An interpretable DIC risk prediction model based on convolutional neural networks with time series data
Abstract Disseminated intravascular coagulation (DIC) is a complex, life-threatening syndrome associated with the end-stage of different coagulation disorders. Early prediction of the risk of DIC development is an urgent clinical need to reduce adverse outcomes. However, effective approaches and mod...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-11-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-05004-2 |
| _version_ | 1811180271601451008 |
|---|---|
| author | Hao Yang Jiaxi Li Siru Liu Mengjiao Zhang Jialin Liu |
| author_facet | Hao Yang Jiaxi Li Siru Liu Mengjiao Zhang Jialin Liu |
| author_sort | Hao Yang |
| collection | DOAJ |
| description | Abstract Disseminated intravascular coagulation (DIC) is a complex, life-threatening syndrome associated with the end-stage of different coagulation disorders. Early prediction of the risk of DIC development is an urgent clinical need to reduce adverse outcomes. However, effective approaches and models to identify early DIC are still lacking. In this study, a novel interpretable deep learning based time series is used to predict the risk of DIC. The study cohort included ICU patients from a 4300-bed academic hospital between January 1, 2019, and January 1, 2022. Experimental results show that our model achieves excellent performance (AUC: 0.986, Accuracy: 95.7%, and F1:0.935). Gradient-weighted Class Activation Mapping (Grad-CAM) was used to explain how predictive models identified patients with DIC. The decision basis of the model was displayed in the form of a heat map. The model can be used to identify high-risk patients with DIC early, which will help in the early intervention of DIC patients and improve the treatment effect. |
| first_indexed | 2024-04-11T06:48:35Z |
| format | Article |
| id | doaj.art-f33ad416eb13496f98b71bd228cb0c28 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-11T06:48:35Z |
| publishDate | 2022-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-f33ad416eb13496f98b71bd228cb0c282022-12-22T04:39:17ZengBMCBMC Bioinformatics1471-21052022-11-0123111410.1186/s12859-022-05004-2An interpretable DIC risk prediction model based on convolutional neural networks with time series dataHao Yang0Jiaxi Li1Siru Liu2Mengjiao Zhang3Jialin Liu4Information Center, West China Hospital, Sichuan UniversityDepartment of Clinical Laboratory Medicine, Jinniu Maternity and Child Health Hospital of ChengduDepartment of Biomedical Informatics, Vanderbilt University Medical CenterInformation Center, West China Hospital, Sichuan UniversityInformation Center, West China Hospital, Sichuan UniversityAbstract Disseminated intravascular coagulation (DIC) is a complex, life-threatening syndrome associated with the end-stage of different coagulation disorders. Early prediction of the risk of DIC development is an urgent clinical need to reduce adverse outcomes. However, effective approaches and models to identify early DIC are still lacking. In this study, a novel interpretable deep learning based time series is used to predict the risk of DIC. The study cohort included ICU patients from a 4300-bed academic hospital between January 1, 2019, and January 1, 2022. Experimental results show that our model achieves excellent performance (AUC: 0.986, Accuracy: 95.7%, and F1:0.935). Gradient-weighted Class Activation Mapping (Grad-CAM) was used to explain how predictive models identified patients with DIC. The decision basis of the model was displayed in the form of a heat map. The model can be used to identify high-risk patients with DIC early, which will help in the early intervention of DIC patients and improve the treatment effect.https://doi.org/10.1186/s12859-022-05004-2Disseminated intravascular coagulationPredictionMachine learning |
| spellingShingle | Hao Yang Jiaxi Li Siru Liu Mengjiao Zhang Jialin Liu An interpretable DIC risk prediction model based on convolutional neural networks with time series data BMC Bioinformatics Disseminated intravascular coagulation Prediction Machine learning |
| title | An interpretable DIC risk prediction model based on convolutional neural networks with time series data |
| title_full | An interpretable DIC risk prediction model based on convolutional neural networks with time series data |
| title_fullStr | An interpretable DIC risk prediction model based on convolutional neural networks with time series data |
| title_full_unstemmed | An interpretable DIC risk prediction model based on convolutional neural networks with time series data |
| title_short | An interpretable DIC risk prediction model based on convolutional neural networks with time series data |
| title_sort | interpretable dic risk prediction model based on convolutional neural networks with time series data |
| topic | Disseminated intravascular coagulation Prediction Machine learning |
| url | https://doi.org/10.1186/s12859-022-05004-2 |
| work_keys_str_mv | AT haoyang aninterpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT jiaxili aninterpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT siruliu aninterpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT mengjiaozhang aninterpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT jialinliu aninterpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT haoyang interpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT jiaxili interpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT siruliu interpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT mengjiaozhang interpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata AT jialinliu interpretabledicriskpredictionmodelbasedonconvolutionalneuralnetworkswithtimeseriesdata |