A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis
Background: Sepsis-induced coagulopathy (SIC) denotes an increased mortality rate and poorer prognosis in septic patients.Objectives: Our study aimed to develop and validate machine-learning models to dynamically predict the risk of SIC in critically ill patients with sepsis.Methods: Machine-learnin...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2020.637434/full |
| _version_ | 1818931179782406144 |
|---|---|
| author | Qin-Yu Zhao Qin-Yu Zhao Le-Ping Liu Jing-Chao Luo Yan-Wei Luo Huan Wang Yi-Jie Zhang Rong Gui Guo-Wei Tu Zhe Luo Zhe Luo |
| author_facet | Qin-Yu Zhao Qin-Yu Zhao Le-Ping Liu Jing-Chao Luo Yan-Wei Luo Huan Wang Yi-Jie Zhang Rong Gui Guo-Wei Tu Zhe Luo Zhe Luo |
| author_sort | Qin-Yu Zhao |
| collection | DOAJ |
| description | Background: Sepsis-induced coagulopathy (SIC) denotes an increased mortality rate and poorer prognosis in septic patients.Objectives: Our study aimed to develop and validate machine-learning models to dynamically predict the risk of SIC in critically ill patients with sepsis.Methods: Machine-learning models were developed and validated based on two public databases named Medical Information Mart for Intensive Care (MIMIC)-IV and the eICU Collaborative Research Database (eICU-CRD). Dynamic prediction of SIC involved an evaluation of the risk of SIC each day after the diagnosis of sepsis using 15 predictive models. The best model was selected based on its accuracy and area under the receiver operating characteristic curve (AUC), followed by fine-grained hyperparameter adjustment using the Bayesian Optimization Algorithm. A compact model was developed, based on 15 features selected according to their importance and clinical availability. These two models were compared with Logistic Regression and SIC scores in terms of SIC prediction.Results: Of 11,362 patients in MIMIC-IV included in the final cohort, a total of 6,744 (59%) patients developed SIC during sepsis. The model named Categorical Boosting (CatBoost) had the greatest AUC in our study (0.869; 95% CI: 0.850–0.886). Coagulation profile and renal function indicators were the most important features for predicting SIC. A compact model was developed with an AUC of 0.854 (95% CI: 0.832–0.872), while the AUCs of Logistic Regression and SIC scores were 0.746 (95% CI: 0.735–0.755) and 0.709 (95% CI: 0.687–0.733), respectively. A cohort of 35,252 septic patients in eICU-CRD was analyzed. The AUCs of the full and the compact models in the external validation were 0.842 (95% CI: 0.837–0.846) and 0.803 (95% CI: 0.798–0.809), respectively, which were still larger than those of Logistic Regression (0.660; 95% CI: 0.653–0.667) and SIC scores (0.752; 95% CI: 0.747–0.757). Prediction results were illustrated by SHapley Additive exPlanations (SHAP) values, which made our models clinically interpretable.Conclusions: We developed two models which were able to dynamically predict the risk of SIC in septic patients better than conventional Logistic Regression and SIC scores. |
| first_indexed | 2024-12-20T04:12:29Z |
| format | Article |
| id | doaj.art-da8b6a0233b34a1490c58ea2aa11d893 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-12-20T04:12:29Z |
| publishDate | 2021-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-da8b6a0233b34a1490c58ea2aa11d8932022-12-21T19:53:51ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2021-01-01710.3389/fmed.2020.637434637434A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With SepsisQin-Yu Zhao0Qin-Yu Zhao1Le-Ping Liu2Jing-Chao Luo3Yan-Wei Luo4Huan Wang5Yi-Jie Zhang6Rong Gui7Guo-Wei Tu8Zhe Luo9Zhe Luo10Department of Blood Transfusion, The Third Xiangya Hospital of Central South University, Changsha, ChinaCollege of Engineering and Computer Science, Australian National University, Canberra, ACT, AustraliaDepartment of Blood Transfusion, The Third Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, ChinaDepartment of Blood Transfusion, The Third Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, ChinaDepartment of Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, ChinaDepartment of Blood Transfusion, The Third Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, ChinaDepartment of Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai, ChinaDepartment of Critical Care Medicine, Xiamen Branch, Zhongshan Hospital, Fudan University, Xiamen, ChinaBackground: Sepsis-induced coagulopathy (SIC) denotes an increased mortality rate and poorer prognosis in septic patients.Objectives: Our study aimed to develop and validate machine-learning models to dynamically predict the risk of SIC in critically ill patients with sepsis.Methods: Machine-learning models were developed