A5031825709- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare
- COVID-19 diagnosis using AI
- Computational and Text Analysis Methods
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- Sepsis Diagnosis and Treatment
- Artificial Intelligence in Healthcare and Education
- Imbalanced Data Classification Techniques
- Diabetes Management and Research
National Taipei University of Technology
2022-2024
An ICU is a critical care unit that provides advanced medical support and continuous monitoring for patients with severe illnesses or injuries. Predicting the mortality rate of can not only improve patient outcomes, but also optimize resource allocation. Many studies have attempted to create scoring systems models predict using large amounts structured clinical data. However, unstructured data recorded during admission, such as notes made by physicians, often overlooked. This study used...
Cardiovascular diseases have been identified as one of the top three causes death worldwide, with onset and deaths mostly due to heart failure (HF). In ICU, where patients HF are at increased risk consume significant medical resources, early accurate prediction time for high would enable them receive appropriate timely care. The data this study were obtained from MIMIC-III database, we collected vital signs tests 6699 patient during first 24 h their ICU admission. order predict mortality in...
Predicting clinical patients’ vital signs is a leading critical issue in intensive care units (ICUs) related studies. Early prediction of the mortality ICU patients can reduce overall and cost complication treatment. Some studies have predicted based on electronic health record (EHR) data by using machine learning models. However, semi-structured (i.e., diagnosis inspection reports) rarely used these This study utilized from Medical Information Mart for Intensive Care III. We Latent...
The increasing rate of intensive care unit (ICU) readmissions poses significant challenges in healthcare, impacting both costs and patient outcomes. Predicting readmission after discharge is crucial for improving medical quality reducing expenses. Traditional analyses electronic health record (EHR) data have primarily focused on numerical data, often neglecting valuable text data.
Prognostic outcomes for patients with type 2 diabetes in the intensive care unit (ICU), including mortality and readmission rates, are critical informed clinical decision-making. Although existing research has established a link between adverse ICU, potential of machine learning techniques enhancing predictive accuracy not been fully realized. This study seeks to develop validate models employing algorithms forecast 30-day post-discharge rates among ICU patients, thereby supporting Data were...
Heart failure remains a leading cause of mortality worldwide, particularly within Intensive Care Unit (ICU)-patient populations. This study introduces an innovative approach to predicting ICU by seamlessly integrating electronic health record (EHR) data with BERTopic-based hybrid machine-learning methodology. The MIMIC-III database serves as the primary source, encompassing structured and unstructured from 6606 ICU-admitted heart-failure patients. Unstructured are processed using BERTopic,...