[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125128-en":3,"doc-seo-125128-105":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},125128,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","MACHINE LEARNING APPROACHES OF LOGISTIC ORGAN DYSFUNCTION SCORE PREDICTION WITH DATA ACQUIRED FROM BEDSIDE IN ICU - Master’s thesis","Machine Learning Approaches of Logistic Organ Dysfunction Score Prediction with data acquired from bedside in ICU targets accurate early estimation of patient organ dysfunction and mortality risk in high-stakes intensive care settings. The study addresses time and cost barriers of Logistic Organ Dysfunction Score (LODS) computation by training models to predict total LODS from bedside-retrievable data within the first 12 hours. Using the MIMIC-IV database, the best-performing XGBoost model relies on eight features and reports MAE 1.4173 and RMSE 1.8222. Results support more practical LODS usage and provide evidence-supported probabilities to assist treatment adjustment.","Chen Zhu  \nMACHINE LEARNING APPROACHES OF LOGISTIC ORGAN DYSFUNCTION SCORE PREDICTION WITH DATA ACQUIRED FROM BEDSIDE IN ICU  \nFaculty of Information Technology and Communication Sciences (ITC) Master’s thesis May 2024  \nAbstract  \nChen Zhu: Machine Learning Approaches of Logistic Organ Dysfunction Score Prediction with Data Acquired from Bedside in ICU  \nMaster’s thesis Tampere University  \nMaster’s Degree Programme in Computing Sciences May 2024  \nIntensive Care Unit (ICU) is a high-stakes environment in hospitals, where patients are at a higher risk than in other departments, such as organ dysfunction, and are monitored with devices, along with more care workers. Effectively predicting patient status in an ICU is a critical task serving patient health and resource allocation. Logistic Organ Dysfunction Score (LODS), calculated with weighted variables of the worst values in the first 24 hours, is an organ dysfunction scoring system that reflects the severity level of organ systems, and can be converted to the probability of mortality in a certain period. However, LODS calculation requires some laboratory results, such as bilirubin, which costs time and money. Effective prediction of LODS value could measure the patient’s overall organ dysfunction situation and calculate the probability of mortality for the patient, providing doctors with assistance in adjusting treatment. Machine learning can utilize large amounts of data and existing algorithms to train effective models for highly accurate prediction tasks.  \nThere are some studies on predicting organ dysfunction with bedside data and some Electronic Health Records (EHR) information, including demographic information and laboratory results. This thesis proposes machine learning models, trained with the Medical Information Mart for Intensive Care (MIMIC) -IV database, to predict total LODS with data that can be acquired bedside in the first 12 hours of ICU stay, to save time and assist doctors in treatment. The model with the best performance utilized eight features and was trained using XGBoost. It achieved a mean absolute error (MAE) of 1.4173 and a root mean square error (RMSE) of 1.8222 . These models enhance the practicality and ease of application of LODS, while providing evidence-supported calculated probabilities of mortality. Moreover, this study fills the gap of predicting LODS.  \nKeywords: machine learning, organ dysfunction score, bedside data, deep learning  \nThe originality of this thesis has been checked using the Turnitin Originality Check service.  \nContents  \n1 Introduction ................................... 1  \n1.1 ICU and Scoring System ......................... 1  \n1.2 Machine Learning ............................. 2  \n1.3 Motivation and Objectives ........................ 3  \n2 Background ................................... 5  \n2.1 Severity Scoring systems in Critical Care ................ 5  \n2.1.1 Logistic Organ Dysfunction Score .................. 6  \n2.2 Machine Learning ............................. 9  \n2.2.1 Supervised Training and Regression ................ 10  \n2.2.2 Underfitting and Overfitting ..................... 11  \n2.2.3 Machine Learning in ICU Settings ................. 11  \n3 Prior Work ................................... 