Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 31 for “"MIMIC-IV"”.
-
Predicting 30-Day Unplanned ICU Readmissions Using Deep Learning and Natural Language Processing Techniques: A MIMIC IV Data Analysis
… 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 …
-
Predicting patient outcome from clinical journals and biomedical articles: Using the MIMIC-IV database, multiple in-hospital mortality prediction models are created, to which improvements are attempted through the use of word embeddings trained on scientific biomedical literature
… information suitable for developing AI-driven systems to support medical workers, and with some work, we believe that data from the biomedical literature can also be used to improve these systems. In this work, clinical records from ICU patients in the MIMIC-IV database are used to create …
-
Developing a comparative framework for machine-learning classifying models based on the Emergency Severity Index triage system
… in healthcare premises, where they receive a variety of cases, including critical ones and life-threatening conditions. Arranging the order of received patients and providing timely and efficient care is of utmost importance. This procedure is usually carried out by a nurse who considers …
-
Analýza EKG markerů se vztahem k srdečnímu selhání
… 12svodových EKG záznamů z veřejné databáze MIMIC-IV. Cílem práce bylo navrhnout nové EKG markery pro detekci tohoto klinického syndromu a provést jejich statistickou analýzu. Součástí práce je rovněž analýza vztahu navržených markerů k progresi srdečního selhání.
-
Implementing Fairness in Real-World Healthcare Machine Learning through Datasheet for Database
… is essential to ensure fairness, i.e., models delivering equitable performance to all individuals, irrespective of their inherent or acquired characteristics. This requires a thorough examination of the data used and the specific applications of these models. This study conducted a six-year …
-
Encoding FHIR Medical Data for Transformers
… performance of this method on the open source MIMIC-IV FHIR dataset is validated for length-of-stay prediction (LOS) and mortality prediction (MP) tasks. In addition, I explore methods for encoding numerical and time-delta values using continuous vector encodings rather than assigning discrete …
-
Automated Medical Coding Using Supervised Deep Learning and Large Language Models
… to limited labeled data, lengthy clinical narratives, and the imbalanced distribution of frequent and rare codes. This thesis investigates automated ICD code prediction using both supervised deep learning and Large Language Model (LLM)-based approaches on MIMIC-IV. In the first part, supervised …
-
Thresholds for Initiating Invasive Ventilation in Hypoxemic Respiratory Failure
Background: Invasive ventilation is a potentially life-saving intervention for people with severe hypoxemic respiratory failure, however the optimal thresholds for its initiation are unknown. Objectives: In people with hypoxemic respiratory failure, (1) measure the probability of invasive …
-
Functional Causal Mediation Analysis with Zero-inflated Count Data
… The proposed framework is illustrated in a MIMIC-IV application among patients undergoing coronary artery bypass grafting, where the use of sex as a non-manipulable treatment is discussed, and a principal stratification framework is adopted to handle post-treatment selection into the …
-
Towards agentic AI for point-of-care echocardiography reasoning and interpretation
… measurement-feasibility prediction, quantitative measurement extraction, and guideline retrieval. Measurements are grounded in speci c frames and anatomical structures, while interpretations are supported by retrieved clinical guidelines, producing an auditable reasoning process. EchoAgent is …
-
MedBench: Benchmarking Machine Learning Methods for Medical Tabular Prediction
… by constructing a benchmark from the ADNI, MIMIC-IV, and NHANES datasets, covering prognostic and diagnostic tasks across binary classification, multiclass classification, and regression. TabPFN, TabICL, and MITRAarecomparedwith classical baselines using modality specific metrics, aggregate …
-
Real-world evidence for the management of blood glucose in the intensive care unit
… a core aspect of patient management in the intensive care unit (ICU). Blood glucose has a well-known U-shaped relationship with mortality and morbidity in ICU patients, with both hypo- and hyper-glycaemia associated with poor patient outcomes. As a result, up to 40-90% of ICU patients receive …
-
SELECTIVE K-MEANS INFERENCE FOR HETEROGENEITY IN TRAUMATIC BRAIN INJURY
… of first-day ICU physiology with selective inference to test inter-cluster differences while accounting for data-driven selection (Chen and Witten 2023). This statistical innovation rigorously tests for differences between clusters while controlling for the bias introduced by using the …
-
Leveraging temporality, dose effect, and co-medication to improve drug safety surveillance
… and drug–drug interactions (DDIs) more effectively. First, we develop and evaluate a generative transformer architecture (GPT-2) trained from scratch on longitudinal EHR data from two distinct repositories (MIMIC-IV and a large university health system, UW). Unlike traditional …
-
Improving Predictive Process Analytics with Deep Learning and XAI
In this doctoral thesis, we explore the innovative application of the Tab Transformerarchitecture in the realm of predictive process mining, marking a significant advancement inforecasting subsequent events within activity sequences. Utilising the PM2 methodology,known for its structured approach …
-
Enhancing Time Series Predictions For Healthcare Decision Support Using Federated Learning and Large Language Models
… to enhance decision-making processes by effectively analyzing time series data to provide actionable insights. This thesis focuses on the role of federated learning as a mechanism to improve time series forecasting for blood demand, alongside leveraging large language models (LLMs) for time …
-
Reconstructing Private Data from Trained Models
… Model Inversion (MI) attacks can be effectively adapted to tabular data—a domain where risks are underexplored compared to the image modality. To address this question, we propose a novel adaptation of the Pseudo-Label Guided Model Inversion (PLG-MI) attack for tabular data by utilizing a …
-
Improving Inpatient Deterioration Prediction Using Temporal AI
… Machine Learning (ML), offers an alternative approach that can leverage temporal patterns encoded within physiological time-series data. This thesis develops temporally aware ML models for clinical deterioration prediction, addressing three research questions: Can temporal deep learning …
Page 1 of 2