Predicting postoperative nausea and vomiting with the application of an artificial neural network

Peng, Shih-Kuei; Wu, Keyi; Wang, J.J.; Chuang, Jen-Hsiang; Peng, Shih-Yen; Lai, Yuan

doi:10.1093/bja/ael282

Cited by 31 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The AUC for the final model was 0.734, which exceeds the commonly recognized threshold of 0.70 to be considered diagnostically useful 39 and compares favorably with commonly cited risk-scoring models [30][31][32][33][34][35][36] designed to predict PONV (range for AUCs: 0.61-0.70). In addition to having acceptable utility for predicting ORADEs, it is important for a risk score to be practicable in the clinical setting.…”

Section: Incidence Of Orade Overall and By Gendersupporting

confidence: 49%

“…[27][28][29] For example, Kooij et al (2008) found that including a simple risk-scoring system designed to identify patients with a high risk of experiencing postoperative nausea and vomiting (PONV) as part of the routine preoperative screening process significantly improved guideline adherence for prescribing PONV prophylaxis. 27 Several risk-scoring models, mainly for PONV, 11,[30][31][32][33][34][35][36][37] based on a patient's clinical/demographic profile have been developed with the goal of aiding health care providers in identifying high-risk patients and providing an opportunity to determine the safest and most effective pain management strategy. While evaluation of these models has focused primarily on their utility for predicting ADEs, very few have also considered whether the risk scores can transitively predict downstream outcomes such as increased costs and length of stay (LOS).…”

Section: Study Design and Sample Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Development and Validation of a Risk Score to Identify Patients at High Risk for Opioid-Related Adverse Drug Events

Minkowitz¹,

Scranton

Gruschkus

et al. 2014

JMCP

View full text Add to dashboard Cite

BACKGROUND: Opioid-related adverse drug events (ORADEs) are common causes of hospitalization and increased health care costs. OBJECTIVES: To (a) estimate rates of specific adverse drug events (ADEs) among gastrointestinal (GI) surgery patients receiving postoperative opioids; (b) examine the utility of a risk-scoring model in categorizing patients at high risk of experiencing ORADEs; and (c) quantify potential clinical/economic benefits of targeting high-risk GI surgical patients for opioid-sparing regimens in terms of hospitalization cost, length of stay (LOS), and 30-day readmission rates. METHODS: Using a retrospective design based on an administrative database, patients with an inpatient surgical procedure between January 1, 2010, and December 31, 2010, were included. GI surgical patients aged > 18 years followed from admission through 30 days postdischarge were characterized as high or low risk using clinical/demographic characteristics and were evaluated for several outcomes. Using multivariate logistic regression, the ORADE incidence, total hospitalization cost, LOS, and 30-day readmissions were compared for high-risk and low-risk patients. RESULTS: In 87.8% (n = 3,235) of the surgical population, there was a strong concordance between risk assignment and ORADE incidence. Among the remaining 12.2% (n = 449) of patients, 5.5% (n = 202) were low risk with an ORADE, and 6.7% (n = 247) were high risk without an ORADE. Overall, 20.6% (n = 344) of high-risk patients experienced ≥ 1 ORADE (mean cost: $31,988; LOS: 12.1 days) compared with only 5.3% (n = 107) of lowrisk patients (mean cost: $25,216; LOS: 8.0 days). High-risk patients had higher hospitalization costs and longer LOS than low-risk patients, respectively (mean cost: $19,234 vs. $13,036; mean LOS: 6.8 days vs. 3.3 days). These differences correspond to 47.0% higher costs for high-risk patients and an LOS approximately twice as long compared with low-risk patients. CONCLUSIONS: Patient clinical/demographic characteristics influence the risk of developing ORADEs. Risk assessment tools can effectively identify high-risk patients, thereby enabling interventions that can reduce ORADEs, decrease hospital costs, and improve postsurgical experiences for patients.

show abstract

Section: Incidence Of Orade Overall and By Gendersupporting

confidence: 49%

Section: Study Design and Sample Selectionmentioning

confidence: 99%

Development and Validation of a Risk Score to Identify Patients at High Risk for Opioid-Related Adverse Drug Events

Minkowitz¹,

Scranton

Gruschkus

et al. 2014

JMCP

View full text Add to dashboard Cite

show abstract

“…In recent years ANN has been widely applied in computer-aided diagnosis [7, 8], outcome prediction [9, 10], and signal processing [11, 12]. A good predictive model for postoperative nausea and vomiting (PONV) helps us do risk classification and management.…”

Section: Introductionmentioning

confidence: 99%

Predicting Postoperative Vomiting for Orthopedic Patients Receiving Patient-Controlled Epidural Analgesia with the Application of an Artificial Neural Network

Gong

Ting

et al. 2014

BioMed Research International

View full text Add to dashboard Cite

Patient-controlled epidural analgesia (PCEA) was used in many patients receiving orthopedic surgery to reduce postoperative pain but is accompanied with certain incidence of vomiting. Predictions of the vomiting event, however, were addressed by only a few authors using logistic regression (LR) models. Artificial neural networks (ANN) are pattern-recognition tools that can be used to detect complex patterns within data sets. The purpose of this study was to develop the ANN based predictive model to identify patients with high risk of vomiting during PCEA used. From January to March 2007, the PCEA records of 195 patients receiving PCEA after orthopedic surgery were used to develop the two predicting models. The ANN model had a largest area under curve (AUC) in receiver operating characteristic (ROC) curve. The areas under ROC curves of ANN and LR models were 0.900 and 0.761, respectively. The computer-based predictive model should be useful in increasing vigilance in those patients most at risk for vomiting while PCEA is used, allowing for patient-specific therapeutic intervention, or even in suggesting the use of alternative methods of analgesia.

show abstract

“…However, other studies indicated that there was no linear correlation between MS and HRV [7,8]. Yet, other studies suggested that the relationship between HRV and sympathovagal activities could be influenced by subjects' active adjustments [9,10].…”

Section: Introductionmentioning

confidence: 99%

Effect of respiratory modulation on relationship between heart rate variability and motion sickness

Lin

Chiu

et al. 2011

2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

This study investigates the interplay among heart rate variability (HRV), respiration, and the severity of motion sickness (MS) in a realistic passive driving task. Although HRV is a commonly used metrically in physiological research or even believed to be a direct measure of sympathovagal activities, the results of MS-effected HRV remain mixed across studies. The goal of this study is to find the source of these contradicting results of HRV associated with MS. Experimental results of this study showed that the group trend of the low-frequency (LF) component and the LF/HF ratio increased and high-frequency (HF) component decreased significantly as self-reported MS level increased (p<0.001), consistent with a perception-driven autonomic response of the cardiovascular system. However, in one of the subjects, the relationship was reversed when individuals intentionally adjust themselves (deep breathing) to relieve the discomfort of MS during the experiments. It appears that the correlations between HRV and MS level were higher when individuals made fewer adjustments (the number of deep breathing) during the passive driving experiments.

show abstract

Predicting postoperative nausea and vomiting with the application of an artificial neural network

Abstract: The ANN provided the best predictive performance among all tested models.

Cited by 31 publications

References 18 publications

Development and Validation of a Risk Score to Identify Patients at High Risk for Opioid-Related Adverse Drug Events

Development and Validation of a Risk Score to Identify Patients at High Risk for Opioid-Related Adverse Drug Events

Predicting Postoperative Vomiting for Orthopedic Patients Receiving Patient-Controlled Epidural Analgesia with the Application of an Artificial Neural Network

Effect of respiratory modulation on relationship between heart rate variability and motion sickness

Contact Info

Product

Resources

About