A Machine Learning Prediction Model for Delayed CIPONV

Postoperative Nausea and Vomiting Clinical Trial

Official title:

A Machine Learning-based Prediction Model for Delayed Clinically Important Postoperative Nausea and Vomiting in High-risk Patients Undergoing Laparoscopic Gastrointestinal Surgery

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT06443697
• Other study ID #: 2024ZSLYEC-202
• Status: Recruiting
• Start date: April 23, 2024
• Est. completion date: May 30, 2024

Study information

• Verified date: May 2024
• Source: Sixth Affiliated Hospital, Sun Yat-sen University
• Contact: Zhinan Zheng, MD
• Phone: 0086-15915734893
• Email: zhengzhn5[@]mail.sysu.edu.cn
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Postoperative nausea and vomiting (PONV) can lead to serious postoperative complications, but most symptoms are mild. Clinically important PONV (CIPONV) refers to PONV symptoms that have a significant impact on the patient's well-being and recovery. Present predictive systems for PONV are mainly concentrated on early PONV. However, there is currently no suitable prediction model for delayed PONV, particularly delayed CI-PONV. This study aims to develop and validate a prediction model for delayed CI-PONV using machine learning algorithms utilizing perioperative data from patients undergoing laparoscopic gastrointestinal surgery. All 1154 patients in the FDP-PONV trial will be enrolled in this study. Delayed CIPONV is defined as experiencing CIPONV between 25-120 hours after surgery. After selecting the modeling variables from 81 perioperative clinical features, six machine learning models are established to generate the risk prediction models for delayed CIPONV. The area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score and Brier score are used to evaluate the model performance. Shape Additive explanation analysis was conducted to evaluate feature importance.

Description:

The website https://mvansmeden.shinyapps.io/BeyondEPV/ was used for sample size calculation, considering 6 candidate predictors, an event fraction of 0.14, and a criterion value for reduced mean predictive squared error of 0.03. The calculated sample size is 1080, with a minimally required expected event per variable of 25.1. Therefore, a sample size of 1154 patients is deemed sufficient to support the inclusion of 6 predictors in the development of the predictive model. A total of 81 variables, including demographics, comorbidities, laboratory findings, as well as information related to anesthesia and surgery, are prospectively collected in the FDP-PONV trial and considered as potential predictive factors in this study. The least absolute shrinkage and selection operator method is used to identify clinically significant variables. Further selection of the final predictors is performed using stepwise regression based on the Akaike Information Criterion. The entire dataset is randomly divided into a training set and a validation set in a ratio of 7:3. Six machine learning models, namely logistic regression, random, extreme gradient boosting, k-nearest neighbor, gradient boosting decision, and multi-layer perceptron, were developed to create risk prediction models for delayed CIPONV. The performance of the models is assessed by comparing the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, Brier score and calibration curve. Bootstrap resamples is conducted 1000 times on the training cohort to evaluate the predictive model's performance. Decision curve analysis is conducted to assess the clinical applicability of the model. The SHapley Additive Explanations library (SHAP) is used to interpret the prediction model.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 1154
• Est. completion date: May 30, 2024
• Est. primary completion date: May 30, 2024
• Gender: All
• Age group: 18 Years to 75 Years

Eligibility

Inclusion Criteria:

a) age between 18 and 75 years, b) having 3 or 4 Apfel risk factors, and c) scheduled to undergo laparoscopic gastrointestinal surgical procedures under general anesthesia. Exclusion Criteria: a) American Society of Anesthesiologists (ASA) physical status greater than 3, b) severe hepatic dysfunction, c) contraindications to fosaprepitant, 5-HT3 receptor antagonist, or dexamethasone, d) preoperative use of medications known to have antiemetic properties, e) presence of mental disorders or inability to communicate, and f) pregnant or nursing women.

Related Conditions & MeSH terms

• Nausea
• Postoperative Nausea and Vomiting
• Vomiting

Intervention

Other:
• No intervention
This is a secondary analysis nested in a cohort of high-risk postoperative nausea and vomiting patients, and no intervention is implemented.

