Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia
Abstract Postoperative nausea and vomiting (PONV) can lead to various postoperative complications. The risk assessment model of PONV is helpful in guiding treatment and reducing the incidence of PONV, whereas the published models of PONV do not have a high accuracy rate. This study aimed to collect...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-33807-7 |
| _version_ | 1797841088181960704 |
|---|---|
| author | Min Xie Yan Deng Zuofeng Wang Yanxia He Xingwei Wu Meng Zhang Yao He Yu Liang Tao Li |
| author_facet | Min Xie Yan Deng Zuofeng Wang Yanxia He Xingwei Wu Meng Zhang Yao He Yu Liang Tao Li |
| author_sort | Min Xie |
| collection | DOAJ |
| description | Abstract Postoperative nausea and vomiting (PONV) can lead to various postoperative complications. The risk assessment model of PONV is helpful in guiding treatment and reducing the incidence of PONV, whereas the published models of PONV do not have a high accuracy rate. This study aimed to collect data from patients in Sichuan Provincial People’s Hospital to develop models for predicting PONV based on machine learning algorithms, and to evaluate the predictive performance of the models using the area under the receiver characteristic curve (AUC), accuracy, precision, recall rate, F1 value and area under the precision-recall curve (AUPRC). The AUC (0.947) of our best machine learning model was significantly higher than that of the past models. The best of these models was used for external validation on patients from Chengdu First People’s Hospital, and the AUC was 0.821. The contributions of variables were also interpreted using SHapley Additive ExPlanation (SHAP). A history of motion sickness and/or PONV, sex, weight, history of surgery, infusion volume, intraoperative urine volume, age, BMI, height, and PCA_3.0 were the top ten most important variables for the model. The machine learning models of PONV provided a good preoperative prediction of PONV for intravenous patient-controlled analgesia. |
| first_indexed | 2024-04-09T16:25:22Z |
| format | Article |
| id | doaj.art-94bcf9640f814d4ebb28c7b1a52125b0 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T16:25:22Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-94bcf9640f814d4ebb28c7b1a52125b02023-04-23T11:16:21ZengNature PortfolioScientific Reports2045-23222023-04-0113111110.1038/s41598-023-33807-7Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesiaMin Xie0Yan Deng1Zuofeng Wang2Yanxia He3Xingwei Wu4Meng Zhang5Yao He6Yu Liang7Tao Li8Laboratory of Mitochondria and Metabolism, Department of Anesthesiology, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan UniversityLaboratory of Mitochondria and Metabolism, Department of Anesthesiology, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan UniversityDepartment of Anesthesiology, Chengdu First People’s HospitalDepartment of Anesthesiology, Sichuan Academy of Medical Sciences & Sichuan Provincial People’s HospitalPersonalized Drug Therapy Key Laboratory of Sichuan Province, Department of Pharmacy, Sichuan Academy of Medical Sciences & Sichuan Provincial People’s HospitalDepartment of Anesthesiology, Sichuan Academy of Medical Sciences & Sichuan Provincial People’s HospitalDepartment of Anesthesiology, Sichuan Academy of Medical Sciences & Sichuan Provincial People’s HospitalDepartment of Anesthesiology, Sichuan Academy of Medical Sciences & Sichuan Provincial People’s HospitalLaboratory of Mitochondria and Metabolism, Department of Anesthesiology, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan UniversityAbstract Postoperative nausea and vomiting (PONV) can lead to various postoperative complications. The risk assessment model of PONV is helpful in guiding treatment and reducing the incidence of PONV, whereas the published models of PONV do not have a high accuracy rate. This study aimed to collect data from patients in Sichuan Provincial People’s Hospital to develop models for predicting PONV based on machine learning algorithms, and to evaluate the predictive performance of the models using the area under the receiver characteristic curve (AUC), accuracy, precision, recall rate, F1 value and area under the precision-recall curve (AUPRC). The AUC (0.947) of our best machine learning model was significantly higher than that of the past models. The best of these models was used for external validation on patients from Chengdu First People’s Hospital, and the AUC was 0.821. The contributions of variables were also interpreted using SHapley Additive ExPlanation (SHAP). A history of motion sickness and/or PONV, sex, weight, history of surgery, infusion volume, intraoperative urine volume, age, BMI, height, and PCA_3.0 were the top ten most important variables for the model. The machine learning models of PONV provided a good preoperative prediction of PONV for intravenous patient-controlled analgesia.https://doi.org/10.1038/s41598-023-33807-7 |
| spellingShingle | Min Xie Yan Deng Zuofeng Wang Yanxia He Xingwei Wu Meng Zhang Yao He Yu Liang Tao Li Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia Scientific Reports |
| title | Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia |
| title_full | Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia |
| title_fullStr | Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia |
| title_full_unstemmed | Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia |
| title_short | Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia |
| title_sort | development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient controlled analgesia |
| url | https://doi.org/10.1038/s41598-023-33807-7 |
| work_keys_str_mv | AT minxie developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT yandeng developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT zuofengwang developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT yanxiahe developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT xingweiwu developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT mengzhang developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT yaohe developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT yuliang developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia AT taoli developmentandassessmentofnovelmachinelearningmodelstopredicttheprobabilityofpostoperativenauseaandvomitingforpatientcontrolledanalgesia |