[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128720-en":3,"doc-seo-128720-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128720,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine Learning Models Predicting Hospital Admissions During Chemotherapy - A Longitudinal Symptom Severity Study","Chemotherapy toxicity can trigger acute hospital admissions, straining healthcare resources and worsening patients’ well-being. This study builds four machine learning models to predict admission risk during chemotherapy using longitudinal symptom severity reports alongside patient-reported outcome measures (PROMs). The work targets both overall risk after a report and short-term risk within 14 days. Model comparisons show strong performance for admission prediction with balanced accuracy, recall, and specificity above 0.9 for random forest and extreme gradient boosting, while short-term predictions are weaker. PROMs enhance overall model effectiveness, supporting longitudinal collection of symptom severity and PROMs to elucidate toxicity patterns and inform clinicians and patients about potential future complications.","178  \nIntelligent Health Systems – From Technology to Data and Knowledge  \nE. Andrikopoulou et al. (Eds.)  \n© 2025 The Authors.  \nThis article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).  \ndoi:10.3233/SHTI250297  \nMachine Learning Models Predicting Hospital Admissions During Chemotherapy Utilising Longitudinal Symptom Severity Reports and PatientReported Outcome Measures  \nZuzanna WÓJCIKa,b, 1, Vania DIMITROVAb, Lorraine WARRINGTONc, Galina VELIKOVAc,d, Kate ABSOLOMc,e, and Samuel D. RELTONe  \na UKRI Centre for Doctoral Training in Artificial Intelligence for Medical Diagnosis and Care, University of Leeds, Leeds, UK b School of Computer Science, University of Leeds, UK c Leeds Institute of Medical Research, St James’s University Hospital, Leeds, UK d Leeds Cancer Centre, Leeds Teaching Hospitals NHS Trust, Leeds, UK e Leeds Institute of Health Sciences, Leeds, UK  \nORCiD ID: Zuzanna W´ojcik [https://orcid.org/0009-0007-6214-7736](https://orcid.org/0009-0007-6214-7736), Vania Dimitrova [https://orcid.org/0000-0002-7001-0891](https://orcid.org/0000-0002-7001-0891), Lorraine Warrington [https://orcid.org/0000-0002-8389-6134](https://orcid.org/0000-0002-8389-6134), Galina Velikova [https://orcid.org/0000-0003-](https://orcid.org/0000-0003-)  \n1899-5942, Kate Absolom  \n[https://orcid.org/0000-0002-5477-6643](https://orcid.org/0000-0002-5477-6643), Samuel D. Relton [https://orcid.org/0000-0003-](https://orcid.org/0000-0003-)  \n0634-4587  \nAbstract. Chemotherapy toxicity can lead to acute hospital admissions, negatively impacting the healthcare system and patients’well-being. Machine learning (ML) models identifying patients at risk of emergency admissions are often developed on data lacking patients’ perspective. This study used longitudinally collected symptom severity reports and 4 ML models to predict hospital admissions risk during chemotherapy, and short-term admissions risk (within 14 days of a report).  \nIt also compared performance of models developed with, and without the use of patient-reported outcome measures (PROMs). Random forest and extreme gradient boosting models predicted admissions with excellent balanced accuracy, recall, and specificity of over 0.9. However, short-term admissions risk predictions were poor.  \nPROMs improved overall model performance. The results advocate for longitudinal collection and use of symptom severity reports and PROMs. This can support understanding of chemotherapy toxicity patterns leading to emergency admissions,  \nand inform clinicians and patients of potential future complications.  \nKeywords. Patient-reported data, Hospital admissions predictions, ML  \n1 Corresponding Author: Zuzanna Wójcik; E-mail: [sczw@leeds.ac.uk](sczw@leeds.ac.uk).  \nZ. Wójcik et al. / Machine Learning Models Predicting Hospital Admissions 179  \n1. Introduction  \nEmergency hospital admissions resulting from chemotherapy toxicity can negatively impact patients’ quality of life (QoL) and the healthcare system. Machine learning (ML) has been successful in predicting acute hospitalisation during cancer treatment [1], which can help to identify patients at risk of severe chemotherapy toxicity, plan for emergency admissions, and inform treatment decisions.  \nNevertheless, studies predicting clinical outcomes often neglect patients’perspective and develop models using only clinical and demographic data. Our previous work has shown that including patient-reported outcome measures (PROMs), which capture patients’ QoL, improves model performance predicting emergency admissions [2]. However, the data were collected only at chemotherapy baseline.  \nSymptom severity reports are also patient-reported data, often collected longitudinally. They provide patients’ perspective on their health status throughout the duration of treatment. The patterns in longitudinal reports can be identified by ML models to predic","cbCaikLR0Fvq9Abn","https://ap.wps.com/l/cbCaikLR0Fvq9Abn","pdf",301757,2,1,5,"English","en",105,"# Introduction\n## Motivation and gap in patient perspective\n## Study aim\n# Methods\n## Overall methodology\n## Dataset and measures\n# Results and implications\n## Model performance and role of PROMs\n## Clinical relevance","[{\"question\":\"What hospital admission risks does the study aim to predict during chemotherapy?\",\"answer\":\"The study predicts admissions occurring at any time after a report and short-term admissions risk within 14 days of a report.\"},{\"question\":\"How does the study incorporate patient information into the machine learning models?\",\"answer\":\"It uses longitudinal symptom severity reports and compares model performance with and without patient-reported outcome measures (PROMs).\"},{\"question\":\"Which models performed best for predicting admissions, and what was the effect of PROMs?\",\"answer\":\"Random forest and extreme gradient boosting predicted admissions with balanced accuracy, recall, and specificity above 0.9, while short-term prediction was poor. PROMs improved overall model performance, supporting their added value.\"}]","Machine Learning Models Predicting Hospital Admissions During Chemotherapy - A Longitudinal Symptom Severity Study | PDF",1786002849,13,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-models-predicting-hospital-admissions-during-chemotherapy-a-longitudinal-symptom-severity-study","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/machine-learning-models-predicting-hospital-admissions-during-chemotherapy-a-longitudinal-symptom-severity-study/128720/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What hospital admission risks does the study aim to predict during chemotherapy?","Question",{"text":76,"@type":77},"The study predicts admissions occurring at any time after a report and short-term admissions risk within 14 days of a report.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the study incorporate patient information into the machine learning models?",{"text":81,"@type":77},"It uses longitudinal symptom severity reports and compares model performance with and without patient-reported outcome measures (PROMs).",{"name":83,"@type":74,"acceptedAnswer":84},"Which models performed best for predicting admissions, and what was the effect of PROMs?",{"text":85,"@type":77},"Random forest and extreme gradient boosting predicted admissions with balanced accuracy, recall, and specificity above 0.9, while short-term prediction was poor. PROMs improved overall model performance, supporting their added value.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":22,"slug":138},19,"General","general"]