Skip to Content
MDPIMDPI
BioengineeringBioengineering
PDF
  • Article
  • Open Access

1 October 2023

Postoperative Nausea and Vomiting Prediction: Machine Learning Insights from a Comprehensive Analysis of Perioperative Data

,
,
,
,
,
and
1
Department of Anesthesiology and Pain Medicine, Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon-si 24253, Republic of Korea
2
Institute of New Frontier Research Team, Hallym University College of Medicine, Chuncheon-si 24252, Republic of Korea
*
Author to whom correspondence should be addressed.
Bioengineering2023, 10(10), 1152;https://doi.org/10.3390/bioengineering10101152
This article belongs to the Special Issue Artificial Intelligence in Surgery
Version Notes
Order Reprints

Abstract

Postoperative nausea and vomiting (PONV) are common complications after surgery. This study aimed to present the utilization of machine learning for predicting PONV and provide insights based on a large amount of data. This retrospective study included data on perioperative features of patients, such as patient characteristics and perioperative factors, from two hospitals. Logistic regression algorithms, random forest, light-gradient boosting machines, and multilayer perceptrons were used as machine learning algorithms to develop the models. The dataset of this study included 106,860 adult patients, with an overall incidence rate of 14.4% for PONV. The area under the receiver operating characteristic curve (AUROC) of the models was 0.60–0.67. In the prediction models that included only the known risk and mitigating factors of PONV, the AUROC of the models was 0.54–0.69. Some features were found to be associated with patient-controlled analgesia, with opioids being the most important feature in almost all models. In conclusion, machine learning provides valuable insights into PONV prediction, the selection of significant features for prediction, and feature engineering.

1. Introduction

Postoperative nausea and vomiting (PONV) is a common and distressing complication experienced by patients after surgery, particularly under general anesthesia [1,2,3,4]. This can lead to discomfort, delayed recovery, and even extended hospital stays, negatively affecting the overall patient experience and increasing healthcare costs [3,5,6]. Therefore, effective management of PONV is crucial for improving patient outcomes and satisfaction during the postoperative period [7].
Traditional approaches to managing PONV involve the administration of prophylactic antiemetic medications to high-risk patients based on clinical risk factors [7,8,9]. However, these approaches are often suboptimal as they may not accurately predict individual patient risks and can result in unnecessary medication use [10]. Consequently, there is a growing interest in developing more precise and personalized predictive models for PONV, leveraging machine learning algorithms to consider patient-specific data and risk factors.
In recent years, advancements in machine learning have revolutionized various fields, including healthcare [11,12]. In particular, machine learning holds great promise in the prediction and prevention of postoperative complications [13,14], such as PONV. The ability to accurately predict which patients are at higher risk for PONV would allow clinicians to tailor preventive strategies and interventions proactively, ultimately improving patient care and recovery.
This study aimed to present a predictive model for PONV that we developed through machine learning techniques using anonymized patient information, including demographic characteristics, medical history, surgical details, and medication administration records.

2. Materials and Methods

2.1. Study Design

This study used data that had been collected from the electronic medical records of two hospitals at Hallym University. Data were collected from 1 January 2013 to 30 April 2023. This study complied with the World Medical Association Declaration of Helsinki and was approved by the Institutional Regional Ethics Committee. The requirement for informed consent was waived because the data used were from patients whose treatment ended.

2.2. Participants

This study included data from patients who underwent surgery and excluded those aged <18 years who underwent surgery under non-general anesthesia, were unconscious, received postoperative ventilator care, underwent reoperation or discharge within 24 h after surgery, or had missing data.

2.3. Postoperative Nausea and Vomiting

PONV was defined as the occurrence of nausea or vomiting within 24 h after surgery.

2.4. Other Features

The dataset in this study included 103 features that consisted of patient characteristics and perioperative data: Age, the female sex, body mass index, alcohol, smoking, comorbidities (congestive heart failure, cardiac arrhythmias, valvular disease, pulmonary circulation disorders, peripheral vascular disorders, hypertension uncomplicated, hypertension complicated, paralysis, other neurological disorders, chronic pulmonary disease, diabetes uncomplicated, diabetes complicated, hypothyroidism, renal failure, liver disease, peptic ulcer disease excluding bleeding, acquired immune deficiency syndrome/human immunodeficiency virus, lymphoma, metastatic cancer, solid tumor without metastasis, rheumatoid arthritis/collagen vascular diseases, coagulopathy, obesity, weight loss, fluid and electrolyte disorders, blood loss anemia, deficiency anemia, alcohol abuse, drug abuse, psychoses, depression, gastroesophageal reflux disease, migraine), preoperative data (preoperative nausea vomiting, American Society of Anesthesiologists physical status, emergency), intraoperative data (anesthesia time, operation time, administered blood and fluid, urine output, estimated blood loss, unit of packed red blood cells, fresh frozen plasma and platelet concentration, arterial cannulation line, central venous cannulation line, Foley catheter, Levin-tube, type and dose of anesthetics, N2O, antiemetics and type of surgery) and postoperative data (type of patient-controlled analgesia [PCA], dose of opioid in PCA, rate of PCA, opioid dose in postanesthetic care [PACU], O2 supplying after surgery, frequency of administered opioid after PACU, opioid dose except for transdermal opioid patch after PACU and opioid dose of transdermal opioid patch after PACU).

2.5. Data Preprocessing

Data were divided into continuous and categorical categories. Continuous data were standardized by removing the mean and scaling it to the unit variance [15]. This study had an imbalance in the target PONV. There were more patients without PONV than those with PONV. In classification problems, imbalanced datasets negatively affect the accuracy of class predictions [16]. To solve this problem, we applied the synthetic minority oversampling technique (SMOTE) [17]. SMOTE is a method for generating new data of a minor class using the k-NN algorithm. Subsequently, we divided the entire dataset into training and test datasets in an 8:2 ratio. We randomly assigned similar rates of PONV to the training and test sets.

