Development and validation of a practical machine learning model to predict sepsis after liver transplantation
AbstractBackground Postoperative sepsis is one of the main causes of mortality after liver transplantation (LT). Our study aimed to develop and validate a predictive model for postoperative sepsis within 7 d in LT recipients using machine learning (ML) technology.Methods Data of 786 patients receive...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Annals of Medicine |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/07853890.2023.2179104 |
| _version_ | 1797353739091181568 |
|---|---|
| author | Chaojin Chen Bingcheng Chen Jing Yang Xiaoyue Li Xiaorong Peng Yawei Feng Rongchang Guo Fengyuan Zou Shaoli Zhou Ziqing Hei |
| author_facet | Chaojin Chen Bingcheng Chen Jing Yang Xiaoyue Li Xiaorong Peng Yawei Feng Rongchang Guo Fengyuan Zou Shaoli Zhou Ziqing Hei |
| author_sort | Chaojin Chen |
| collection | DOAJ |
| description | AbstractBackground Postoperative sepsis is one of the main causes of mortality after liver transplantation (LT). Our study aimed to develop and validate a predictive model for postoperative sepsis within 7 d in LT recipients using machine learning (ML) technology.Methods Data of 786 patients received LT from January 2015 to January 2020 was retrospectively extracted from the big data platform of Third Affiliated Hospital of Sun Yat-sen University. Seven ML models were developed to predict postoperative sepsis. The area under the receiver-operating curve (AUC), sensitivity, specificity, accuracy, and f1-score were evaluated as the model performances. The model with the best performance was validated in an independent dataset involving 118 adult LT cases from February 2020 to April 2021. The postoperative sepsis-associated outcomes were also explored in the study.Results After excluding 109 patients according to the exclusion criteria, 677 patients underwent LT were finally included in the analysis. Among them, 216 (31.9%) were diagnosed with sepsis after LT, which were related to more perioperative complications, increased postoperative hospital stay and mortality after LT (all p < .05). Our results revealed that a larger volume of red blood cell infusion, ascitic removal, blood loss and gastric drainage, less volume of crystalloid infusion and urine, longer anesthesia time, higher level of preoperative TBIL were the top 8 important variables contributing to the prediction of post-LT sepsis. The Random Forest Classifier (RF) model showed the best overall performance to predict sepsis after LT among the seven ML models developed in the study, with an AUC of 0.731, an accuracy of 71.6%, the sensitivity of 62.1%, and specificity of 76.1% in the internal validation set, and a comparable AUC of 0.755 in the external validation set.Conclusions Our study enrolled eight pre- and intra-operative variables to develop an RF-based predictive model of post-LT sepsis to assist clinical decision-making procedure. |
| first_indexed | 2024-03-08T13:35:24Z |
| format | Article |
| id | doaj.art-6cec9bf2fe134168a9dc86df245afe84 |
| institution | Directory Open Access Journal |
| issn | 0785-3890 1365-2060 |
| language | English |
| last_indexed | 2024-03-08T13:35:24Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Annals of Medicine |
| spelling | doaj.art-6cec9bf2fe134168a9dc86df245afe842024-01-16T19:13:22ZengTaylor & Francis GroupAnnals of Medicine0785-38901365-20602023-12-0155162463310.1080/07853890.2023.2179104Development and validation of a practical machine learning model to predict sepsis after liver transplantationChaojin Chen0Bingcheng Chen1Jing Yang2Xiaoyue Li3Xiaorong Peng4Yawei Feng5Rongchang Guo6Fengyuan Zou7Shaoli Zhou8Ziqing Hei9Department of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaGuangzhou AID Cloud Technology Co., LTD, Guangzhou, People’s Republic of ChinaGuangzhou AID Cloud Technology Co., LTD, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, People’s Republic of ChinaAbstractBackground Postoperative sepsis is one of the main causes of mortality after liver transplantation (LT). Our study aimed to develop and validate a predictive model for postoperative sepsis within 7 d in LT recipients using machine learning (ML) technology.Methods Data of 786 patients received LT from January 2015 to January 2020 was retrospectively extracted from the big data platform of Third Affiliated Hospital of Sun Yat-sen University. Seven ML models were developed to predict postoperative sepsis. The area under the receiver-operating curve (AUC), sensitivity, specificity, accuracy, and f1-score were evaluated as the model performances. The model with the best performance was validated in an independent dataset involving 118 adult LT cases from February 2020 to April 2021. The postoperative sepsis-associated outcomes were also explored in the study.Results After excluding 109 patients according to the exclusion criteria, 677 patients underwent LT were finally included in the analysis. Among them, 216 (31.9%) were diagnosed with sepsis after LT, which were related to more perioperative complications, increased postoperative hospital stay and mortality after LT (all p < .05). Our results revealed that a larger volume of red blood cell infusion, ascitic removal, blood loss and gastric drainage, less volume of crystalloid infusion and urine, longer anesthesia time, higher level of preoperative TBIL were the top 8 important variables contributing to the prediction of post-LT sepsis. The Random Forest Classifier (RF) model showed the best overall performance to predict sepsis after LT among the seven ML models developed in the study, with an AUC of 0.731, an accuracy of 71.6%, the sensitivity of 62.1%, and specificity of 76.1% in the internal validation set, and a comparable AUC of 0.755 in the external validation set.Conclusions Our study enrolled eight pre- and intra-operative variables to develop an RF-based predictive model of post-LT sepsis to assist clinical decision-making procedure.https://www.tandfonline.com/doi/10.1080/07853890.2023.2179104Postoperative sepsisliver transplantationmachine learningearly interventiondecision-making |
| spellingShingle | Chaojin Chen Bingcheng Chen Jing Yang Xiaoyue Li Xiaorong Peng Yawei Feng Rongchang Guo Fengyuan Zou Shaoli Zhou Ziqing Hei Development and validation of a practical machine learning model to predict sepsis after liver transplantation Annals of Medicine Postoperative sepsis liver transplantation machine learning early intervention decision-making |
| title | Development and validation of a practical machine learning model to predict sepsis after liver transplantation |
| title_full | Development and validation of a practical machine learning model to predict sepsis after liver transplantation |
| title_fullStr | Development and validation of a practical machine learning model to predict sepsis after liver transplantation |
| title_full_unstemmed | Development and validation of a practical machine learning model to predict sepsis after liver transplantation |
| title_short | Development and validation of a practical machine learning model to predict sepsis after liver transplantation |
| title_sort | development and validation of a practical machine learning model to predict sepsis after liver transplantation |
| topic | Postoperative sepsis liver transplantation machine learning early intervention decision-making |
| url | https://www.tandfonline.com/doi/10.1080/07853890.2023.2179104 |
| work_keys_str_mv | AT chaojinchen developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT bingchengchen developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT jingyang developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT xiaoyueli developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT xiaorongpeng developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT yaweifeng developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT rongchangguo developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT fengyuanzou developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT shaolizhou developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation AT ziqinghei developmentandvalidationofapracticalmachinelearningmodeltopredictsepsisafterlivertransplantation |