106 citations · 125 across the 11 of their papers we have counts for
6 papers · 1 filter
ICD Codes are Insufficient to Create Datasets for Machine Learning: An Evaluation Using All of Us Data for Coccidioidomycosis and Myocardial Infarction
Abigail E. Whitlock, Gondy Leroy, Fariba M. Donovan +1
In medicine, machine learning (ML) datasets are often built using the International Classification of Diseases (ICD) codes. As new models are being developed, there is a need for l…
Role of Dependency Distance in Text Simplification: A Human vs ChatGPT Simplification Comparison
Sumi Lee, Gondy Leroy, David Kauchak +1
This study investigates human and ChatGPT text simplification and its relationship to dependency distance. A set of 220 sentences, with increasing grammatical difficulty as measure…
Crowdsourcing with Enhanced Data Quality Assurance: An Efficient Approach to Mitigate Resource Scarcity Challenges in Training Large Language Models for Healthcare
P. Barai, G. Leroy, P. Bisht +5
Large Language Models (LLMs) have demonstrated immense potential in artificial intelligence across various domains, including healthcare. However, their efficacy is hindered by the…
Utilizing Large Language Models to Generate Synthetic Data to Increase the Performance of BERT-Based Neural Networks
Chancellor R. Woolsey, Prakash Bisht, Joshua Rothman +1
An important issue impacting healthcare is a lack of available experts. Machine learning (ML) models could resolve this by aiding in diagnosing patients. However, creating datasets…
Text and Audio Simplification: Human vs. ChatGPT
Gondy Leroy, David Kauchak, Philip Harber +2
Text and audio simplification to increase information comprehension are important in healthcare. With the introduction of ChatGPT, an evaluation of its simplification performance i…
Effects of Added Emphasis and Pause in Audio Delivery of Health Information
Arif Ahmed, Gondy Leroy, Stephen A. Rains +3
Health literacy is crucial to supporting good health and is a major national goal. Audio delivery of information is becoming more popular for informing oneself. In this study, we e…