2.6. Machine Learning

We used five algorithms to develop the PONV prediction models. The four algorithms were as follows: logistic regression, random forest, light-gradient boosting machine, multilayer perceptron, and extreme boosting machine [18,19,20,21,22]. In the random forest, we used the balanced random forest built-in packages without SMOTE. A balanced random forest randomly under-samples each bootstrap sample to balance it [23]. Prediction models were developed by applying a training dataset to each algorithm.
Hyperparameter tuning and cross-validation using RandomSearchCV were conducted to obtain the models with the best performance. RandomSearchCV is a random combination of selected hyperparameters used to train the model [24]. The hyperparameters used in RandomSearchCV are summarized in Listing A1 in Appendix A. We determined a strategy to evaluate the performance of the five-fold cross-validated model on the training set as the area under the receiver operating characteristic curve (AUROC). Subsequently, the best models for each algorithm were evaluated using a test set.
Additionally, we developed simplified models that included features known to be associated with PONV in adults, which included female sex, smoking status, age, volatile anesthetics, duration of anesthesia, postoperative opioid use, risky surgery (laparoscopic surgery and obstetric gynecologic surgery), and preventive antiemetics. Although most known risks or mitigation factors follow the Fourth Consensus Guidelines for the Management of Postoperative Nausea and Vomiting [9], some features were missing or insufficient. Postoperative opioid use was determined when opioids were used within 24 h after surgery. Preventive antiemetics were determined when antiemetics were used intraoperatively or in the PACU before the occurrence of PONV. As we did not have data associated with a history of PONV, or motion sickness, we added data regarding preoperative nausea and vomiting. For risky surgeries, we included only laparoscopic surgery and obstetric and gynecologic surgery because we did not have data on cholecystectomy and bariatric surgery.
To obtain the feature importance, we used mutual information, which quantifies the dependency or association between two random variables. In the context of feature importance, mutual information is used to measure the amount of information gained regarding a target variable by knowing the value of a particular feature. This is a method to assess the relevance of a feature in predicting a target variable [25].

2.7. Statistics

Descriptive analyses were performed to compare the characteristics and perioperative data of the training and test sets. Categorical features were presented as numbers and percentages, and continuous features were presented as medians and interquartile ranges. The differences were evaluated as absolute standardized differences. Five metrics were calculated to assess the model performance; the AUROC was used as the primary metric, as well as recall, precision, f1-score, and accuracy. Bootstrapping (n = 1000) was performed to calculate 95% confidence intervals (CI). Python (version 3.7; PSF, Beaverton, OR, USA) was used to calculate the model metrics.

3. Results

A total of 149,802 patients underwent surgery under general anesthesia from 1 January 2013 to 30 April 2023. After 42,942 patients were excluded, data of 106,860 patients were divided into training (n = 84,888) and test (n = 21,372) sets. Details are summarized in Figure 1. The numbers of PONV cases were 12,287 (14.5%) and 3072 (14.4%) in the training and test sets, respectively. Patient characteristics and perioperative data are summarized in Table 1 and Table 2, respectively. The absolute standardized difference between the training and test sets was below 0.1 for all features.
Figure 1. Flow chart.
Table 1. Characteristics data of patients.
Table 2. Perioperative data of patients.

3.1. Performance of Models, including All Features

Figure 2 shows the AUROC for each model according to the algorithm. Logistic regression (AUROC [95% CI] = 0.67 [0.66–0.68]) and balanced random forest (AUROC [95% CI] = 0.67 [0.66–0.68]) had the highest AUROC. Table 3 shows the precision, recall, accuracy, and f1 score of each model according to the algorithm. In terms of precision, light GBM was the highest (0.60, 95% CI: 0.57–0.63). In terms of recall, logistic regression was the highest (0.57, 95% CI: 0.55–0.59). In terms of accuracy, light GBM was the highest (0.87, 95% CI: 0.86–0.87). In terms of f1 score, the balanced random forest was the highest (0.42, 95% CI: 0.41–0.44).
Figure 2. The area under the receiver operating characteristic curve of each model according to algorithm when all features are included. Note: 95% confidence interval: logistic regression, 0.66–0.68; random forest, 0.62–0.63; light gradient boosting machine, 0.59–0.60; multilayer perceptron, 0.62–0.64; balanced random forest, 0.66–0.68.
Table 3. Precision, recall, accuracy, and f1 score of each model according to the algorithm.

3.2. Performance of Models, including 10 Known Risks and Mitigating Factors

Figure 3 shows the AUROC of the models, including the known risks and mitigating factors according to the algorithm. Balanced random forest (AUROC [95% CI] = 0.69 [0.68–0.70]) had the highest AUROC. Table 4 shows the precision, recall, accuracy, and f1 score of each model according to the algorithm. In terms of precision, light GBM was the highest (0.46, 95% CI: 0.42–0.49). In terms of recall, balanced random forest was the highest (0.71, 95% CI: 0.69–0.72). In terms of accuracy, light GBM was the highest (0.85, 95% CI: 0.85–0.86). In terms of the f1 score, the balanced random forest was the highest (0.39, 95% CI: 0.38–0.40).
Figure 3. The area under the receiver operating characteristic curve of models, including known risk and mitigating factors according to the algorithm Note: 95% confidence interval: logistic regression, 0.66–0.68; random forest, 0.60–0.61; light gradient boosting machine, 0.53–0.54; multilayer perceptron, 0.64–0.66; balanced random forest, 0.68–0.70.
Table 4. Precision, recall, accuracy, and f1 score of models, including known risk and mitigating factors according to the algorithm.