13  \n3.1 Models with bed side data in ICU .................... 13  \n3.2 Organ dysfunction score related research ................ 15  \n3.3 Decision Tree based algorithm applied on medical data ........ 17  \n3.4 Discussion of Prior Work ......................... 18  \n4 Methods ..................................... 20  \n4.1 Dataset .................................. 20  \n4.2 Feature Correlation and Reduction ................... 21  \n4.2.1 Pearson Correlation ......................... 21  \n4.2.2 Spearman Correlation ........................ 22  \n4.3 Missing Data Imputation ......................... 22  \n4.3.1 Linear Interpolation ......................... 23  \n4.3.2 Probabilistic Principal Component Analysis ...........","cbCaiaaV8cu1Lber","https://ap.wps.com/l/cbCaiaaV8cu1Lber","pdf",1406247,1,69,"English","en",105,"# 1 Introduction\n## 1.1 ICU and Scoring System\n## 1.2 Machine Learning\n## 1.3 Motivation and Objectives\n# 2 Background\n## 2.1 Severity Scoring systems in Critical Care\n## 2.1.1 Logistic Organ Dysfunction Score\n## 2.2 Machine Learning\n## 2.2.1 Supervised Training and Regression\n## 2.2.2 Underfitting and Overfitting\n## 2.2.3 Machine Learning in ICU Settings\n# 3 Prior Work\n## 3.1 Models with bed side data in ICU\n## 3.2 Organ dysfunction score related research\n## 3.3 Decision Tree based algorithm applied on medical data\n## 3.4 Discussion of Prior Work\n# 4 Methods\n## 4.1 Dataset\n## 4.2 Feature Correlation and Reduction\n## 4.3 Missing Data Imputation\n## 4.4 Models\n## 4.5 Evaluation\n## 4.6 Explainable Artificial Intelligence\n# 5 Experiments\n## 5.1 Data Collection\n## 5.2 Experiment I: Correlation Coefficient and XGBoost\n## 5.3 Experiment II: Convolutional Neural Network and XGBoost\n# 6 Results\n## 6.1 Experiment I: Correlation Coefficient and XGBoost\n## 6.2 Experiment II: Convolutional Neural Network and XGBoost\n# 7 Discussion\n## 7.1 Limitations and Further Study\n# 8 Conclusion","[{\"question\":\"Why is early prediction of LODS important in an ICU?\",\"answer\":\"ICU patients face higher risk of organ dysfunction, and LODS supports severity quantification and mortality probability estimation. Early prediction helps clinicians adjust treatment and supports efficient resource allocation.\"},{\"question\":\"How does the thesis reduce the burden of LODS calculation?\",\"answer\":\"Instead of requiring laboratory results needed for LODS computation, the study trains models to predict total LODS using data that can be acquired at the bedside in the first 12 hours.\"},{\"question\":\"What dataset and model achieved the best performance?\",\"answer\":\"Models are trained on the MIMIC-IV database. The top-performing model uses XGBoost with eight features and reports MAE 1.4173 and RMSE 1.8222.\"}]","MACHINE LEARNING APPROACHES OF LOGISTIC ORGAN DYSFUNCTION SCORE PREDICTION WITH DATA ACQUIRED FROM BEDSIDE IN ICU - Master’s thesis | PDF",1785896815,174,{"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-approaches-of-logistic-organ-dysfunction-score-prediction-with-data-acquired-from-bedside-in-icu-masters-thesis","",{"@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-approaches-of-logistic-organ-dysfunction-score-prediction-with-data-acquired-from-bedside-in-icu-masters-thesis/125128/",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","2026-08-05",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},"Why is early prediction of LODS important in an ICU?","Question",{"text":75,"@type":76},"ICU patients face higher risk of organ dysfunction, and LODS supports severity quantification and mortality probability estimation. Early prediction helps clinicians adjust treatment and supports efficient resource allocation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis reduce the burden of LODS calculation?",{"text":80,"@type":76},"Instead of requiring laboratory results needed for LODS computation, the study trains models to predict total LODS using data that can be acquired at the bedside in the first 12 hours.",{"name":82,"@type":73,"acceptedAnswer":83},"What dataset and model achieved the best performance?",{"text":84,"@type":76},"Models are trained on the MIMIC-IV database. The top-performing model uses XGBoost with eight features and reports MAE 1.4173 and RMSE 1.8222.","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"]