Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia.
<h4>Background</h4>Postoperative nausea and vomiting (PONV) is a still highly relevant problem and is known to be a distressing side effect in patients. The aim of this study was to develop a machine learning model to predict PONV up to 24 h with fentanyl-based intravenous patient-contro...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0277957 |
| _version_ | 1797956078751711232 |
|---|---|
| author | Jae-Geum Shim Kyoung-Ho Ryu Eun-Ah Cho Jin Hee Ahn Yun Byeong Cha Goeun Lim Sung Hyun Lee |
| author_facet | Jae-Geum Shim Kyoung-Ho Ryu Eun-Ah Cho Jin Hee Ahn Yun Byeong Cha Goeun Lim Sung Hyun Lee |
| author_sort | Jae-Geum Shim |
| collection | DOAJ |
| description | <h4>Background</h4>Postoperative nausea and vomiting (PONV) is a still highly relevant problem and is known to be a distressing side effect in patients. The aim of this study was to develop a machine learning model to predict PONV up to 24 h with fentanyl-based intravenous patient-controlled analgesia (IV-PCA).<h4>Methods</h4>From July 2019 and July 2020, data from 2,149 patients who received fentanyl-based IV-PCA for analgesia after non-cardiac surgery under general anesthesia were applied to develop predictive models. The rates of PONV at 1 day after surgery were measured according to patient characteristics as well as anesthetic, surgical, or PCA-related factors. All statistical analyses and computations were performed using the R software.<h4>Results</h4>A total of 2,149 patients were enrolled in this study, 337 of whom (15.7%) experienced PONV. After applying the machine-learning algorithm and Apfel model to the test dataset to predict PONV, we found that the area under the receiver operating characteristic curve using logistic regression was 0.576 (95% confidence interval [CI], 0.520-0.633), k-nearest neighbor was 0.597 (95% CI, 0.537-0.656), decision tree was 0.561 (95% CI, 0.498-0.625), random forest was 0.610 (95% CI, 0.552-0.668), gradient boosting machine was 0.580 (95% CI, 0.520-0.639), support vector machine was 0.649 (95% CI, 0.592-0.707), artificial neural network was 0.686 (95% CI, 0.630-0.742), and Apfel model was 0.643 (95% CI, 0.596-0.690).<h4>Conclusions</h4>We developed and validated machine learning models for predicting PONV in the first 24 h. The machine learning model showed better performance than the Apfel model in predicting PONV. |
| first_indexed | 2024-04-10T23:43:14Z |
| format | Article |
| id | doaj.art-01e27f1835ad4bd18661b34509e7f510 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-10T23:43:14Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-01e27f1835ad4bd18661b34509e7f5102023-01-11T05:32:24ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-011712e027795710.1371/journal.pone.0277957Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia.Jae-Geum ShimKyoung-Ho RyuEun-Ah ChoJin Hee AhnYun Byeong ChaGoeun LimSung Hyun Lee<h4>Background</h4>Postoperative nausea and vomiting (PONV) is a still highly relevant problem and is known to be a distressing side effect in patients. The aim of this study was to develop a machine learning model to predict PONV up to 24 h with fentanyl-based intravenous patient-controlled analgesia (IV-PCA).<h4>Methods</h4>From July 2019 and July 2020, data from 2,149 patients who received fentanyl-based IV-PCA for analgesia after non-cardiac surgery under general anesthesia were applied to develop predictive models. The rates of PONV at 1 day after surgery were measured according to patient characteristics as well as anesthetic, surgical, or PCA-related factors. All statistical analyses and computations were performed using the R software.<h4>Results</h4>A total of 2,149 patients were enrolled in this study, 337 of whom (15.7%) experienced PONV. After applying the machine-learning algorithm and Apfel model to the test dataset to predict PONV, we found that the area under the receiver operating characteristic curve using logistic regression was 0.576 (95% confidence interval [CI], 0.520-0.633), k-nearest neighbor was 0.597 (95% CI, 0.537-0.656), decision tree was 0.561 (95% CI, 0.498-0.625), random forest was 0.610 (95% CI, 0.552-0.668), gradient boosting machine was 0.580 (95% CI, 0.520-0.639), support vector machine was 0.649 (95% CI, 0.592-0.707), artificial neural network was 0.686 (95% CI, 0.630-0.742), and Apfel model was 0.643 (95% CI, 0.596-0.690).<h4>Conclusions</h4>We developed and validated machine learning models for predicting PONV in the first 24 h. The machine learning model showed better performance than the Apfel model in predicting PONV.https://doi.org/10.1371/journal.pone.0277957 |
| spellingShingle | Jae-Geum Shim Kyoung-Ho Ryu Eun-Ah Cho Jin Hee Ahn Yun Byeong Cha Goeun Lim Sung Hyun Lee Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. PLoS ONE |
| title | Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. |
| title_full | Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. |
| title_fullStr | Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. |
| title_full_unstemmed | Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. |
| title_short | Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. |
| title_sort | machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient controlled analgesia |
| url | https://doi.org/10.1371/journal.pone.0277957 |
| work_keys_str_mv | AT jaegeumshim machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia AT kyounghoryu machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia AT eunahcho machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia AT jinheeahn machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia AT yunbyeongcha machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia AT goeunlim machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia AT sunghyunlee machinelearningforpredictionofpostoperativenauseaandvomitinginpatientswithintravenouspatientcontrolledanalgesia |