Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory

<p dir="ltr">Intensive care is quite expensive, so patients’ transfer to lower-level wards must be carefully considered. A patient who is discharged from the ICU too soon carries the danger of receiving insufficient care, which results in readmission. Readmission prediction tasks are...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Nadia Rasheed (22997257) (author)
مؤلفون آخرون: Usman Khaliq (22997260) (author), Ashfaq Ahmed (71749) (author), Amine Bermak (1895947) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513524547452928
author Nadia Rasheed (22997257)
author2 Usman Khaliq (22997260)
Ashfaq Ahmed (71749)
Amine Bermak (1895947)
author2_role author
author
author
author_facet Nadia Rasheed (22997257)
Usman Khaliq (22997260)
Ashfaq Ahmed (71749)
Amine Bermak (1895947)
author_role author
dc.creator.none.fl_str_mv Nadia Rasheed (22997257)
Usman Khaliq (22997260)
Ashfaq Ahmed (71749)
Amine Bermak (1895947)
dc.date.none.fl_str_mv 2025-09-08T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2025.3601117
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Predicting_Patient_ICU_Readmission_Using_Recurrent_Neural_Networks_With_Long_Short-Term_Memory/31056595
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Data management and data science
ICU readmission prediction
LSTM
MIMIC-III
time series analysis
Hospitals
Long short term memory
Data models
Predictive models
Codes
Prediction algorithms
Medical diagnostic imaging
Feature extraction
dc.title.none.fl_str_mv Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Intensive care is quite expensive, so patients’ transfer to lower-level wards must be carefully considered. A patient who is discharged from the ICU too soon carries the danger of receiving insufficient care, which results in readmission. Readmission prediction tasks are less extensively researched, and the techniques employed have not produced satisfactory results. Conventional machine learning methods with non-sequential data have been employed in the majority of the studies. The goal of this research is to propose a solution that can accurately predict the likelihood of an unplanned ICU readmission within 30 days. The proposed method addresses the issues of missing values and data imbalance, in particular. Our method combines low-dimensional embeddings of medical concepts, such as diseases labeled using the ICD-9 code, with temporal features extracted from chart events data. Three alternative models are trained using Long-Short-Term Memory (LSTM), which employ ICU stay data from the last 24 hours, 48 hours, and 72 hours. The Medical Information Mart for Intensive Care (MIMIC-III) dataset is used to train and validate models. We tested our proposed methods on the unseen data of the MIMIC-III dataset to assess their efficacy. The model that was trained using the last 48-hour ICU data performed better than other models, reaching an 84.2% area under the receiver operating characteristic curve (AUC-ROC). The ROC scores of the other models are 82.6%, 78.9%, 77.4%, 75.6%, and 71.4% for Gated Recurrent Unit (GRU), Support Vector Machine (SVM), Logistic Regression (LR), Naïve Baise (NB), and K-Nearest Neighbor (KNN), respectively. The findings indicate that the suggested approach can outperform the state-of-the-art methods.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3601117" target="_blank">https://dx.doi.org/10.1109/access.2025.3601117</a></p>
eu_rights_str_mv openAccess
id Manara2_1187d337393c1a968b2998cda9688fc6
identifier_str_mv 10.1109/access.2025.3601117
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/31056595
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term MemoryNadia Rasheed (22997257)Usman Khaliq (22997260)Ashfaq Ahmed (71749)Amine Bermak (1895947)Health sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceData management and data scienceICU readmission predictionLSTMMIMIC-IIItime series analysisHospitalsLong short term memoryData modelsPredictive modelsCodesPrediction algorithmsMedical diagnostic imagingFeature extraction<p dir="ltr">Intensive care is quite expensive, so patients’ transfer to lower-level wards must be carefully considered. A patient who is discharged from the ICU too soon carries the danger of receiving insufficient care, which results in readmission. Readmission prediction tasks are less extensively researched, and the techniques employed have not produced satisfactory results. Conventional machine learning methods with non-sequential data have been employed in the majority of the studies. The goal of this research is to propose a solution that can accurately predict the likelihood of an unplanned ICU readmission within 30 days. The proposed method addresses the issues of missing values and data imbalance, in particular. Our method combines low-dimensional embeddings of medical concepts, such as diseases labeled using the ICD-9 code, with temporal features extracted from chart events data. Three alternative models are trained using Long-Short-Term Memory (LSTM), which employ ICU stay data from the last 24 hours, 48 hours, and 72 hours. The Medical Information Mart for Intensive Care (MIMIC-III) dataset is used to train and validate models. We tested our proposed methods on the unseen data of the MIMIC-III dataset to assess their efficacy. The model that was trained using the last 48-hour ICU data performed better than other models, reaching an 84.2% area under the receiver operating characteristic curve (AUC-ROC). The ROC scores of the other models are 82.6%, 78.9%, 77.4%, 75.6%, and 71.4% for Gated Recurrent Unit (GRU), Support Vector Machine (SVM), Logistic Regression (LR), Naïve Baise (NB), and K-Nearest Neighbor (KNN), respectively. The findings indicate that the suggested approach can outperform the state-of-the-art methods.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3601117" target="_blank">https://dx.doi.org/10.1109/access.2025.3601117</a></p>2025-09-08T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3601117https://figshare.com/articles/journal_contribution/Predicting_Patient_ICU_Readmission_Using_Recurrent_Neural_Networks_With_Long_Short-Term_Memory/31056595CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/310565952025-09-08T06:00:00Z
spellingShingle Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
Nadia Rasheed (22997257)
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Data management and data science
ICU readmission prediction
LSTM
MIMIC-III
time series analysis
Hospitals
Long short term memory
Data models
Predictive models
Codes
Prediction algorithms
Medical diagnostic imaging
Feature extraction
status_str publishedVersion
title Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
title_full Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
title_fullStr Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
title_full_unstemmed Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
title_short Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
title_sort Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory
topic Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Data management and data science
ICU readmission prediction
LSTM
MIMIC-III
time series analysis
Hospitals
Long short term memory
Data models
Predictive models
Codes
Prediction algorithms
Medical diagnostic imaging
Feature extraction