3.3. Feature Importance

Table 5 lists the top 20 most important features in the models. The female sex, smoking status, obstetric and gynecologic surgery, and factors associated with postoperative opioid use were included in the five models. The importance of all features is summarized in Table A1 in Appendix B.
Table 5. Top 20 importance features using mutual information according to model.
Table 6 shows the feature importance and score in the models that include 10 known risks and mitigating features. The female sex had the highest score in the three models (logistic regression, light gradient boosting machine, and balanced random forest), whereas postoperative opioids had the highest score in the two models (random forest and multilayer perceptron).
Table 6. Feature importance and score in models that include 10 known risks and mitigating features.
In this study, we developed PONV prediction models with machine learning using the characteristics and perioperative data of 84,888 patients. In the evaluation of models using data from 21,372 patients, the performance of the models showed that AUROC ranged from 0.6 to 0.67 when all features were included. When the known risk and mitigating factors were included, the AUROC ranged from 0.54 to 0.69.
Shim et al. recently reported the prediction of PONV using machine learning in patients undergoing intravenous PCA [26]. Their study included 2149 patients and used seven algorithms and 13 features. Despite the small size of their data compared with ours, their AUROC ranged from 0.576 to 0.686 and was 0.643 when only Apfel risk factors were used. Their AUROC values were similar to those obtained in our study. On the other hand, Xie et al. also reported the probability of PONV for PCA using machine learning. Although they included 2222 patients and 21 features, their best AUROC value was 0.947. However, because their study included only patients who received PCA and the PCA regimen was limited, their models could not predict all patients undergoing general anesthesia. Zhou et al. reported the prediction of early postoperative PONV using multiple machine-learning and deep-learning algorithms [27]. Their study included 2149 patients and used seven algorithms and 15 features. They also had a small amount of data, but the AUROC values of the models ranged from 0.611 to 0.732. Some models showed better performance than ours. However, their data were obtained 10–15 years ago, and there were no recent data. Therefore, their models do not reflect the recent situation of anesthesia and surgery.
To develop models that can be applied to most patients under general anesthesia as much as possible, the training of the models included data from over 80,000 patients from two hospitals and 102 features. Additionally, we developed brief models that included only 10 known risks and mitigating factors. These factors are general categories that medical staff investigate or apply to general anesthesia. However, no model with excellent performance included only the 10 known risks and mitigating factors. In addition, the performance of some metrics was worse than that of models that included all features. If the removed features contain crucial information related to the target variable, their removal can result in poor performance. In this case, the model may lack the information necessary to make accurate predictions [28].
In models that included all features, the most important features were associated with opioids or PCA. In our study, if simplified models were developed with the most important features, models would have no choice but to include only the biased types of data, such as opioids and PCA, and other risk factors for PONV would have been excluded from the models. Incorporating or transforming some features may be needed to improve performance and ease of use, such as incorporating variable factors associated with postoperative opioid use. Although feature elimination sometimes helps in understanding the data, reducing computational requirements, reducing the effect of the curse of dimensionality, and improving predictor performance [29], a larger and more representative dataset can lead to better generalization [30]. The selection and transformation of features should be performed carefully, considering the specific characteristics of the data and the problem at hand.
Upon analyzing the results of feature importance, certain features consistently emerge as influential across multiple models. For instance, female sex was the variable that consistently held a substantial influence in all models, suggesting that sex might play a significant role in PONV prediction. Similarly, smoking status was another significant factor across all models, indicating its relevance in predicting the risk of PONV. Interestingly, the variables associated with opioid use demonstrated significant importance across all models, suggesting a robust association between opioid administration and the likelihood of PONV, similar to the conventional prediction of PONV. Predictions using machine learning also underscore the need for cautious opioid management strategies to mitigate the risk of PONV.
The strengths of this study include its meticulous approach to model development by utilizing a substantial dataset of over 80,000 patients and incorporating a rich set of features. This emphasis on data quantity and feature diversity provides a robust foundation for predictive modeling. In addition, the development of comprehensive models incorporating a wide range of features and simplified models based on known risk and mitigating factors acknowledges the practical need for predictive tools that can be applied to most patients undergoing general anesthesia. The integration of artificial intelligence into such medical information creates a new opportunity to design and improve new systems beyond existing systems [31].
This study also has several limitations.
  • Our models acknowledged that including only known risk and mitigating factors did not exhibit strong performance and, in some cases, showed worse metrics than the models with all features. This limitation suggests that there may be unaccounted factors contributing to PONV that are not captured solely by known risks and mitigating factors.
  • Although our study included a substantial number of patients, data were obtained from only two hospitals. This may raise questions regarding the diversity of patient populations and medical practices, potentially affecting the generalizability of the models to other healthcare settings.
  • Some studies referenced for comparison had outdated data, which might not accurately reflect the current landscape of anesthesia and surgery. This emphasizes the importance of continuously updating the models based on recent data.
  • This study highlighted the challenges of feature selection and the potential impacts of excluding informative features. However, further insight into the specific criteria and methods used for feature selection would enhance the transparency of the model development process.

4. Conclusions

Our study offers a valuable contribution to the realm of predictive modeling for PONV in patients undergoing general anesthesia. However, the performance of models based solely on known risks and mitigating factors highlights the complexity of PONV prediction and the need to consider additional contributing variables. Furthermore, the origin of the dataset from two hospitals warrants cautious interpretation when considering its generalizability across diverse healthcare settings. Prediction of PONV can lead to a significant reduction in PONV incidence by personalizing anesthesia and medication plans, efficiently allocating resources, improving patient experience, and strengthening recovery protocols. This can benefit patients by minimizing discomfort as well as making healthcare delivery and resource utilization more efficient. However, improved usability and performance of the model are needed to make this a reality.

