[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118524-en":3,"doc-seo-118524-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118524,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Statistical models versus machine learning approach for competing risks in proctological surgery","Clinical risk prediction models are widely used across surgical care, traditionally built with regression techniques such as logistic regression. Machine learning is increasingly adopted as an alternative for prediction and classification because it can capture complex, non-linear associations and combine numerous variables. This study evaluated machine learning against classical logistic regression for preoperative risk assessment in proctological surgery using nationwide audit data from 1,510 patients with Goligher grade III hemorrhoidal disease. Ten predictors were assessed, and complication risk was measured at 30-day follow-up, with performance compared by AUC, balanced accuracy, sensitivity, and specificity; both approaches showed comparable predictive capability.","Updates in Surgery (2025) 77:333–341  \n[https://doi.org/10.1007/s13304-025-02109-0](https://doi.org/10.1007/s13304-025-02109-0)  \nStatistical models versus machine learning approach for competing risks in proctological surgery  \nLucia Romano1 · Andrea Manno2,3 · Fabrizio Rossi2 · Francesco Masedu1 · Margherita Attanasio1 · Fabio Vistoli1 · Antonio Giuliani1  \nReceived: 2 August 2024 / Accepted: 17 January 2025 / Published online: 25 January 2025 © The Author(s) 2025  \nAbstract  \nClinical risk prediction models are ubiquitous in many surgical domains. The traditional approach to develop these models involves the use of regression analysis. Machine learning algorithms are gaining in popularity as an alternative approach for prediction and classification problems. They can detect non-linear relationships between independent and dependent variablesand incorporate many of them. In our work, we aimed to investigate the potential role of machine learning versus classical logistic regression for the preoperative risk assessment in proctological surgery. We used clinical data from a nationwide audit: the database consisted of 1510 patients affected by Goligher’s grade III hemorrhoidal disease who underwent elective surgery. We collected anthropometric, clinical, and surgical data and we considered ten predictors to evaluate modelpredictive performance. The clinical outcome was the complication rate evaluated at 30-day follow-up. Logistic regression and three machine learning techniques (Decision Tree, Support Vector Machine, Extreme Gradient Boosting) were compared in terms of area under the curve, balanced accuracy, sensitivity, and specificity. In our setting, machine learning and logistic regression models reached an equivalent predictive performance. Regarding the relative importance of the input features, all models agreed in identifying the most important factor. Combining and comparing statistical analysis and machine learning approaches in clinical field should be a common ambition, focused on improving and expanding interdisciplinary cooperation.  \nKeywords Competing risks · Predictive performance · Logistic regression · Supervised machine learning  \nIntroduction  \nClinical risk prediction models are ubiquitous in many surgical domains. The traditional approach to develop these models involves the use of regression analysis, for example, logistic regression (LR) to predict disease outcomes (prognosis) after surgical interventions. Machine learning (ML) algorithms are gaining in popularity as an alternative approach for prediction and classification problems. In fact, advances in processing power and cloud storage have given clinicians access to increased amounts and types of data,  \n* Lucia Romano [lucia.romano1989@libero.it](lucia.romano1989@libero.it)  \n1 Department of Biotechnological and Applied Clinical Sciences, University of L’Aquila, L’Aquila, Italy  \n2 Department of Information Engineering, Computer Science and Mathematics, University of L’Aquila, L’Aquila, Italy  \n3 Center of Excellence DEWS, University of L’Aquila, L’Aquila, Italy  \nthat facilitated the utilization of artificial intelligence (AI) . ML is a component of AI; it relies on computer algorithmsand data analysis to learn patterns that exceeds the capacity of the human mind to comprehend [1] . They can detect non-linear relationships between independent and dependent variables and incorporate many of them [2, 3] . In clinical settings, for risk stratification of patients, various types of supervised machine learning algorithms have been used with large clinical databases.“Supervised” refers to the existence of a training set: in these algorithms, part of the data set (the“training” data set) is analyzed to build a model, and another part of the data set (the “testing” data set) is used to validate the model [4] .  \nAlthough both techniques (LR and ML) have been used to develop risk models for postoperative complications, it is unclear if machine learning is","cbCaimCn6uVK4jiR","https://ap.wps.com/l/cbCaimCn6uVK4jiR","pdf",900641,1,9,"English","en",105,"# Abstract\n# Introduction\n# Methods\n## Source of data\n## Participants","[{\"question\":\"What comparison did the study make between statistical modeling and machine learning?\",\"answer\":\"The study compared classical logistic regression with three supervised machine learning methods (Decision Tree, Support Vector Machine, and Extreme Gradient Boosting) for preoperative risk assessment.\"},{\"question\":\"What data and outcome were used to evaluate predictive performance?\",\"answer\":\"The analysis used nationwide audit clinical data from 1,510 patients with Goligher grade III hemorrhoidal disease, and the outcome was the complication rate assessed at 30-day follow-up.\"},{\"question\":\"How did the models perform in predicting complications?\",\"answer\":\"In this setting, machine learning and logistic regression achieved equivalent predictive performance, with all models agreeing on the most important input feature.\"}]","Statistical models versus machine learning approach for competing risks in proctological surgery | PDF",1785683979,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"statistical-models-versus-machine-learning-approach-for-competing-risks-in-proctological-surgery","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/statistical-models-versus-machine-learning-approach-for-competing-risks-in-proctological-surgery/118524/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What comparison did the study make between statistical modeling and machine learning?","Question",{"text":75,"@type":76},"The study compared classical logistic regression with three supervised machine learning methods (Decision Tree, Support Vector Machine, and Extreme Gradient Boosting) for preoperative risk assessment.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data and outcome were used to evaluate predictive performance?",{"text":80,"@type":76},"The analysis used nationwide audit clinical data from 1,510 patients with Goligher grade III hemorrhoidal disease, and the outcome was the complication rate assessed at 30-day follow-up.",{"name":82,"@type":73,"acceptedAnswer":83},"How did the models perform in predicting complications?",{"text":84,"@type":76},"In this setting, machine learning and logistic regression achieved equivalent predictive performance, with all models agreeing on the most important input feature.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]