[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-456049-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-456049-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","regarding-prediction-of-postoperative-nausea-and-vomiting-in-patients-undergoing-sedated-gastrointestinal-endoscopy-based-on-machine-learning-letter-to-the-editor","Regarding - prediction of postoperative nausea and vomiting in patients undergoing sedated gastrointestinal endoscopy based on machine learning - letter to the editor","","Letter to the editor responding to a multicentre machine-learning study predicting postoperative nausea and vomiting after sedated gastrointestinal endoscopy. The authors commend model development, validation, interpretability via SHAP, and deployment of an online tool for precision risk assessment, while suggesting improvements: strengthen population diversity and predictor selection, include clinically important factors such as genetic susceptibility, sedation protocol details, and antiemetic prophylaxis/rescue pathways. They also request clearer explanations of model choice, overfitting risk, and stronger head-to-head comparisons against conventional tools, using consistent evaluation metrics.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/regarding-prediction-of-postoperative-nausea-and-vomiting-in-patients-undergoing-sedated-gastrointestinal-endoscopy-based-on-machine-learning-letter-to-the-editor/456049/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/regarding-prediction-of-postoperative-nausea-and-vomiting-in-patients-undergoing-sedated-gastrointestinal-endoscopy-based-on-machine-learning-letter-to-the-editor/456049.png","ImageObject",300,407,{"name":42,"@type":43},"Đào","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",7,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main purpose of the letter to the editor?","Question",{"text":63,"@type":64},"To provide comments on a multicentre machine-learning study that predicts postoperative nausea and vomiting after sedated gastrointestinal endoscopy, highlighting strengths and areas for improvement.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which additional predictors does the letter suggest incorporating?",{"text":68,"@type":64},"It recommends capturing clinically important factors such as genetic susceptibility (e.g., CYP2D6 polymorphisms), intraoperative antiemetic prophylaxis, and granular anaesthetic details including agents, doses, sedation strategy, and opioid use.",{"name":70,"@type":61,"acceptedAnswer":71},"What comparison improvements does the letter request for stronger impact?",{"text":72,"@type":64},"It calls for head-to-head benchmarking against widely used conventional tools (e.g., the simplified Apfel score) and additional discussion of why LDA was optimal, including overfitting risk and comparisons with non-linear or deep-learning approaches.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},456049,1790814787,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,109,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":107,"slug":108},40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":26,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":97,"preview_page_count":4},1374402968488,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","AnnAls of Medicine  \n2026, Vol. 58, no. 1, 2611193 [https://doi.org/10.1080/07853890.2025.261](https://doi.org/10.1080/07853890.2025.261)1193  \nLETTER TO THE EDITOR     \nRegarding: ‘prediction of postoperative nausea and vomiting in patients undergoing sedated gastrointestinal endoscopy based on machine learning’  \nWe read with considerable interest the multicentre study by Yao and colleagues that applied machine-learning approaches to predict postoperative nausea and vomiting (PONV) after sedated gastrointestinal endoscopy [1] . By developing and validating 11 models, selecting an LDA model with favourable generalisability, leveraging SHAP to enhance interpretability, and deploying an online prediction tool, the authors provide a potentially useful strategy for precision risk assessment and more individualised perioperative management.  \nFirst, the diversity of the study population and the selection/definition of predictors could be further strengthened. The external validation cohort was derived exclusively from hospitals within the same geographic region in China, which may limit transportability across populations with different ethnic backgrounds, healthcare resources, and perioperative practice patterns [2] . In addition, several clinically important predictors were not captured, including genetic susceptibility (e.g. CYP2D6 polymorphisms associated with PONV vulnerability), intraoperative antiemetic prophylaxis, and granular anaesthetic details (specific agents and doses) . This is particularly relevant in sedated endoscopy, where PONV risk is strongly influenced by sedation strategy and medication choices (e.g. propofol vs remimazolam selection and dosing, concomitant opioid use and dose, sedation depth and bolus patterns), as well as by prophylactic and rescue antiemetic use—factors that may act as strong confounders and materially affect model portability across centres [3,4] . We suggest that the authors, at minimum, provide a structured description of sedation protocols and antiemetic prevention/rescue pathways (indications, drug classes/doses, and timing) . Where data permit, incorporating key medication variables into modelling or performing sensitivity analyses (with vs without antiemetic-related variables, comparing discrimination and calibration) would help clarify whether the model estimates ‘intrinsic/natural’ risk or the residual risk under a specific prophylaxis strategy, thereby improving interpretability and clinical usability.  \nSecond, deeper and more clinically anchored model comparisons would enhance the manuscript’s impact. Because the evaluation did not include head-to-head benchmarking against widely used conventional tools (e.g. the simplified Apfel score), it remains difficult to quantify incremental value in predictive performance, operational simplicity, and personalised adaptability—areas where traditional scores often have advantagesin uptake and workflow feasibility [5] . We recommend direct comparisons using consistent metrics (e.g. AUC, calibration, and—where feasible—time burden and user acceptability) to delineate the model’s competitive strengths and its appropriate boundary of use. Moreover, additional discussion is warranted regarding why LDA emerged as the ‘optimal’ model given the potentially complex and non-linear relationships in clinical data, alongside clearer assessment of overfitting risk and benchmarking against non-linear/deep-learning approaches in the same task.  \nIn summary, this work introduces an interpretable, web-deployable ML-based model for PONV risk prediction after sedated gastrointestinal endoscopy, with meaningful innovation and translational potential. Further improvements in population diversity, inclusion and clarification of key perioperative medication variables, and more rigorous comparisons with established clinical tools would likely strengthen generalisability, scientific robustness, and real-world applicability.  \nAuthors contributions  \nCRediT: Chenh","cbCail68k4x1Br7Z","https://ap.wps.com/l/cbCail68k4x1Br7Z","pdf",119201,"English","# Letter to the Editor\n## Model development, validation, and interpretability\n## Strengthening predictors and external generalisability\n## Clinically anchored comparisons and benchmarking\n## Summary and authors’ contributions","[{\"question\":\"What is the main purpose of the letter to the editor?\",\"answer\":\"To provide comments on a multicentre machine-learning study that predicts postoperative nausea and vomiting after sedated gastrointestinal endoscopy, highlighting strengths and areas for improvement.\"},{\"question\":\"Which additional predictors does the letter suggest incorporating?\",\"answer\":\"It recommends capturing clinically important factors such as genetic susceptibility (e.g., CYP2D6 polymorphisms), intraoperative antiemetic prophylaxis, and granular anaesthetic details including agents, doses, sedation strategy, and opioid use.\"},{\"question\":\"What comparison improvements does the letter request for stronger impact?\",\"answer\":\"It calls for head-to-head benchmarking against widely used conventional tools (e.g., the simplified Apfel score) and additional discussion of why LDA was optimal, including overfitting risk and comparisons with non-linear or deep-learning approaches.\"}]","Regarding - prediction of postoperative nausea and vomiting in patients undergoing sedated gastrointestinal endoscopy based on machine learning - letter to the editor | PDF",1790745013]