Skip to main content
Abstract Articles

Large Language Models for the Prediction of Hospital Discharge in Medical and Surgical Inpatients

Authors: Anthea L Bell ( University of Michigan Medical School) , Natalie M Guzman ( University of Michigan Medical School) , Karan Desai ( University of Michigan Medical School) , Veronica L Gilbert ( University of Michigan Medical School) , Sam Lehn ( University of Michigan Medical School) , Jonathan Spagnoli ( University of Michigan Medical School) , Andrew Wong MD ( University of Michigan Medical School)

  • Large Language Models for the Prediction of Hospital Discharge in Medical and Surgical Inpatients

    Abstract Articles

    Large Language Models for the Prediction of Hospital Discharge in Medical and Surgical Inpatients

    Authors: , , , , , ,

Download

Downloads:
Download HTML

2be29e99-f258-4ee5-ad29-9706d262280c

Introduction

Accurate discharge prediction is critical for health care delivery, affecting key factors in healthcare operations including scheduling, bed utilization, capacity management, and patient satisfaction1. While large language models (LLMs) have demonstrated effectiveness in healthcare operational tasks, including length of stay prediction and readmission forecasting,2 their performance can vary based on operational factors such as hospital-specific clinical workflows, primary service team preferences, and cultural differences in care. This study analyzed the ability of a LLM to predict hospital discharge among patients hospitalized at a large academic medical center, identified performance barriers for LLM success, and developed optimization strategies for improving future LLM performance.

Methods

Same-day discharge predictions were generated using the Llama 3.3-70B model for a randomized dataset of 1,000 inpatients at a tertiary academic medical center hospitalized from January 1, 2024 through December 31, 2024. Two-step prompting was used to generate a binary discharge prediction (1=discharge, 0=no discharge) and a clinical explanation to support this prediction. Clinical notes from the previous day through 6am on prediction day were provided to the model. To characterize errors made by the model, a qualitative analysis was performed on 202 prediction errors (24 false positives, 178 false negatives) by four trained reviewers. Reviewers examined clinical documentation, model predictions, and model reasoning outputs to identify discordance patterns and extract representative examples.

Results

False positives (n=24) occurred due to inadequate knowledge of specialty-specific discharge protocols, failure to account for patient preferences despite clinical readiness, and reliance on sparse or outdated documentation. False negatives (n=178) resulted from excessive conservatism in prediction thresholds, overemphasis on early hospitalization events, inability to distinguish inpatient versus outpatient management requirements, and overweighting surgical complexity rather than current clinical stability.

Conclusions

LLMs have the potential to improve discharge prediction accuracy, but require integration of institution and specialty-specific clinical knowledge to improve reasoning capabilities. Service-specific interventions including targeted prompting for recovery protocols, improved distinction between inpatient and outpatient care needs, and better incorporation of current patient status over historical complexity may optimize model performance. These improvements could enhance resource allocation efficiency and support safer discharge decisions across inpatient populations.

References

  1. Barnes S, Hamrock E, Toerper M, et al. Real-time prediction of inpatient length of stay for discharge prioritization. J Am Med Inform Assoc. 2016;23(e1):e2-e10. doi:10.1093/jamia/ocv106

  2. Jiang LY, Liu XC, Nejatian NP, et al. Health system-scale language models are all-purpose prediction engines. Nature. 2023;619(7969):357-362. doi:10.1038/s41586-023-06160-y

26 Views

7 Downloads

Published on
19 Jun 2026
Peer Reviewed

Publication details

  • Article Number: 13

Competing Interests

  • The authors have no conflicts of interest to disclose.

Jump to

File Checksums (MD5)

  • HTML: 3d52f9caf98e077b9e5eb4ae3cf0b6db