8 papers
Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
Michele Miranda, Xinlan Yan, Nishant Mishra +4
Protecting patient privacy in clinical narratives is essential for enabling secondary use of healthcare data under regulations such as GDPR and HIPAA. While manual de-identificatio…
A Causal Framework for Evaluating ICU Discharge Strategies
Sagar Nagaraj Simha, Juliette Ortholand, Dave Dongelmans +4
In this applied paper, we address the difficult open problem of when to discharge patients from the Intensive Care Unit. This can be conceived as an optimal stopping scenario with…
Detection of Adverse Drug Events in Dutch clinical free text documents using Transformer Models: benchmark study
Rachel M. Murphy, Nishant Mishra, Nicolette F. de Keizer +5
In this study, we establish a benchmark for adverse drug event (ADE) detection in Dutch clinical free-text documents using several transformer models, clinical scenarios, and fit-f…
Interpretable phenotyping of Heart Failure patients with Dutch discharge letters
Vittorio Torri, Machteld J. Boonstra, Marielle C. van de Veerdonk +6
Objective: Heart failure (HF) patients present with diverse phenotypes affecting treatment and prognosis. This study evaluates models for phenotyping HF patients based on left vent…
Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activations
Mohammad Azizmalayeri, Ameen Abu-Hanna, Giovanni Cinà
Detecting out-of-distribution (OOD) instances is crucial for the reliable deployment of machine learning models in real-world scenarios. OOD inputs are commonly expected to cause a…
LLM aided semi-supervision for Extractive Dialog Summarization
Nishant Mishra, Gaurav Sahu, Iacer Calixto +2
Generating high-quality summaries for chat dialogs often requires large labeled datasets. We propose a method to efficiently use unlabeled data for extractive summarization of cust…
Causal prediction models for medication safety monitoring: The diagnosis of vancomycin-induced acute kidney injury
Izak Yasrebi-de Kom, Joanna Klopotowska, Dave Dongelmans +4
The current best practice approach for the retrospective diagnosis of adverse drug events (ADEs) in hospitalized patients relies on a full patient chart review and a formal causali…
Unmasking the Chameleons: A Benchmark for Out-of-Distribution Detection in Medical Tabular Data
Mohammad Azizmalayeri, Ameen Abu-Hanna, Giovanni Ciná
Despite their success, Machine Learning (ML) models do not generalize effectively to data not originating from the training distribution. To reliably employ ML models in real-world…