Author Contributions

Conceptualization, Y.-S.K. and J.-J.L.; methodology, J.-H.K. and Y.-S.K.; software, M.-G.K. and B.-R.C.; validation, Y.-S.K.; formal analysis, S.-M.H.; investigation, B.-R.C. and M.-G.K.; resources, J.-J.L. and S.-Y.L.; data curation, J.-H.K.; writing—original draft preparation, Y.-S.K. and J.-H.K.; writing—editing, all authors; visualization, J.-H.K.; supervision, J.-J.L. and S.-Y.L.; project administration, J.L and S.-M.H. All authors have read and agreed to the published version of the manuscript.

Funding

This research was supported by a grant from the Medical Data-Driven Hospital Support Project through the Korea Health Information Service (KHIS), funded by the Ministry of Health and Welfare, Republic of Korea.

Institutional Review Board Statement

This study was conducted in accordance with the Declaration of Helsinki and was approved by the Clinical Research Ethics Committee of Chuncheon Sacred Hospital (No. 2023-05-003).

Data Availability Statement

Restrictions apply to the data availability. Data were obtained from the Hallym Medical Center and made available from the clinical data warehouse with permission from the Hallym Medical Center.

Conflicts of Interest

The authors declare that this research was conducted in the absence of commercial or financial relationships that could be construed as potential conflict of interest.

Appendix A

Listing A1. Definition of hyperparameter search space for each algorithm.
 #Define the hyperparameter search space for each algorithm.
 param_dist_logreg = {
 ‘C’: [0.001, 0.01, 0.1, 1, 10, 100],
 ‘penalty’: [‘l1′, ‘l2′],
 ‘solver’: [‘liblinear’, ‘saga’],
 ‘max_iter’: [100, 200, 300, 500]
 }

 param_dist_rf = {
 ‘n_estimators’: [100, 200, 300, 500],
 ‘criterion’: [‘gini’, ‘entropy’],
 ‘max_depth’: [None, 5, 10, 20, 30],
 ‘min_samples_split’: [2, 5, 10],
 ‘min_samples_leaf’: [1, 2, 4],
 ‘class_weight’: [None, ‘balanced’, ‘balanced_subsample’]
 }

 param_dist_svm = {
 ‘C’: [0.001, 0.01, 0.1, 1, 10, 100],
 ‘kernel’: [‘linear,’ ‘poly, ‘ ‘rbf,’ ‘sigmoid’],
 ‘gamma’: [‘scale’, ‘auto’, 0.001, 0.01, 0.1, 1, 10, 100],
 }

 param_dist_lgbm = {
 ‘learning_rate’: [0.01, 0.1, 0.3],
 ‘n_estimators’: [100, 200, 300],
 ‘max_depth’: [3, 5, 7, −1],
 ‘num_leaves’: [31, 50, 100, 200],
 ‘subsample’: [0.8, 0.9, 1.0],
 ‘colsample_bytree’: [0.8, 0.9, 1.0],
 ‘reg_alpha’: [0, 0.01, 0.1],
 ‘reg_lambda’: [0, 0.01, 0.1]
 }

 param_dist_mlp = {
 ‘hidden_layer_sizes’: [(50,), (100,), (50, 50), (100, 50)],
 ‘activation’: [‘relu’, ‘logistic’],
 ‘solver’: [‘adam’, ‘sgd’],
 ‘learning_rate’: [‘constant, ‘ ‘invscaling, ‘ ‘adaptive’],
 ‘alpha’: [0.0001, 0.001, 0.01],
 ‘batch_size’: [16, 32, 64],
 ‘max_iter’: [100, 200, 300]
 }.

