[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117259-en":3,"doc-seo-117259-105":29,"detail-sidebar-cat-0-en-105":94},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},117259,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Forecasting Patient Early Readmission from Irish Hospital Discharge Records Using Conventional Machine Learning Models","Predicting patient readmission supports healthcare risk management by preventing adverse events, reducing costs, and improving outcomes. The study compares conventional machine learning models and deep learning models on a multimodal dataset of electronic discharge records from an Irish acute hospital, using demographics, hospitalization history, and clinical diagnosis codes. The work addresses data imbalance and mixed data types, and applies SHAP for explainable AI. Benchmarking and feature engineering increase AUROC from 0.628 to 0.7, highlighting diagnosis and social factors as key 30-day readmission predictors.","diagnostics  \nArticle  \nForecasting Patient Early Readmission from Irish Hospital Discharge Records Using Conventional Machine Learning Models  \nMinh-Khoi Pham 1,2, *, Tai Tan Mai 1,2, Martin Crane 1,2, Malick Ebiele 1,3, Rob Brennan 1,3, Marie E. Ward 4, Una Geary 4, Nick McDonald 5 and Marija Bezbradica 1,2  \nCitation: Pham, M.-K.; Mai, T.T.; Crane, M.; Ebiele, M.; Brennan, R.; Ward, M.E.; Geary, U.; McDonald, N.; Bezbradica, M. Forecasting Patient Early Readmission from Irish Hospital Discharge Records Using Conventional Machine Learning Models. Diagnostics 2024, 14, 2405 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics14212405  \nAcademic Editor: Jae-Ho Han  \nReceived: 24 August 2024  \nRevised: 27 September 2024  \nAccepted: 23 October 2024  \nPublished: 29 October 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 ADAPT Centre, D02 PN40 Dublin, Ireland; [tai.tanmai@dcu.ie](tai.tanmai@dcu.ie) (T.T.M.); [martin.crane@dcu.ie](martin.crane@dcu.ie) (M.C.);  \nmalick.ebiele@adaptcentre.ie (M.E.); [rob.brennan@ucd.ie](rob.brennan@ucd.ie) (R.B.); [marija.bezbradica@dcu.ie](marija.bezbradica@dcu.ie) (M.B.)  \n2 School of Computing, Dublin City University, D09 Y074 Dublin, Ireland  \n3 School of Computer Science, University College Dublin, D04 V1W8 Dublin, Ireland  \n4 St James’s Hospital, D08 NHY1 Dublin, Ireland; [maward@stjames.ie](maward@stjames.ie) (M.E.W.); [ugeary@stjames.ie](ugeary@stjames.ie) (U.G.)  \n5 School of Psychology, Trinity College Dublin, D02 F6N2 Dublin, Ireland; [nmcdonld@tcd.ie](nmcdonld@tcd.ie)  \n* [Correspondence: minhkhoi.pham@adaptcentre.ie](Correspondence: minhkhoi.pham@adaptcentre.ie)  \nAbstract: Background/Objectives: Predicting patient readmission is an important task for healthcare risk management, as it can help prevent adverse events, reduce costs, and improve patient outcomes. In this paper, we compare various conventional machine learning models and deep learning modelson a multimodal dataset of electronic discharge records from an Irish acute hospital. Methods: We evaluate the effectiveness of several widely used machine learning models that leverage patient demographics, historical hospitalization records, and clinical diagnosis codes to forecast future clinical risks. Our work focuses on addressing two key challenges in the medical fields, data imbalance and the variety of data types, in order to boost the performance of machine learning algorithms. Furthermore, we also employ SHapley Additive Explanations (SHAP) value visualization to interpret the model predictions and identify both the key data features and disease codes associated with readmission risks, identifying a specific set of diagnosis codes that are significant predictors of readmission within 30 days. Results: Through extensive benchmarking and the application of a variety of feature engineering techniques, we successfully improved the area under the curve (AUROC) score from 0.628 to 0.7 across our models on the test dataset. We also revealed that specific diagnoses, including cancer, COPD, and certain social factors, are significant predictors of 30-day readmission risk. Conversely, bacterial carrier status appeared to have minimal impact due to lowercase frequencies. Conclusions: Our study demonstrates how we effectively utilize routinely collected hospital data to forecast patient readmission through the use of conventional machine learning while applying explainable AI techniques to explore the correlation between data features and patient readmission rate.  \nKeywords: electronic patient records; multimodal deep learning; explainable AI  \n1. Introduction  \nEffective risk manag","cbCaieZSR7TLeg5V","https://ap.wps.com/l/cbCaieZSR7TLeg5V","pdf",804478,1,19,"English","en",105,"# Introduction\n## Readmission as a risk-management metric\n# Methods\n## Conventional vs deep learning models\n## Data sources and multimodal features\n## Model interpretation with SHAP\n# Results\n## AUROC improvement via feature engineering\n## Key diagnosis codes and risk factors\n# Conclusions\n## Forecasting with explainable conventional ML","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"Forecasting 30-day early patient readmission risk using routine Irish hospital discharge records and machine learning approaches.\"},{\"question\":\"Which data types are used to predict readmission?\",\"answer\":\"The models leverage patient demographics, historical hospitalization records, and clinical diagnosis codes from electronic discharge data.\"},{\"question\":\"How does the study interpret model predictions?\",\"answer\":\"It uses SHAP value visualization to identify key features and disease codes associated with readmission risk.\"},{\"question\":\"What performance improvement and key predictors are reported?\",\"answer\":\"AUROC increases from 0.628 to 0.7 after benchmarking and feature engineering, and specific diagnoses such as cancer and COPD are identified as significant predictors of 30-day readmission.\"}]",1785674762,48,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":89,"head_meta":91,"extra_data":93,"updated_unix":27},"forecasting-patient-early-readmission-from-irish-hospital-discharge-records-using-conventional-machine-learning-models","",{"@graph":35,"@context":88},[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/forecasting-patient-early-readmission-from-irish-hospital-discharge-records-using-conventional-machine-learning-models/117259/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"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","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80,84],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of the study?","Question",{"text":74,"@type":75},"Forecasting 30-day early patient readmission risk using routine Irish hospital discharge records and machine learning approaches.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which data types are used to predict readmission?",{"text":79,"@type":75},"The models leverage patient demographics, historical hospitalization records, and clinical diagnosis codes from electronic discharge data.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the study interpret model predictions?",{"text":83,"@type":75},"It uses SHAP value visualization to identify key features and disease codes associated with readmission risk.",{"name":85,"@type":72,"acceptedAnswer":86},"What performance improvement and key predictors are reported?",{"text":87,"@type":75},"AUROC increases from 0.628 to 0.7 after benchmarking and feature engineering, and specific diagnoses such as cancer and COPD are identified as significant predictors of 30-day readmission.","https://schema.org",{"og:url":51,"og:type":90,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":92,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":95},[96,100,104,108,113,118,123,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},"Exam",70,"exam",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},5,"Comic",60,"comic",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},6,"Technology",50,"technology",{"id":119,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":139,"show_sort_weight":109,"slug":140},"General","general"]