Generative AI costs in large healthcare systems, an example in revenue cycle

Michael L. Burns; Ssu Ying Chen; Chu An Tsai; John Vandervest; Balaji Pandian; Paige Nong; David A. Hanauer; Andrew Rosenberg; Jodyn Platt

doi:10.1038/s41746-025-01971-x

Generative AI costs in large healthcare systems, an example in revenue cycle

Michael L. Burns
, Ssu Ying Chen
, Chu An Tsai
, John Vandervest
, Balaji Pandian
, Paige Nong
, David A. Hanauer
, Andrew Rosenberg
, Jodyn Platt

Health Policy and Management

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

Application of large language models in healthcare continues to expand, specifically for medical free-text classification tasks. While foundation models like those from ChatGPT show potential, alternative models demonstrate superior accuracy and lower costs. This study underscores significant challenges, including computational costs and model reliability. Amidst rising healthcare expenditures and AI’s perceived potential to reduce costs, a combination of local and commercial models might offer balanced solutions for healthcare systems.

Original language	English (US)
Article number	579
Journal	npj Digital Medicine
Volume	8
Issue number	1
DOIs	https://doi.org/10.1038/s41746-025-01971-x
State	Published - Dec 2025

Bibliographical note

Publisher Copyright:
© The Author(s) 2025.

PubMed: MeSH publication types

Journal Article

Publisher link

10.1038/s41746-025-01971-x

Find It

Find It at U of M Libraries

Cite this

@article{6c6a530335bb4dafaa694f33f0f7a035,

title = "Generative AI costs in large healthcare systems, an example in revenue cycle",

abstract = "Application of large language models in healthcare continues to expand, specifically for medical free-text classification tasks. While foundation models like those from ChatGPT show potential, alternative models demonstrate superior accuracy and lower costs. This study underscores significant challenges, including computational costs and model reliability. Amidst rising healthcare expenditures and AI{\textquoteright}s perceived potential to reduce costs, a combination of local and commercial models might offer balanced solutions for healthcare systems.",

author = "Burns, \{Michael L.\} and Chen, \{Ssu Ying\} and Tsai, \{Chu An\} and John Vandervest and Balaji Pandian and Paige Nong and Hanauer, \{David A.\} and Andrew Rosenberg and Jodyn Platt",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",

year = "2025",

month = dec,

doi = "10.1038/s41746-025-01971-x",

language = "English (US)",

volume = "8",

journal = "npj Digital Medicine",

issn = "2398-6352",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Generative AI costs in large healthcare systems, an example in revenue cycle

AU - Burns, Michael L.

AU - Chen, Ssu Ying

AU - Tsai, Chu An

AU - Vandervest, John

AU - Pandian, Balaji

AU - Nong, Paige

AU - Hanauer, David A.

AU - Rosenberg, Andrew

AU - Platt, Jodyn

PY - 2025/12

Y1 - 2025/12

N2 - Application of large language models in healthcare continues to expand, specifically for medical free-text classification tasks. While foundation models like those from ChatGPT show potential, alternative models demonstrate superior accuracy and lower costs. This study underscores significant challenges, including computational costs and model reliability. Amidst rising healthcare expenditures and AI’s perceived potential to reduce costs, a combination of local and commercial models might offer balanced solutions for healthcare systems.

AB - Application of large language models in healthcare continues to expand, specifically for medical free-text classification tasks. While foundation models like those from ChatGPT show potential, alternative models demonstrate superior accuracy and lower costs. This study underscores significant challenges, including computational costs and model reliability. Amidst rising healthcare expenditures and AI’s perceived potential to reduce costs, a combination of local and commercial models might offer balanced solutions for healthcare systems.

UR - https://www.scopus.com/pages/publications/105017733129

UR - https://www.scopus.com/pages/publications/105017733129#tab=citedBy

U2 - 10.1038/s41746-025-01971-x

DO - 10.1038/s41746-025-01971-x

M3 - Article

C2 - 41028226

AN - SCOPUS:105017733129

SN - 2398-6352

VL - 8

JO - npj Digital Medicine

JF - npj Digital Medicine

IS - 1

M1 - 579

ER -

Generative AI costs in large healthcare systems, an example in revenue cycle

Abstract

Bibliographical note

PubMed: MeSH publication types

Publisher link

Find It

Other files and links

Fingerprint

Cite this