Appendix B

Table A1. Feature importance and score used mutual information in models that include all features.
Table A1. Feature importance and score used mutual information in models that include all features.
Logistic RegressionRandom ForestLight Gradient Boosting MachineMulti-Layer PerceptronBalanced Random Forest
FeatureScore FeatureScoreFeatureScoreFeatureScore FeatureScore
Age, year0.014329Age, year0.014209Age, year0.010966Age, year0.011432Age, year0.035396
Female0.150907Female0.133513Female0.09546Female0.057632Female0.109128
Body mass index0.010811Body mass index0.006313Body mass index0Body mass index0.007466Body mass index0.004668
Alcohol0.055069Alcohol0.039759Alcohol0.023542Alcohol0.019388Alcohol0.032532
Smoking0.063328Smoking0.068043Smoking0.043676Smoking0.025659Smoking0.052161
Congestive heart failure0.01305Congestive heart failure0.00061Congestive heart failure0.006554Congestive heart failure0.003448Congestive heart failure0.008212
Cardiac arrhythmias0.013201Cardiac arrhythmias0Cardiac arrhythmias0.000727Cardiac arrhythmias0Cardiac arrhythmias0.004049
Valvular disease0Valvular disease0Valvular disease0.000858Valvular disease0.004271Valvular disease0
Pulmonary circulation disorders0.001711Pulmonary circulation disorders0Pulmonary circulation disorders0Pulmonary circulation disorders0Pulmonary circulation disorders0.001633
Peripheral vascular disorders0.011444Peripheral vascular disorders0.002393Peripheral vascular disorders0.001461Peripheral vascular disorders0.002524Peripheral vascular disorders0
Hypertension uncomplicated0.035809Hypertension uncomplicated0.003582Hypertension uncomplicated0Hypertension uncomplicated0.011136Hypertension uncomplicated0.004505
Hypertension complicated0.022409Hypertension complicated0.010994Hypertension complicated0.004092Hypertension complicated0.004717Hypertension complicated0.004397
Paralysis0.004824Paralysis0Paralysis0Paralysis0Paralysis0.00206
Other neurological disorders0.007542Other neurological disorders0.00373Other neurological disorders7.43 × 10−5Other neurological disorders0Other neurological disorders0
Chronic pulmonary disease0.036637Chronic pulmonary disease0.003064Chronic pulmonary disease0Chronic pulmonary disease0Chronic pulmonary disease0.001339
Diabetes uncomplicated0.041356Diabetes uncomplicated0.009213Diabetes uncomplicated0.007142Diabetes uncomplicated0.001278Diabetes uncomplicated0.004796
Diabetes complicated0.032078Diabetes complicated0.011004Diabetes complicated0.00391Diabetes complicated0.009505Diabetes complicated0
Hypothyroidism0.002325Hypothyroidism0.005612Hypothyroidism0Hypothyroidism0.002583Hypothyroidism0.001331
Renal failure0.026439Renal failure0.008957Renal failure0Renal failure0.0061Renal failure0.00426
Liver disease0.022072Liver disease0.006019Liver disease0Liver disease0.002106Liver disease2.02 × 10−5
Peptic ulcer disease excluding bleeding0.011524Peptic ulcer disease excluding bleeding0Peptic ulcer disease excluding bleeding0.000322Peptic ulcer disease excluding bleeding0.002732Peptic ulcer disease excluding bleeding0.004694
AIDS/HIV0.004832AIDS/HIV0.004172AIDS/HIV0.004959AIDS/HIV0.002683AIDS/HIV0.00416
Lymphoma0Lymphoma0.001566Lymphoma0Lymphoma0Lymphoma0.000138
Metastatic cancer0.005225Metastatic cancer0Metastatic cancer0.002773Metastatic cancer0.000338Metastatic cancer0.012946
Solid tumor without metastasis0.021974Solid tumor without metastasis0.01209Solid tumor without metastasis0.001404Solid tumor without metastasis0.001608Solid tumor without metastasis0.00237
Rheumatoid arthritis/collagen vascular diseases0.00187Rheumatoid arthritis/collagen vascular diseases0Rheumatoid arthritis/collagen vascular diseases0Rheumatoid arthritis/collagen vascular diseases0Rheumatoid arthritis/collagen vascular diseases0.00218
Coagulopathy0Coagulopathy0Coagulopathy0.007293Coagulopathy0Coagulopathy0
Obesity0Obesity0Obesity0Obesity0Obesity0.000236
Weight loss0.003957Weight loss0Weight loss0.008786Weight loss0.002254Weight loss0
Fluid and electrolyte disorders0.00901Fluid and electrolyte disorders0.000449Fluid and electrolyte disorders0.004403Fluid and electrolyte disorders0.008499Fluid and electrolyte disorders0
Blood loss anemia0.000666Blood loss anemia0Blood loss anemia0Blood loss anemia0Blood loss anemia0.011309
Deficiency anemia0.016697Deficiency anemia0.004104Deficiency anemia0.00156Deficiency anemia0.009742Deficiency anemia0
Alcohol abuse0.013662Alcohol abuse0.007081Alcohol abuse0.008237Alcohol abuse0.008525Alcohol abuse0.000989
Drug abuse0.012531Drug abuse0Drug abuse0Drug abuse0.000605Drug abuse0.001179
Psychoses0Psychoses0.00376Psychoses0.003083Psychoses0.001452Psychoses0
Depression0.005406Depression0.005307Depression0.001237Depression0.001572Depression0
GERD0.024686GERD0GERD0GERD0.007851GERD0.001501
Migraine0.007358Migraine0Migraine0Migraine0.003449Migraine0.00197
Preoperative nausea and vomiting0Preoperative nausea and vomiting0Preoperative nausea and vomiting0.003574Preoperative nausea and vomiting0.005058Preoperative nausea and vomiting0.002056
