Search Results for author:
Found 9 papers, 4 papers with code
Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification
We anticipate that our template guidance will forge a fresh approach to elucidating AI models by integrating clinical domain expertise.
Developing Federated Time-to-Event Scores Using Heterogeneous Real-World Survival Data
We applied our approach to sites with heterogeneous survival data originating from emergency departments in Singapore and the United States.
Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning
In this work, we propose to integrate foundation models with clustering methods to select samples for cold-start active learning initialization.
Leveraging Anatomical Constraints with Uncertainty for Pneumothorax Segmentation
We propose a novel approach that incorporates the lung+ space as a constraint during DL model training for pneumothorax segmentation on 2D chest radiographs.
Federated Learning for Clinical Structured Data: A Benchmark Comparison of Engineering and Statistical Approaches
Our goal was to bridge the gap by presenting the first comprehensive comparison of FL frameworks from both engineering and statistical domains.
LATTE: Label-efficient Incident Phenotyping from Longitudinal Electronic Health Records
We propose a LAbel-efficienT incidenT phEnotyping (LATTE) algorithm to accurately annotate the timing of clinical events from longitudinal EHR data.
Federated and distributed learning applications for electronic health records and structured medical data: A scoping review
Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice.
FedScore: A privacy-preserving framework for federated scoring system development
We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models.
High-throughput relation extraction algorithm development associating knowledge articles and electronic health records
In this paper, we present Hi-RES, a framework for high-throughput relation extraction algorithm development.
