We design and implement a multi-stage modeling approach focused on predicting unplanned 30-day all- cause intensive care unit (ICU) hospital readmissions using the Medical Information Mart for Intensive Care (MIMIC IV) dataset. Structured data consisting of demographic information, comorbidities, lab results, and vital signs are combined with features extracted from medical text data consisting of patients’ diagnoses, procedures, and discharge notes and further engineered using several methods, including Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and word embeddings.
We sequentially implement three distinct Dense Neural Networks (DNNs) combined with the LightGBM gradient-boosting framework. Our model attained a 5-fold cross-validated area under the ROC curve (AU- ROC) of 0.81. Our results demonstrate the effectiveness of the proposed modeling approach in identifying high-risk patients for unplanned ICU readmissions within 30 days of initial discharge.
This research adds to the expanding field of healthcare informatics by highlighting the effectiveness of incorporating a multitude of Natural Language Processing (NLP) and other patient-engineered features in a single model. These discoveries offer valuable insights for healthcare professionals and decision-makers aiming to decrease ICU readmissions.
","abstract_html":"<p>We design and implement a multi-stage modeling approach focused on predicting unplanned 30-day all- cause intensive care unit (ICU) hospital readmissions using the Medical Information Mart for Intensive Care (MIMIC IV) dataset. Structured data consisting of demographic information, comorbidities, lab results, and vital signs are combined with features extracted from medical text data consisting of patients’ diagnoses, procedures, and discharge notes and further engineered using several methods, including Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and word embeddings.</p> <p>We sequentially implement three distinct Dense Neural Networks (DNNs) combined with the LightGBM gradient-boosting framework. Our model attained a 5-fold cross-validated area under the ROC curve (AU- ROC) of 0.81. Our results demonstrate the effectiveness of the proposed modeling approach in identifying high-risk patients for unplanned ICU readmissions within 30 days of initial discharge.</p> <p>This research adds to the expanding field of healthcare informatics by highlighting the effectiveness of incorporating a multitude of Natural Language Processing (NLP) and other patient-engineered features in a single model. These discoveries offer valuable insights for healthcare professionals and decision-makers aiming to decrease ICU readmissions.</p>","abstract_has_math":false,"creators":["Licerio, David"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computational and Data Sciences","degree_department":null,"school":null,"contributors":["Dr. Cyril Rakovski","Dr. Hanna Lu","Dr. Adrian Vajiac"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05-01T07:00:00Z","date_published":"2024-05-01T07:00:00Z","updated_at":"2026-07-24T01:38:37Z","subjects":["Deep Learning","Natural Language Processing","ICU Predictions","Machine Learning","Data Science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.chapman.edu/cads_theses/20","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Cyril Rakovski","Dr. Hanna Lu","Dr. Adrian Vajiac"]},{"key":"dc:creator","label":"Author","values":["Licerio, David"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-05-06T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computational and Data Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning","Natural Language Processing","ICU Predictions","Machine Learning","Data Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.chapman.edu/cads_theses/20"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We design and implement a multi-stage modeling approach focused on predicting unplanned 30-day all- cause intensive care unit (ICU) hospital readmissions using the Medical Information Mart for Intensive Care (MIMIC IV) dataset. Structured data consisting of demographic information, comorbidities, lab results, and vital signs are combined with features extracted from medical text data consisting of patients’ diagnoses, procedures, and discharge notes and further engineered using several methods, including Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and word embeddings.
We sequentially implement three distinct Dense Neural Networks (DNNs) combined with the LightGBM gradient-boosting framework. Our model attained a 5-fold cross-validated area under the ROC curve (AU- ROC) of 0.81. Our results demonstrate the effectiveness of the proposed modeling approach in identifying high-risk patients for unplanned ICU readmissions within 30 days of initial discharge.
This research adds to the expanding field of healthcare informatics by highlighting the effectiveness of incorporating a multitude of Natural Language Processing (NLP) and other patient-engineered features in a single model. These discoveries offer valuable insights for healthcare professionals and decision-makers aiming to decrease ICU readmissions.
"]},{"key":"dc:source","label":"Dc Source","values":["D. Licerio, \"Predicting 30-day unplanned ICU readmissions using deep learning and natural language processing techniques: A MIMIC IV data analysis,\" M. S. thesis, Chapman University, Orange, CA, 2024. https://doi.org/10.36837/chapman.000557"]},{"key":"dc:title","label":"Title","values":["Predicting 30-Day Unplanned ICU Readmissions Using Deep Learning and Natural Language Processing Techniques: A MIMIC IV Data Analysis"]}]}],"canonical_facts":{"dc:contributor":["Dr. Cyril Rakovski","Dr. Hanna Lu","Dr. Adrian Vajiac"],"dc:creator":["Licerio, David"],"dc:date.available":["2026-05-06T07:00:00Z"],"dc:description.abstract":["We design and implement a multi-stage modeling approach focused on predicting unplanned 30-day all- cause intensive care unit (ICU) hospital readmissions using the Medical Information Mart for Intensive Care (MIMIC IV) dataset. Structured data consisting of demographic information, comorbidities, lab results, and vital signs are combined with features extracted from medical text data consisting of patients’ diagnoses, procedures, and discharge notes and further engineered using several methods, including Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and word embeddings.
We sequentially implement three distinct Dense Neural Networks (DNNs) combined with the LightGBM gradient-boosting framework. Our model attained a 5-fold cross-validated area under the ROC curve (AU- ROC) of 0.81. Our results demonstrate the effectiveness of the proposed modeling approach in identifying high-risk patients for unplanned ICU readmissions within 30 days of initial discharge.
This research adds to the expanding field of healthcare informatics by highlighting the effectiveness of incorporating a multitude of Natural Language Processing (NLP) and other patient-engineered features in a single model. These discoveries offer valuable insights for healthcare professionals and decision-makers aiming to decrease ICU readmissions.
"],"dc:identifier":["https://digitalcommons.chapman.edu/cads_theses/20"],"dc:source":["D. Licerio, \"Predicting 30-day unplanned ICU readmissions using deep learning and natural language processing techniques: A MIMIC IV data analysis,\" M. S. thesis, Chapman University, Orange, CA, 2024. https://doi.org/10.36837/chapman.000557"],"dc:subject":["Deep Learning","Natural Language Processing","ICU Predictions","Machine Learning","Data Science"],"dc:title":["Predicting 30-Day Unplanned ICU Readmissions Using Deep Learning and Natural Language Processing Techniques: A MIMIC IV Data Analysis"],"thesis:degree_discipline":["Computational and Data Sciences"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-07-24T01:38:37Z"}