Anesthesia time, hour0.008031Anesthesia time, hour0.038934Anesthesia time, hour0.030261Anesthesia time, hour0.000964Anesthesia time, hour0.072561
Operation time, hour0.008312Operation time, hour0.041784Operation time, hour0.031438Operation time, hour0.006119Operation time, hour0.063561
ASA PS 0.029379ASA PS 0.006369ASA PS 0.007577ASA PS 0.006162ASA PS0.026592
Emergency0.011446Emergency0.014109Emergency0.00387Emergency0.002443Emergency0.016669
Administered blood, mL0.007107Administered blood, mL0.01352Administered blood, mL0.001689Administered blood, mL0.004122Administered blood, mL0.018886
Administered Fluid, mL0.00746Administered Fluid, mL0.038842Administered Fluid, mL0.017722Administered Fluid, mL0.003735Administered Fluid, mL0.081544
Administered Urine, mL0.013733Administered Urine, mL0.045319Administered Urine, mL0.021812Administered Urine, mL0.002917Administered Urine, mL0.099572
Estimated blood loss, mL0.020982Estimated blood loss, mL0.032045Estimated blood loss, mL0.00701Estimated blood loss, mL0.002474Estimated blood loss, mL0.081764
Intraoperative PRC, unit0.002815Intraoperative PRC, unit0.008796Intraoperative PRC, unit0.009146Intraoperative PRC, unit0Intraoperative PRC, unit0.014102
Intraoperative FFP, unit0Intraoperative FFP, unit0.001007Intraoperative FFP, unit0.000711Intraoperative FFP, unit0Intraoperative FFP, unit0.001156
Intraoperative PC, unit0.005476Intraoperative PC, unit0Intraoperative PC, unit0.000244Intraoperative PC, unit0Intraoperative PC, unit0.000352
A-line0.000496A-line0.019047A-line0.002371A-line0.005451A-line0.069996
C-line0.005401C-line0.00958C-line0C-line0.003437C-line0.036275
Foley0.008587Foley0.022761Foley0.002563Foley0.005108Foley0.059241
Nasogastric tube0Nasogastric tube0.004042Nasogastric tube0.002305Nasogastric tube0.000118Nasogastric tube0
Fasting time, hour0.005584Fasting time, hour0.003814Fasting time, hour0.00098Fasting time, hour0.002977Fasting time, hour0.012837
Induction drug0Induction drug0.013387Induction drug0.000604Induction drug0.003543Induction drug0
Maintenance agent0.007787Maintenance agent0.013547Maintenance agent0.008142Maintenance agent0.010943Maintenance agent0.010467
N2O0.024304N2O0.011115N2O0.007055N2O0.001988N2O0.008418
First intraoperative antiemetics 0.016601First intraoperative antiemetics 0.007223First intraoperative antiemetics 0.00875First intraoperative antiemetics 0.004457First intraoperative antiemetics 0.014732
Second intraoperative antiemetics 0.004754Second intraoperative antiemetics 0.0051Second intraoperative antiemetics 0.002218Second intraoperative antiemetics 0Second intraoperative antiemetics 0.001557
Type of PCA0.098404Type of PCA0.162091Type of PCA0.122345Type of PCA0.061605Type of PCA0.439285
Total PCA dose, mg0.122888Total PCA dose, mg0.190948Total PCA dose, mg0.145924Total PCA dose, mg0.078757Total PCA dose, mg0.481962
PCA flow (mg/h)0.114928PCA flow (mg/h)0.182959PCA flow (mg/h)0.145486PCA flow (mg/h)0.066347PCA flow (mg/h)0.480247
Antiemetics of PCA0.092322Antiemetics of PCA0.167905Antiemetics of PCA0.130546Antiemetics of PCA0.061012Antiemetics of PCA0.434438
Opioid dose at PACU, mg0Opioid dose at PACU, mg0.003604Opioid dose at PACU, mg0.011924Opioid dose at PACU, mg0Opioid dose at PACU, mg0.012209
Preventive antiemetics in PACU0.028454Preventive antiemetics in PACU0.069763Preventive antiemetics in PACU0.091715Preventive antiemetics in PACU0.044332Preventive antiemetics in PACU0.117608
O2 supply within 24 h after surgery0.011319O2 supply within 24 h after surgery0.014543O2 supply within 24 h after surgery0.000974O2 supply within 24 h after surgery0.00047O2 supply within 24 h after surgery0.041406
Frequency of postoperative opioid rescue except for TDFP0.001584Frequency of postoperative opioid rescue except for TDFP0.011442Frequency of postoperative opioid rescue except for TDFP0.010494Frequency of postoperative opioid rescue except for TDFP0.008148Frequency of postoperative opioid rescue except for TDFP0.033191
Dose of postoperative opioid rescue except for TDFP, mg0.006859Dose of postoperative opioid rescue except for TDFP, mg0.020091Dose of postoperative opioid rescue except for TDFP, mg0.00501Dose of postoperative opioid rescue except for TDFP, mg0Dose of postoperative opioid rescue except for TDFP, mg0.044087
Postoperative TDFP within 24 h after surgery (μg/h)0Postoperative TDFP within 24 h after surgery (μg/h)0Postoperative TDFP within 24 h after surgery (μg/h)0.004694Postoperative TDFP within 24 h after surgery (μg/h)0.011601Postoperative TDFP within 24 h after surgery (μg/h)0.00893
Intraoperative continuous infusion dose of propofol0.009027Intraoperative continuous infusion dose of propofol0.003551Intraoperative continuous infusion dose of propofol0.003871Intraoperative continuous infusion dose of propofol0.012563Intraoperative continuous infusion dose of propofol0.002748
Intraoperative injection dose of propofol, mg0.031009Intraoperative injection dose of propofol, mg0.040009Intraoperative injection dose of propofol, mg0.035606Intraoperative injection dose of propofol, mg0.020658Intraoperative injection dose of propofol, mg0.042206
