Early Prediction of Pediatric In-Hospital Cardiac Arrest Using a Tabular Foundation Model

Tuesday, March 24, 2026

10:00 AM - 11:00 AM Central Time

Location: Connections Central - RST 18

SB

Stephanie R. Brown, MBBS, MS

null
null

Disclosure information not submitted.
YX

Yuzhang Xie, MS

Doctoral Student
Emory University Nell Hodgson Woodruff School of Nursing

Disclosure information not submitted.
JG

Jocelyn Grunwell, MD, PhD, MSCR

Associate Professor
Emory University/Children's Healthcare of Atlanta

Disclosure information not submitted.
XH

Xiao Hu, PhD

Professor
Emory University School of Nursing

Disclosure information not submitted.
CY

Carl Yang, PhD

Assistant Professor
Emory University Nell Hodgson Woodruff School of Nursing

Disclosure information not submitted.
SK

Saurabh Kataria, PhD

Post Doctoral Fellow
Emory University Nell Hodgson Woodruff School of Nursing

Disclosure information not submitted.
dB

delgersuren Bold, MS

Research Informatics Specialist
Emory University Nell Hodgson Woodruff School of Nursing

Disclosure information not submitted.
JL

Jiaying Lu, PhD

Assistant Professor
Emory University School of Nursing

Disclosure information not submitted.

Introduction: In-hospital cardiac arrest (IHCA) is an important cause of morbidity and mortality in children. IHCA prediction to prevent events remains a challenge in the pediatric intensive care unit (PICU). Machine learning algorithms have been used successfully for clinical predictions tasks. An emerging approach is the use of foundation models, pre-trained on unrelated datasets, for this purpose. Tabular Prior-data Fitted Network (TabPFN) is a recently published foundation model designed for tabular data, such as electronic health record data. Our objective was to evaluate the ability of TabPFN to predict IHCA in PICU patients 6 hours after admission compared to traditional machine learning algorithms.

Methods: Retrospective cohort study of PICU patients from 1/6/2016-30/5/2022. Features included demographics, vital signs, assessments, laboratory values and medications from the first 6 hours of admission. We compared TabPFN to multiple traditional machine learning algorithms (K-Nearest Neighbor, Random Forest, LightGBM, XGBoost and Tabular Neural Network) for model development.

Results: IHCA occurred in 175/14,050 encounters (1.2%). TabPFN had the best performance (AUROC 0.84, AUPRC 0.16) followed by Random Forest (AUROC 0.83, AUPRC 0.12). Negative predictive value was >98.8% for all algorithms, however positive predictive value was low (2.9-5.1%).

Conclusions: We have demonstrated a modest ability to identify children at risk of IHCA early in their ICU admission, this may be improved by developing models that re-evaluate risk over time. Though the TabPFN model was not developed using pediatric ICU data, it outperformed the other algorithms highlighting the potential of this approach.