An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning
Sepsis-associated coagulation dysfunction greatly increases the mortality of sepsis. Irregular clinical time-series data remains a major challenge for AI medical applications. To early detect and manage sepsis-induced coagulopathy (SIC) and sepsis-associated disseminated intravascular coagulation (D...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Frontiers Media S.A.
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/2d7495b4717845858bc66a17cab36f98 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:2d7495b4717845858bc66a17cab36f98 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:2d7495b4717845858bc66a17cab36f982021-12-03T07:11:20ZAn Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning2296-858X10.3389/fmed.2021.775047https://doaj.org/article/2d7495b4717845858bc66a17cab36f982021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fmed.2021.775047/fullhttps://doaj.org/toc/2296-858XSepsis-associated coagulation dysfunction greatly increases the mortality of sepsis. Irregular clinical time-series data remains a major challenge for AI medical applications. To early detect and manage sepsis-induced coagulopathy (SIC) and sepsis-associated disseminated intravascular coagulation (DIC), we developed an interpretable real-time sequential warning model toward real-world irregular data. Eight machine learning models including novel algorithms were devised to detect SIC and sepsis-associated DIC 8n (1 ≤ n ≤ 6) hours prior to its onset. Models were developed on Xi'an Jiaotong University Medical College (XJTUMC) and verified on Beth Israel Deaconess Medical Center (BIDMC). A total of 12,154 SIC and 7,878 International Society on Thrombosis and Haemostasis (ISTH) overt-DIC labels were annotated according to the SIC and ISTH overt-DIC scoring systems in train set. The area under the receiver operating characteristic curve (AUROC) were used as model evaluation metrics. The eXtreme Gradient Boosting (XGBoost) model can predict SIC and sepsis-associated DIC events up to 48 h earlier with an AUROC of 0.929 and 0.910, respectively, and even reached 0.973 and 0.955 at 8 h earlier, achieving the highest performance to date. The novel ODE-RNN model achieved continuous prediction at arbitrary time points, and with an AUROC of 0.962 and 0.936 for SIC and DIC predicted 8 h earlier, respectively. In conclusion, our model can predict the sepsis-associated SIC and DIC onset up to 48 h in advance, which helps maximize the time window for early management by physicians.Ruixia CuiRuixia CuiWenbo HuaKai QuHeran YangYingmu TongYingmu TongQinglin LiQinglin LiHai WangHai WangYanfen MaSinan LiuSinan LiuTing LinTing LinJingyao ZhangJingyao ZhangJingyao ZhangJian SunChang LiuChang LiuChang LiuFrontiers Media S.A.articleSICsepsis-associated DICirregular time-series dataearly real-time predictionmachine learningMedicine (General)R5-920ENFrontiers in Medicine, Vol 8 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
SIC sepsis-associated DIC irregular time-series data early real-time prediction machine learning Medicine (General) R5-920 |
| spellingShingle |
SIC sepsis-associated DIC irregular time-series data early real-time prediction machine learning Medicine (General) R5-920 Ruixia Cui Ruixia Cui Wenbo Hua Kai Qu Heran Yang Yingmu Tong Yingmu Tong Qinglin Li Qinglin Li Hai Wang Hai Wang Yanfen Ma Sinan Liu Sinan Liu Ting Lin Ting Lin Jingyao Zhang Jingyao Zhang Jingyao Zhang Jian Sun Chang Liu Chang Liu Chang Liu An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning |
| description |
Sepsis-associated coagulation dysfunction greatly increases the mortality of sepsis. Irregular clinical time-series data remains a major challenge for AI medical applications. To early detect and manage sepsis-induced coagulopathy (SIC) and sepsis-associated disseminated intravascular coagulation (DIC), we developed an interpretable real-time sequential warning model toward real-world irregular data. Eight machine learning models including novel algorithms were devised to detect SIC and sepsis-associated DIC 8n (1 ≤ n ≤ 6) hours prior to its onset. Models were developed on Xi'an Jiaotong University Medical College (XJTUMC) and verified on Beth Israel Deaconess Medical Center (BIDMC). A total of 12,154 SIC and 7,878 International Society on Thrombosis and Haemostasis (ISTH) overt-DIC labels were annotated according to the SIC and ISTH overt-DIC scoring systems in train set. The area under the receiver operating characteristic curve (AUROC) were used as model evaluation metrics. The eXtreme Gradient Boosting (XGBoost) model can predict SIC and sepsis-associated DIC events up to 48 h earlier with an AUROC of 0.929 and 0.910, respectively, and even reached 0.973 and 0.955 at 8 h earlier, achieving the highest performance to date. The novel ODE-RNN model achieved continuous prediction at arbitrary time points, and with an AUROC of 0.962 and 0.936 for SIC and DIC predicted 8 h earlier, respectively. In conclusion, our model can predict the sepsis-associated SIC and DIC onset up to 48 h in advance, which helps maximize the time window for early management by physicians. |
| format |
article |
| author |
Ruixia Cui Ruixia Cui Wenbo Hua Kai Qu Heran Yang Yingmu Tong Yingmu Tong Qinglin Li Qinglin Li Hai Wang Hai Wang Yanfen Ma Sinan Liu Sinan Liu Ting Lin Ting Lin Jingyao Zhang Jingyao Zhang Jingyao Zhang Jian Sun Chang Liu Chang Liu Chang Liu |
| author_facet |
Ruixia Cui Ruixia Cui Wenbo Hua Kai Qu Heran Yang Yingmu Tong Yingmu Tong Qinglin Li Qinglin Li Hai Wang Hai Wang Yanfen Ma Sinan Liu Sinan Liu Ting Lin Ting Lin Jingyao Zhang Jingyao Zhang Jingyao Zhang Jian Sun Chang Liu Chang Liu Chang Liu |
| author_sort |
Ruixia Cui |
| title |
An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning |
| title_short |
An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning |
| title_full |
An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning |
| title_fullStr |
An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning |
| title_full_unstemmed |
An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning |
| title_sort |
interpretable early dynamic sequential predictor for sepsis-induced coagulopathy progression in the real-world using machine learning |
| publisher |
Frontiers Media S.A. |
| publishDate |
2021 |
| url |
https://doaj.org/article/2d7495b4717845858bc66a17cab36f98 |
| work_keys_str_mv |
AT ruixiacui aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT ruixiacui aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT wenbohua aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT kaiqu aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT heranyang aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT yingmutong aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT yingmutong aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT qinglinli aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT qinglinli aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT haiwang aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT haiwang aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT yanfenma aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT sinanliu aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT sinanliu aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT tinglin aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT tinglin aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jingyaozhang aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jingyaozhang aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jingyaozhang aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jiansun aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT changliu aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT changliu aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT changliu aninterpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT ruixiacui interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT ruixiacui interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT wenbohua interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT kaiqu interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT heranyang interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT yingmutong interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT yingmutong interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT qinglinli interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT qinglinli interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT haiwang interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT haiwang interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT yanfenma interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT sinanliu interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT sinanliu interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT tinglin interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT tinglin interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jingyaozhang interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jingyaozhang interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jingyaozhang interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT jiansun interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT changliu interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT changliu interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning AT changliu interpretableearlydynamicsequentialpredictorforsepsisinducedcoagulopathyprogressionintherealworldusingmachinelearning |
| _version_ |
1718373862714900480 |