Interpretability of an FDA-authorized AI/ML sepsis diagnostic tool improved by SHAP values

These results suggest health care providers value transparency into AI/ML algorithms designed for clinical use, and that Shapley values are a useful approach to providing that transparency, which in turn may improve tool adoption and clinical utility.

Authors

Institutions

Publication Details

Journal
JAMIA Open
Published
2026-01-06
DOI
https://doi.org/10.1093/jamiaopen/ooag020
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Interpretability of an FDA-authorized AI/ML sepsis diagnostic tool improved by SHAP values

Scott Smith, Ashok Palagiri, Nicholas Maddens, Tatyana Shvilkina et al.
JAMIA Open
Artificial Intelligence in Healthcare and Education
article

Interpretability of an FDA-authorized AI/ML sepsis diagnostic tool improved by SHAP values

Scott Smith, Ashok Palagiri, Nicholas Maddens, Tatyana Shvilkina, J. H. Lee, Akhil Bhargava, Carmen DeMarco, Neil R. Evans, Stockton Mayer, Kurian Thomas, Ramona Berghea, Falgun Gosai, Andrew Friederich, B. Stenson, Aimee Espinosa, Roneil G. Malkani, Carlos G. Lopez-Espina, Grace L. Staples, Alexandra Halalau, Clinton Ezekiel, Amanda Doodlesack, Peter S. Antkowiak, Alon Dagan, Sihai Dave Zhao, Vikram Oke, Lekshminarayan Raghavakurup, Lavneet Chawla, Deesha Sarma, Eric Reseland, Muleta Tafa, Hugo Dávila, Francisco R. Davila, Niko Kurtzman, Aamer Syed, M.J. Crisp, Saleem Azad, Roshni Patel, Matthew Sims, Samuel Raouf, Ruoqing Zhu, Farhan Ali, Lee Schmalz, Bobby Reddy, Gregory Watson, Rashid Bashir, Max S Kravitz, Nathan I Shapiro, Karthik Iyer, Farid Sadaka, Robin Carver, Sahib Singh
article en

Abstract

These results suggest health care providers value transparency into AI/ML algorithms designed for clinical use, and that Shapley values are a useful approach to providing that transparency, which in turn may improve tool adoption and clinical utility.

JAMIA OpenVol. 9(1)
Beth Israel Deaconess Medical Center (US), Emory Healthcare (US), Harvard University (US), Emory University (US), University of Illinois Urbana-Champaign (US), Chicago Institute for Psychoanalysis (US), OSF Saint Francis Medical Center (US), Beaumont Hospital, Royal Oak (US), Jesse Brown VA Medical Center (US), Mercy Hospital (US), Jefferson Hospital (US), LifeBridge Health (US), University of California, Davis (US)
Openalex Percentile: Top 44%
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.