[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122772-en":3,"doc-seo-122772-105":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":20,"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},122772,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine learning based readmission and mortality prediction in heart failure patients","Machine learning methods are used to predict in-hospital and 6-month mortality and to forecast 30-day and 90-day hospital readmission in heart failure patients. From 1101 cases, 737 patients remained after exclusions, with 34 conventional features collected per patient. Data are split 70/30, standardized via Z-score, and key features selected using Boruta, RFE, and MRMR. Eight ML models are trained with tenfold cross-validation and grid search, leaving holdout testing untouched.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning based readmission and mortality prediction in heart failure patients  \nMaziar Sabouri1,2,9, Ahmad Bitarafan Rajabi2,3,4,9, Ghasem Hajianfar2, Omid Gharibi1,2, Mobin Mohebi 5, Atlas HaddadiAvval6, Nasim Naderi2* & Isaac Shiri7,8*  \nThis study intends to predict in-hospital and 6-month mortality, as well as 30-day and 90-day hospital readmission, using Machine Learning (ML) approach via conventional features. A total of 737 patients remained after applying the exclusion criteria to 1101 heart failure patients. Thirty-four conventional features were collected for each patient. First, the data were divided into train and test cohorts with a 70–30% ratio. Then train data were normalized using the Z-score method, and its mean and standard deviation were applied to the test data. Subsequently, Boruta, RFE, and MRMR feature selection methods were utilized to select more important features in the training set. In the next step, eight ML approaches were used for modeling. Next, hyperparameters were optimized using tenfold crossvalidation and grid search in the train dataset. All model development steps (normalization, featureselection, and hyperparameter optimization) were performed on a train set without touching the holdout test set. Then, bootstrapping was done 1000 times on the hold-out test data. Finally, the obtained results were evaluated using four metrics: area under the ROC curve (AUC), accuracy (ACC), specificity (SPE), and sensitivity (SEN). The RFE-LR (AUC: 0.91, ACC: 0.84, SPE: 0.84, SEN: 0.83) and Boruta-LR (AUC: 0.90, ACC: 0.85, SPE: 0.85, SEN: 0.83) models generated the best results in terms of in-hospital  \nmortality. In terms of 30-day rehospitalization, Boruta-SVM (AUC: 0.73, ACC: 0.81, SPE: 0.85, SEN:  \n0.50) and MRMR-LR (AUC: 0.71, ACC: 0.68, SPE: 0.69, SEN: 0.63) models performed the best. The best  \nmodel for 3-month rehospitalization was MRMR-KNN (AUC: 0.60, ACC: 0.63, SPE: 0.66, SEN: 0.53) and regarding 6-month mortality, the MRMR-LR (AUC: 0.61, ACC: 0.63, SPE: 0.44, SEN: 0.66) and MRMR-NB (AUC: 0.59, ACC: 0.61, SPE: 0.48, SEN: 0.63) models outperformed the others. Reliable models were developed in 30-day rehospitalization and in-hospital mortality using conventional features and ML techniques. Such models can effectively personalize treatment, decision-making, and wiser budget allocation. Obtained results in 3-month rehospitalization and 6-month mortality endpoints were not astonishing and further experiments with additional information are needed to fetch promising results in these endpoints.  \nHeart Failure (HF) is the underlying cause of over one-third of cardiovascular deaths, with more than 64 million sufferers worldwide1. Acute Heart Failure (AHF) is a clinical condition caused when the myocardium function is either lost or exacerbated rapidly or quickly. As a result of this condition, the heart is often unable to sustain a sufficient cardiac output and meet metabolic demands. This condition puts patients’ quality of life, function, and lifespan at risk2,3.  \nHF is a common disorder that can increase in-hospital mortality4. Furthermore, AHF has 30-day and 1-year hospital readmission rates of 16–19% and 53%, respectively, as depicted in various trials5,6. In Khan et al.7 study, 6,669,313 and 5,077,949 HF rehospitalizations cases for 30 and 90 days were examined, and 18.2% and 31.2% were readmitted in each group, respectively. In a study by Fudim et al.8, patients who were readmitted within 30  \n1Department of Medical Physics, School of Medicine, Iran University of Medical Science, Tehran, Iran. 2Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran. 3Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran. 4Cardiovascular Interventional Research Center, Rajaie Cardiovascular Medical and ","cbCaiuYiNtuuk8dD","https://ap.wps.com/l/cbCaiuYiNtuuk8dD","pdf",8391751,1,13,"English","en",105,"# Predictive aims and cohort selection\n## Features and dataset preparation\n## Feature selection and modeling\n## Hyperparameter optimization and evaluation metrics\n## Key results by endpoint\n# Clinical background and motivation","[{\"question\":\"How many heart failure patients were included and what features were used?\",\"answer\":\"737 patients were included after exclusions from 1101. The study collected 34 conventional features for each patient.\"},{\"question\":\"Which methods were used for feature selection and model development?\",\"answer\":\"Boruta, RFE, and MRMR were applied for feature selection using the training set. Eight ML approaches were then used for modeling, with hyperparameters optimized using tenfold cross-validation and grid search.\"},{\"question\":\"How were model performance results evaluated for prediction tasks?\",\"answer\":\"Performance was assessed on a holdout test set using four metrics: AUC, accuracy, specificity, and sensitivity. Models were also bootstrapped 1000 times for evaluation stability.\"}]","Machine learning based readmission and mortality prediction in heart failure patients | PDF",1785812819,33,{"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},"machine-learning-based-readmission-and-mortality-prediction-in-heart-failure-patients","",{"@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/machine-learning-based-readmission-and-mortality-prediction-in-heart-failure-patients/122772/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How many heart failure patients were included and what features were used?","Question",{"text":75,"@type":76},"737 patients were included after exclusions from 1101. The study collected 34 conventional features for each patient.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which methods were used for feature selection and model development?",{"text":80,"@type":76},"Boruta, RFE, and MRMR were applied for feature selection using the training set. Eight ML approaches were then used for modeling, with hyperparameters optimized using tenfold cross-validation and grid search.",{"name":82,"@type":73,"acceptedAnswer":83},"How were model performance results evaluated for prediction tasks?",{"text":84,"@type":76},"Performance was assessed on a holdout test set using four metrics: AUC, accuracy, specificity, and sensitivity. Models were also bootstrapped 1000 times for evaluation stability.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]