and validated based on two public databases named Medical Information Mart for Intensive Care (MIMIC)-IV and the eICU Collaborative Research Database (eICU-CRD). Dynamic prediction of SIC involved an evaluation of the risk of SIC each day after the diagnosis of sepsis using 15 predictive models. The best model was selected based on its accuracy and area under the receiver operating characteristic curve (AUC), followed by fine-grained hyperparameter adjustment using the Bayesian Optimization Algorithm. A compact model was developed, based on 15 features selected according to their importance and clinical availability. These two models were compared with Logistic Regression and SIC scores in terms of SIC prediction.Results: Of 11,362 patients in MIMIC-IV included in the final cohort, a total of 6,744 (59%) patients developed SIC during sepsis. The model named Categorical Boosting (CatBoost) had the greatest AUC in our study (0.869; 95% CI: 0.850–0.886). Coagulation profile and renal function indicators were the most important features for predicting SIC. A compact model was developed with an AUC of 0.854 (95% CI: 0.832–0.872), while the AUCs of Logistic Regression and SIC scores were 0.746 (95% CI: 0.735–0.755) and 0.709 (95% CI: 0.687–0.733), respectively. A cohort of 35,252 septic patients in eICU-CRD was analyzed. The AUCs of the full and the compact models in the external validation were 0.842 (95% CI: 0.837–0.846) and 0.803 (95% CI: 0.798–0.809), respectively, which were still larger than those of Logistic Regression (0.660; 95% CI: 0.653–0.667) and SIC scores (0.752; 95% CI: 0.747–0.757). Prediction results were illustrated by SHapley Additive exPlanations (SHAP) values, which made our models clinically interpretable.Conclusions: We developed two models which were able to dynamically predict the risk of SIC in septic patients better than conventional Logistic Regression and SIC scores.https://www.frontiersin.org/articles/10.3389/fmed.2020.637434/fullsepsis-induced coagulopathydynamic predictionmachine learningLogistic Regressionexternal validationmodel interpretation |
| spellingShingle | Qin-Yu Zhao Qin-Yu Zhao Le-Ping Liu Jing-Chao Luo Yan-Wei Luo Huan Wang Yi-Jie Zhang Rong Gui Guo-Wei Tu Zhe Luo Zhe Luo A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis Frontiers in Medicine sepsis-induced coagulopathy dynamic prediction machine learning Logistic Regression external validation model interpretation |
| title | A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis |
| title_full | A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis |
| title_fullStr | A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis |
| title_full_unstemmed | A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis |
| title_short | A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis |
| title_sort | machine learning approach for dynamic prediction of sepsis induced coagulopathy in critically ill patients with sepsis |
| topic | sepsis-induced coagulopathy dynamic prediction machine learning Logistic Regression external validation model interpretation |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2020.637434/full |
| work_keys_str_mv | AT qinyuzhao amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT qinyuzhao amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT lepingliu amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT jingchaoluo amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT yanweiluo amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT huanwang amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT yijiezhang amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT ronggui amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT guoweitu amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT zheluo amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT zheluo amachinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT qinyuzhao machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT qinyuzhao machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT lepingliu machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT jingchaoluo machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT yanweiluo machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT huanwang machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT yijiezhang machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT ronggui machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT guoweitu machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT zheluo machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis AT zheluo machinelearningapproachfordynamicpredictionofsepsisinducedcoagulopathyincriticallyillpatientswithsepsis |