Locations

Country	Name	City	State
China	Department of Anesthesia, The Sixth Affiliated Hospital, Sun Yat-sen University	Guangzhou	Guangdong

Sponsors (1)

Lead Sponsor	Collaborator
Sixth Affiliated Hospital, Sun Yat-sen University

Country where clinical trial is conducted

China, 

References & Publications (10)

Apfel CC, Laara E, Koivuranta M, Greim CA, Roewer N. A simplified risk score for predicting postoperative nausea and vomiting: conclusions from cross-validations between two centers. Anesthesiology. 1999 Sep;91(3):693-700. doi: 10.1097/00000542-199909000-00022. — View Citation

Chow R, Navari RM, Terry B, DeAngelis C, Prsic EH. Olanzapine 5 mg vs 10 mg for the prophylaxis of chemotherapy-induced nausea and vomiting: a network meta-analysis. Support Care Cancer. 2022 Feb;30(2):1015-1018. doi: 10.1007/s00520-021-06606-x. No abstract available. — View Citation

Gan TJ, Gu J, Singla N, Chung F, Pearman MH, Bergese SD, Habib AS, Candiotti KA, Mo Y, Huyck S, Creed MR, Cantillon M; Rolapitant Investigation Group. Rolapitant for the prevention of postoperative nausea and vomiting: a prospective, double-blinded, placebo-controlled randomized trial. Anesth Analg. 2011 Apr;112(4):804-12. doi: 10.1213/ANE.0b013e31820886c3. Epub 2011 Mar 8. — View Citation

Hermans V, De Pooter F, De Groote F, De Hert S, Van der Linden P. Effect of dexamethasone on nausea, vomiting, and pain in paediatric tonsillectomy. Br J Anaesth. 2012 Sep;109(3):427-31. doi: 10.1093/bja/aes249. — View Citation

Mc Loughlin S, Terrasa SA, Ljungqvist O, Sanchez G, Garcia Fornari G, Alvarez AO. Nausea and vomiting in a colorectal ERAS program: Impact on nutritional recovery and the length of hospital stay. Clin Nutr ESPEN. 2019 Dec;34:73-80. doi: 10.1016/j.clnesp.2019.08.010. Epub 2019 Sep 11. — View Citation

Mraovic B, Simurina T. Effects of an intravenous lidocaine bolus before tracheal extubation on recovery after breast surgery - Lidocaine at the End (LATE) study: a randomized controlled clinical trial. Croat Med J. 2023 Aug 31;64(4):222-230. doi: 10.3325/cmj.2023.64.222. — View Citation

Myles PS, Wengritzky R. Simplified postoperative nausea and vomiting impact scale for audit and post-discharge review. Br J Anaesth. 2012 Mar;108(3):423-9. doi: 10.1093/bja/aer505. Epub 2012 Jan 29. — View Citation

Nino MC, Calle S, Ruiz D, Baron MA, Cohen D, Martinez JE, Benitez DS, Mejia JA, Guerra JD, Kattah L. Rethinking postoperative nausea and vomiting prevention beyond perioperative medications. J Clin Anesth. 2024 Aug;95:111457. doi: 10.1016/j.jclinane.2024.111457. Epub 2024 Mar 29. No abstract available. — View Citation

White PF, Sacan O, Nuangchamnong N, Sun T, Eng MR. The relationship between patient risk factors and early versus late postoperative emetic symptoms. Anesth Analg. 2008 Aug;107(2):459-63. doi: 10.1213/ane.0b013e31817aa6e4. — View Citation

Wu CL, Berenholtz SM, Pronovost PJ, Fleisher LA. Systematic review and analysis of postdischarge symptoms after outpatient surgery. Anesthesiology. 2002 Apr;96(4):994-1003. doi: 10.1097/00000542-200204000-00030. No abstract available. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Delayed clinically important postoperative nausea and vomiting	A postoperative nausea and vomiting severity score of = 5 based on the simplified postoperative nausea and vomiting impact scoring system, assessed between 25 and 120 hours after surgery.	Every 24 hours after surgery (at 2-day, 3-day, 4-day and 5-day)