Intraoperative dose of etomidate, mg0.003061Intraoperative dose of etomidate, mg0.012007Intraoperative dose of etomidate, mg0.001926Intraoperative dose of etomidate, mg0.001963Intraoperative dose of etomidate, mg0
Intraoperative dose of ketamine, mg0Intraoperative dose of ketamine, mg0.012963Intraoperative dose of ketamine, mg0Intraoperative dose of ketamine, mg0.007965Intraoperative dose of ketamine, mg0
Intraoperative dose of thiopental sodium, mg0Intraoperative dose of thiopental sodium, mg0.009748Intraoperative dose of thiopental sodium, mg0Intraoperative dose of thiopental sodium, mg0.00023Intraoperative dose of thiopental sodium, mg0
Intraoperative dose of dexmedetomidine, mg0.003159Intraoperative dose of dexmedetomidine, mg0.001652Intraoperative dose of dexmedetomidine, mg0Intraoperative dose of dexmedetomidine, mg0Intraoperative dose of dexmedetomidine, mg0.010115
Intraoperative dose of fentanyl, μg0.139895Intraoperative dose of fentanyl, μg0.206067Intraoperative dose of fentanyl, μg0.167898Intraoperative dose of fentanyl, μg0.080612Intraoperative dose of fentanyl, μg0.493458
Intraoperative dose of alfentanil, mg0.007663Intraoperative dose of alfentanil, mg0.010001Intraoperative dose of alfentanil, mg0.011716Intraoperative dose of alfentanil, mg0Intraoperative dose of alfentanil, mg0.03767
Intraoperative dose of sufentanil, mg0Intraoperative dose of sufentanil, mg0.004908Intraoperative dose of sufentanil, mg0.005716Intraoperative dose of sufentanil, mg0.00315Intraoperative dose of sufentanil, mg0.00679
Intraoperative dose of pethidine, mg0.002121Intraoperative dose of pethidine, mg0Intraoperative dose of pethidine, mg0.001803Intraoperative dose of pethidine, mg0Intraoperative dose of pethidine, mg0.009948
Intraoperative dose of morphine, mg0Intraoperative dose of morphine, mg0Intraoperative dose of morphine, mg0Intraoperative dose of morphine, mg0.000745Intraoperative dose of morphine, mg0
Intraoperative dose of neostigmine, mg0.011668Intraoperative dose of neostigmine, mg0Intraoperative dose of neostigmine, mg0.005509Intraoperative dose of neostigmine, mg0.003925Intraoperative dose of neostigmine, mg0.006208
Intraoperative dose of pyridostigmine, mg0.015152Intraoperative dose of pyridostigmine, mg0.007306Intraoperative dose of pyridostigmine, mg0.006987Intraoperative dose of pyridostigmine, mg0.007709Intraoperative dose of pyridostigmine, mg0.01198
Intraoperative dose of sugammadex, mg0.004219Intraoperative dose of sugammadex, mg0.002466Intraoperative dose of sugammadex, mg0.007416Intraoperative dose of sugammadex, mg0.005625Intraoperative dose of sugammadex, mg0.006301
Robotic surgery0.010594Robotic surgery0.009638Robotic surgery0.011253Robotic surgery0.002059Robotic surgery0.020797
Laparoscopic surgery0.005243Laparoscopic surgery0.001475Laparoscopic surgery0.00509Laparoscopic surgery0.006372Laparoscopic surgery0.08291
heart surgery0.001553heart surgery0heart surgery0.003475heart surgery0heart surgery0.002751
Abdomen surgery0Abdomen surgery0.006568Abdomen surgery0.000849Abdomen surgery9.77 × 10−6Abdomen surgery0.064653
Breast surgery0.015245Breast surgery0.008716Breast surgery0.00424Breast surgery0.003715Breast surgery0.026665
Ear surgery0.000189Ear surgery0.003594Ear surgery0Ear surgery0Ear surgery0.014613
Endocrinologic surgery0.007103Endocrinologic surgery0Endocrinologic surgery0.007086Endocrinologic surgery0.001702Endocrinologic surgery0.01862
Eye surgery0.003236Eye surgery0Eye surgery0.002919Eye surgery0.001273Eye surgery0.003301
Head and neck surgery0.032772Head and neck surgery0.028516Head and neck surgery0.028426Head and neck surgery0.018761Head and neck surgery0.088718
Musculoskeletal surgery0.016588Musculoskeletal surgery0.022552Musculoskeletal surgery0.00291Musculoskeletal surgery0.00477Musculoskeletal surgery0.044453
Neurosurgery0.004762Neurosurgery0.002645Neurosurgery0.002558Neurosurgery0Neurosurgery0.006022
Obstetric and gynecologic surgery0.056Obstetric and gynecologic surgery0.038353Obstetric and gynecologic surgery0.037278Obstetric and gynecologic surgery0.025596Obstetric and gynecologic surgery0.094796
Spine surgery0.001873Spine surgery0.008075Spine surgery0.00383Spine surgery0.001408Spine surgery0.001849
Thoracic surgery0.006697Thoracic surgery0Thoracic surgery0.003808Thoracic surgery0Thoracic surgery0.004475
Transplantation surgery0Transplantation surgery0Transplantation surgery0Transplantation surgery0.000324Transplantation surgery0.000534
Urogenital surgery0.018391Urogenital surgery0.018924Urogenital surgery0.005083Urogenital surgery0.010378Urogenital surgery0.045068
Vascular surgery0.010679Vascular surgery0.004212Vascular surgery0Vascular surgery0Vascular surgery0.000859
Skin and soft tissue surgery0.010685Skin and soft tissue surgery0Skin and soft tissue surgery0.00063Skin and soft tissue surgery0.003378Skin and soft tissue surgery0.008169
Other surgery0.00544Other surgery0.010513Other surgery0Other surgery0.006076Other surgery0

