Health AI Central
Peer-Reviewed Publication
Laryngoscope Investig Otolaryngol2026;11(4):e70519.August 1, 2026Journal Article

Large Language Models for Optimizing Patient Recruitment Decisions in Voice Data Generation Projects.

James Anibal1,2, Geetha Krishna Chaitanya Nama3, Shrramana Ganesh4, Yosef Nafii4, Samantha Salvi Cruz5, Veronica Daoud4, Madeleine Zanin6, Tram Le4, Parsa Khorrami3, Bradford J Wood2, David Clifton1, Jamie Toghranegar4, Yael Bensoussan4, Yael E Bensoussan1,2,3,4,5,6, Olivier Elemento1,2,3,4,5,6, Jean-Christophe Bélisle-Pipon1,2,3,4,5,6, David Dorr1,2,3,4,5,6, Satrajit Ghosh1,2,3,4,5,6, Alistair Johnson1,2,3,4,5,6, Phillip Payne1,2,3,4,5,6, Maria E Powell1,2,3,4,5,6, Anaïs Rameau1,2,3,4,5,6, Vardit Ravitsky1,2,3,4,5,6, Alexandros Sigaras1,2,3,4,5,6, Shaheen Awan1,2,3,4,5,6, Ruth Bahr1,2,3,4,5,6, Donald Bolser1,2,3,4,5,6, Kathy J Jenkins1,2,3,4,5,6, Frank Rudzicz1,2,3,4,5,6, Jennifer Siu1,2,3,4,5,6, Stephanie Watts1,2,3,4,5,6, Yassmeen Abdel-Aty1,2,3,4,5,6, Toufeeq Ahmed Syed1,2,3,4,5,6, James Anibal1,2,3,4,5,6, Steven Bedrick1,2,3,4,5,6, Isaac Bevers1,2,3,4,5,6, Micah Boyer1,2,3,4,5,6, Rahul Brito1,2,3,4,5,6, Selina A Casalino1,2,3,4,5,6, John Costello1,2,3,4,5,6, Enrique Diaz-Ocampo1,2,3,4,5,6, Mahmoud Elmahdy1,2,3,4,5,6, Kenneth Fletcher1,2,3,4,5,6, Alexander Gelbard1,2,3,4,5,6, Karim Hanna1,2,3,4,5,6, Bill Hersh1,2,3,4,5,6, Lochana Jayachandran1,2,3,4,5,6, Kaley Jenney1,2,3,4,5,6, Andrea Krussel1,2,3,4,5,6, Chloe Loewith1,2,3,4,5,6, Tempestt Neal1,2,3,4,5,6, Claire Premi-Bortolotto1,2,3,4,5,6, Sarah Rohde1,2,3,4,5,6, Samantha Salvi Cruz1,2,3,4,5,6, Elizabeth Silberholz1,2,3,4,5,6, Duncan Sutherland1,2,3,4,5,6, Venkata Swarna Mukhi Talluri1,2,3,4,5,6, Jamie Toghranegar1,2,3,4,5,6, Kimberly Vinson1,2,3,4,5,6, Claire Wilson1,2,3,4,5,6, Madeleine Zanin1,2,3,4,5,6, Theresa Zesiewicz1,2,3,4,5,6, Robin Zhao1,2,3,4,5,6
1Computational Health Informatics Lab, Institute of Biomedical Engineering University of Oxford Oxford UK.
2Center for Interventional Oncology NIH Clinical Center, National Institutes of Health Bethesda Maryland USA.
3Department of Computer Science and Engineering University of South Florida Tampa Florida USA.
4USF Health Voice Center, Department of Otolaryngology-Head & Neck Surgery University of South Florida Tampa Florida USA.
5Vanderbilt University Medical Center Nashville Tennessee USA.
6Mount Sinai Hospital Toronto Ontario Canada.
PubMed PMC DOI PDF

Abstract

OBJECTIVES: Past studies have shown that many clinical machine learning models have performance limitations due to imbalances in the training data. For voice data generation projects, the origin of the problem may lie in the recruiting methods used during data collection efforts. This study introduces a generative AI pipeline for "dataset decision support", recommending recruitment decisions based…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.