Evidence-based lab test critical value discovery for ICU patients
In clinical research, a very common task is to predict the patients’ potential critical conditions in future using the time series data collected from the patients. Recently, due to the growth of deep learning, recurrent neural network (RNN), a traditional deep learning model, is widely used to mode...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/74389 |
| _version_ | 1826118336159678464 |
|---|---|
| author | Pan, Ziyuan |
| author2 | Shum Ping |
| author_facet | Shum Ping Pan, Ziyuan |
| author_sort | Pan, Ziyuan |
| collection | NTU |
| description | In clinical research, a very common task is to predict the patients’ potential critical conditions in future using the time series data collected from the patients. Recently, due to the growth of deep learning, recurrent neural network (RNN), a traditional deep learning model, is widely used to model time series data in clinical research. In this project, we proposed a novel architecture for RNN. It allows the neural network to make prediction at each time step based not only on its current input, but the previous prediction and the actual observed result of the previous time step. In our experiment, we focused on predicting the acute kidney injury for patients in ICU. And we found that our proposed methods help to improve the prediction accuracy of RNN. |
| first_indexed | 2024-10-01T04:41:44Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/74389 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:41:44Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/743892023-07-07T16:07:32Z Evidence-based lab test critical value discovery for ICU patients Pan, Ziyuan Shum Ping School of Electrical and Electronic Engineering Saw Swee Hock School of Public Health, National University of Singapore Feng Mengling DRNTU::Engineering::Electrical and electronic engineering In clinical research, a very common task is to predict the patients’ potential critical conditions in future using the time series data collected from the patients. Recently, due to the growth of deep learning, recurrent neural network (RNN), a traditional deep learning model, is widely used to model time series data in clinical research. In this project, we proposed a novel architecture for RNN. It allows the neural network to make prediction at each time step based not only on its current input, but the previous prediction and the actual observed result of the previous time step. In our experiment, we focused on predicting the acute kidney injury for patients in ICU. And we found that our proposed methods help to improve the prediction accuracy of RNN. Bachelor of Engineering 2018-05-17T03:26:32Z 2018-05-17T03:26:32Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/74389 en Nanyang Technological University 54 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Pan, Ziyuan Evidence-based lab test critical value discovery for ICU patients |
| title | Evidence-based lab test critical value discovery for ICU patients |
| title_full | Evidence-based lab test critical value discovery for ICU patients |
| title_fullStr | Evidence-based lab test critical value discovery for ICU patients |
| title_full_unstemmed | Evidence-based lab test critical value discovery for ICU patients |
| title_short | Evidence-based lab test critical value discovery for ICU patients |
| title_sort | evidence based lab test critical value discovery for icu patients |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/74389 |
| work_keys_str_mv | AT panziyuan evidencebasedlabtestcriticalvaluediscoveryforicupatients |