References

  1. Apipan, B.; Rummasak, D.; Wongsirichat, N. Postoperative nausea and vomiting after general anesthesia for oral and maxillofacial surgery. J. Dent. Anesth. Pain Med. 2016, 16, 273–281. [Google Scholar] [CrossRef] [PubMed]
  2. Pierre, S.; Whelan, R. Nausea and vomiting after surgery. Contin. Educ. Anaesth. Crit. Care Pain 2012, 13, 28–32. [Google Scholar] [CrossRef]
  3. Shaikh, S.I.; Nagarekha, D.; Hegade, G.; Marutheesh, M. Postoperative nausea and vomiting: A simple yet complex problem. Anesth. Essays Res. 2016, 10, 388–396. [Google Scholar] [CrossRef] [PubMed]
  4. Silva, A.C.; O’Ryan, F.; Poor, D.B. Postoperative nausea and vomiting (PONV) after orthognathic surgery: A retrospective study and literature review. J. Oral Maxillofac. Surg. 2006, 64, 1385–1397. [Google Scholar] [CrossRef] [PubMed]
  5. Chatterjee, S.; Rudra, A.; Sengupta, S. Current concepts in the management of postoperative nausea and vomiting. Anesthesiol. Res. Pract. 2011, 2011, 748031. [Google Scholar] [CrossRef] [PubMed]
  6. Sizemore, D.C.; Singh, A.; Dua, A.; Singh, K.; Grose, B.W. Postoperative Nausea. In StatPearls; StatPearls Publishing: Treasure Island, FL, USA, 2023. [Google Scholar]
  7. Elvir-Lazo, O.L.; White, P.F.; Yumul, R.; Cruz Eng, H. Management strategies for the treatment and prevention of postoperative/postdischarge nausea and vomiting: An updated review. F1000Research 2020, 9, 983. [Google Scholar] [CrossRef] [PubMed]
  8. Postoperative Nausea and Vomiting. Available online: https://www.uptodate.com/contents/postoperative-nausea-and-vomiting (accessed on 19 August 2023).
  9. Gan, T.J.; Belani, K.G.; Bergese, S.; Chung, F.; Diemunsch, P.; Habib, A.S.; Jin, Z.; Kovac, A.L.; Meyer, T.A.; Urman, R.D.; et al. Fourth Consensus Guidelines for the Management of Postoperative Nausea and Vomiting. Anesth. Analg. 2020, 131, 411–448. [Google Scholar] [CrossRef] [PubMed]
  10. Andrew, B.Y.; Habib, A.S.; Taicher, B.M. The Association of Guideline-Directed Prophylaxis with Postoperative Nausea and Vomiting in Pediatric Patients: A Single-Center, Retrospective Cohort Study. Anesth. Analg. 2023; in press. [Google Scholar]
  11. Habehh, H.; Gohel, S. Machine Learning in Healthcare. Curr. Genom. 2021, 22, 291–300. [Google Scholar] [CrossRef]
  12. Javaid, M.; Haleem, A.; Pratap Singh, R.; Suman, R.; Rab, S. Significance of machine learning in healthcare: Features, pillars and applications. Int. J. Intell. Netw. 2022, 3, 58–73. [Google Scholar] [CrossRef]
  13. El-Sherbini, A.H.; Hassan Virk, H.U.; Wang, Z.; Glicksberg, B.S.; Krittanawong, C. Machine-Learning-Based Prediction Modelling in Primary Care: State-of-the-Art Review. AI 2023, 4, 437–460. [Google Scholar] [CrossRef]
  14. Merath, K.; Hyer, J.M.; Mehta, R.; Farooq, A.; Bagante, F.; Sahara, K.; Tsilimigras, D.I.; Beal, E.; Paredes, A.Z.; Wu, L.; et al. Use of Machine Learning for Prediction of Patient Risk of Postoperative Complications After Liver, Pancreatic, and Colorectal Surgery. J. Gastrointest. Surg. 2020, 24, 1843–1851. [Google Scholar] [CrossRef] [PubMed]
  15. Sklearn Preprocessing Standard Scaler. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html (accessed on 19 August 2023).
  16. Tyagi, S.; Mittal, S. Sampling approaches for imbalanced data classification problem in machine learning. In Proceedings of the ICRIC 2019: Recent Innovations in Computing, Jammu, India, 8–9 March 2020; pp. 209–221. [Google Scholar]
  17. Chawla, N.V.; Bowyer, K.W.; Hall, L.O.; Kegelmeyer, W.P. SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 2002, 16, 321–357. [Google Scholar] [CrossRef]
  18. Light GBM. Available online: https://lightgbm.readthedocs.io/en/v3.3.2/ (accessed on 30 January 2023).
  19. Sklearn Neural_Network MLP Classifier. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html (accessed on 30 January 2023).
  20. sklearn.linear_model.LogisticRegression. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html (accessed on 30 January 2023).
  21. Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
  22. Yağcı, A.M.; Aytekin, T.; Gürgen, F.S. Balanced random forest for imbalanced data streams. In Proceedings of the 2016 24th Signal Processing and Communication Application Conference (SIU), Zonguldak, Turkey, 16–19 May 2016; pp. 1065–1068. [Google Scholar]
  23. BalancedRandomForestClassifier. Available online: https://imbalanced-learn.org/stable/references/generated/imblearn.ensemble.BalancedRandomForestClassifier.html (accessed on 19 August 2023).
  24. Putri, T.A.E.; Widiharih, T.; Santoso, R. Penerapan Tuning Hyperparameter Randomsearchcv Pada Adaptive Boosting Untuk Prediksi Kelangsungan Hidup Pasien Gagal Jantung. J. Gaussian 2023, 11, 397–406. [Google Scholar] [CrossRef]
  25. Barraza, N.; Moro, S.; Ferreyra, M.; de la Peña, A. Mutual information and sensitivity analysis for feature selection in customer targeting: A comparative study. J. Inf. Sci. 2019, 45, 53–67. [Google Scholar] [CrossRef]
  26. Shim, J.-G.; Ryu, K.-H.; Cho, E.-A.; Ahn, J.H.; Cha, Y.B.; Lim, G.; Lee, S.H. Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia. PLoS ONE 2022, 17, e0277957. [Google Scholar] [CrossRef] [PubMed]
  27. Zhou, C.-M.; Wang, Y.; Xue, Q.; Yang, J.-J.; Zhu, Y. Predicting early postoperative PONV using multiple machine-learning- and deep-learning-algorithms. BMC Med. Res. Methodol. 2023, 23, 133. [Google Scholar] [CrossRef] [PubMed]
  28. Steyerberg, E.W.; Uno, H.; Ioannidis, J.P.A.; van Calster, B. Poor performance of clinical prediction models: The harm of commonly applied methods. J. Clin. Epidemiol. 2018, 98, 133–143. [Google Scholar] [CrossRef]
  29. Chandrashekar, G.; Sahin, F. A survey on feature selection methods. Comput. Electr. Eng. 2014, 40, 16–28. [Google Scholar] [CrossRef]
  30. Shorten, C.; Khoshgoftaar, T.M. A survey on Image Data Augmentation for Deep Learning. J. Big Data 2019, 6, 60. [Google Scholar] [CrossRef]
  31. Metha, S.; Chatterjee, A.N. An Investigation on the architecture of public health information system by using artificial intelligence. Seybold Rep. 2023, 18, 747–763. [Google Scholar]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Article Metrics

Citations

Article Access Statistics

Journal Statistics
Multiple requests from the same IP address are counted as one view.
Impact of Oral Administration of Lactiplantibacillus plantarum Strain CNCM I−4459 on Obesity Induced by High-Fat Diet in Mice
Previous
Microwave Breast Sensing via Deep Learning for Tumor Spatial Localization by Probability Maps
Next