coventry University, Priory Street, CV1 5FB, Coventry, UKForecasting the number of hospitalization patients is important for hospital management. The number of hospitalization patients depends on three types of patients, namely admission patients, discharged patients, and inpatients. However, previous works focused on one type of patients rather than the three types of patients together. In this paper, we propose a multi-task forecasting model to forecast the three types of patients simultaneously. We integrate three neural network modules into a unified model for forecasting. Besides, we extract date features of admission and discharged patient flows to improve forecasting accuracy. The algorithm is trained and evaluated on a real-world data set of a one-year daily observation of patient numbers in a hospital. We compare the performance of our model with eight baselines over two real-word data sets. The experimental results show that our approach outperforms other baseline algorithms significantly.https://doi.org/10.34768/amcs-2023-0012hospitalization patientsforecastingneural networkmultitask learning |
| spellingShingle | Zhou Min Huang Xiaoxiao Liu Haipeng Zheng Dingchang Hospitalization Patient Forecasting Based on Multi–Task Deep Learning International Journal of Applied Mathematics and Computer Science hospitalization patients forecasting neural network multitask learning |
| title | Hospitalization Patient Forecasting Based on Multi–Task Deep Learning |
| title_full | Hospitalization Patient Forecasting Based on Multi–Task Deep Learning |
| title_fullStr | Hospitalization Patient Forecasting Based on Multi–Task Deep Learning |
| title_full_unstemmed | Hospitalization Patient Forecasting Based on Multi–Task Deep Learning |
| title_short | Hospitalization Patient Forecasting Based on Multi–Task Deep Learning |
| title_sort | hospitalization patient forecasting based on multi task deep learning |
| topic | hospitalization patients forecasting neural network multitask learning |
| url | https://doi.org/10.34768/amcs-2023-0012 |
| work_keys_str_mv | AT zhoumin hospitalizationpatientforecastingbasedonmultitaskdeeplearning AT huangxiaoxiao hospitalizationpatientforecastingbasedonmultitaskdeeplearning AT liuhaipeng hospitalizationpatientforecastingbasedonmultitaskdeeplearning AT zhengdingchang hospitalizationpatientforecastingbasedonmultitaskdeeplearning |