[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119031-en":3,"doc-seo-119031-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},119031,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Machine Learning in Clinical Diagnosis of Head and Neck Cancer - Clinical Otolaryngology Original Article","Machine learning is applied to improve classification in head and neck cancer (HNC) pathways where malignancy detection rates are low and diagnostic pressure is high. This observational cohort study evaluates multiple models to predict diagnosis across three categories—benign, potential malignant, and malignant—using demographic and symptom questionnaire data from patients referred via the USOC pathway between January 2019 and May 2021. Ordinal logistic regression performs best after up-sampling, supported by reported AUC and balanced accuracy, and highlights living situation, drug use history, and neck lump as key variables.","Clinical Otolaryngology  \nORIGINAL ARTICLE  OPEN ACCESS   \nMachine Learning in Clinical Diagnosis of Head and Neck Cancer  \nHollie Black1  | David Young2  | Alexander Rogers3  | Jenny Montgomery3   \n1Department of Naval Architecture, Ocean and Marine Engineering, University of Strathclyde, Glasgow, UK | 2Department of Mathematics and Statistics, University of Strathclyde, Glasgow, UK | 3Department of Otolaryngology, Head and Neck Surgery, Queen Elizabeth University Hospital, Glasgow, UK Correspondence: Hollie Black ([hollie.black.2017@uni.strath.ac.uk](hollie.black.2017@uni.strath.ac.uk))  \nReceived: 21 September 2023 | Revised: 25 April 2024 | Accepted: 23 August 2024  \nFunding: The authors received no specific funding for this work.  \nKeywords: area under the receiver operator curve | head and neck cancer | machine learning | up-sampling  \nABSTRACT  \nObjective: Machine learning has been effective in other areas of medicine, this study aims to investigate this with regards to HNC and identify which algorithm works best to classify malignant patients.  \nDesign: An observational cohort study.  \nSetting: Queen Elizabeth University Hospital.  \nParticipants: Patients who were referred via the USOC pathway between January 2019 and May 2021.  \nMain Outcome Measures: Predicting the diagnosis of patients from three categories, benign, potential malignant and malignant, using demographics and symptoms data.  \nResults: The classic statistical method of ordinal logistic regression worked best on the data, achieving an AUC of 0.6697 and balanced accuracy of 0.641. The demographic features describing recreational drug use history and living situation were the most important variables alongside the red flag symptom of a neck lump.  \nConclusion: Further studies should aim to collect larger samples of malignant and pre-malignant patients to improve the class imbalance and increase the performance of the machine learning models.  \n1 | Introduction  \nCurrently the number of patients referred to Urgent Suspicion of Cancer (USOC) diagnostic clinics are rising. Less than 10% of people referred to these clinics are diagnosed with cancer [1] . Within the Head and Neck clinic, malignant diagnosis pick-up rates are even lower where the cancer pick-up rate is between 3% and 8%[2, 3] . This high volume of patients attending for diagnoses has created a significant burden on the USOC head and neck referral pathway, making it challenging to meet the 31-day diagnostic target created by the Scottish government.  \nThe head and neck risk calculator has created a classification system, which can identify the probability of a patient having cancer based on their demographics and symptoms. The study  \nobtained results with an AUC of 88.6%[4] . This study aims to review machine-learning models and identify whether these algorithms can better predict head and neck diagnosis of cancer, to support USOC clinics.  \n2 | Methodology  \n2.1 | Data  \nThere were 1045 patients eligible for inclusion in this observational cohort study. The reporting of this study adhered to the EQUATOR reporting guidelines for cohort studies. These patients were referred via the USOC pathway between January 2019 and May 2021. All patients included in the study agreed to anonymised  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2024 The Author(s). Clinical Otolaryngology published by John Wiley & Sons Ltd.  \nClinical Otolaryngology, 2025; 50:31–38 31  \n[https://doi.org/10.1111/coa.14220](https://doi.org/10.1111/coa.14220)  \nSummary  \n• This observational cohort study's aim is to identify the machine learning model which best predicts head and neck cancer, through factors such as demographics, red flag symptoms or associated symptoms.  \n• After up-sampling was conducted on the imbalanced dataset, the models evaluated were ordinal regress","cbCaivKYRodMIrPG","https://ap.wps.com/l/cbCaivKYRodMIrPG","pdf",223401,1,"English","en",105,"# Abstract\n# Introduction\n# Methodology\n## Data\n## Variables\n# Summary","[{\"question\":\"What is the main objective of the study on machine learning for HNC diagnosis?\",\"answer\":\"To determine which machine-learning algorithm best classifies patients into benign, potential malignant, or malignant groups using demographics and symptom data.\"},{\"question\":\"How were patients selected and what was the study design?\",\"answer\":\"The study used an observational cohort design including adults referred through the USOC pathway between January 2019 and May 2021, with exclusions for return patients, known active HNC, and non-completers of the questionnaire.\"},{\"question\":\"Which model performed best and which variables were most important?\",\"answer\":\"Ordinal logistic regression was the best-performing model after up-sampling. The most important variables were living situation, recreational drug use history, and the red flag symptom of a neck lump.\"}]","Machine Learning in Clinical Diagnosis of Head and Neck Cancer - Clinical Otolaryngology Original Article | PDF",1785722010,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"machine-learning-in-clinical-diagnosis-of-head-and-neck-cancer-clinical-otolaryngology-original-article","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-in-clinical-diagnosis-of-head-and-neck-cancer-clinical-otolaryngology-original-article/119031/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main objective of the study on machine learning for HNC diagnosis?","Question",{"text":74,"@type":75},"To determine which machine-learning algorithm best classifies patients into benign, potential malignant, or malignant groups using demographics and symptom data.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How were patients selected and what was the study design?",{"text":79,"@type":75},"The study used an observational cohort design including adults referred through the USOC pathway between January 2019 and May 2021, with exclusions for return patients, known active HNC, and non-completers of the questionnaire.",{"name":81,"@type":72,"acceptedAnswer":82},"Which model performed best and which variables were most important?",{"text":83,"@type":75},"Ordinal logistic regression was the best-performing model after up-sampling. The most important variables were living situation, recreational drug use history, and the red flag symptom of a neck lump.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]