Home // HEALTHINFO 2025, The Tenth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article

Using Data and Artificial Intelligence to Enable Successful Hospital at Home Programs

Authors:
James McGlothlin

Keywords: care pathways; quality; artificial intelligence; predictive analytics; supervised learning; data mining; cardiology.

Abstract:
During the COVID-19 pandemic, health systems and payers had to take novel and extraordinary approaches to create hospital capacity and avoid hospital infections. Hospital at home programs have existed for years, but the pandemic environment led to additional interest, funding and reimbursement approvals for these programs. The hospital at home program is simply the monitoring and treatment of an acute inpatient patient at their residence. Research shows that outcomes and patient experience can be better with a hospital at home stay, while costs are much less. Nonetheless, these programs are relatively new and there are not well-researched standards for choosing patient cohorts or monitoring patient progress. Most hospitals either have a very restricted definition of eligible patients or leave the recommendation to the attending physician. While there are many case studies around the success of individual patients in hospital at home programs, there has been little research into choosing patient cohorts. In this study, we propose to use existing research around clinical trial enrollment and clinical data mining to better identify patient cohorts. We propose to use existing predictive analytics solutions to predict outcomes, adverse events and resource needs for individual patients. By combining all of these approaches, we can identify patients who are likely to succeed with hospital at home treatment, and we can monitor these patients and intervene to avoid risk of complications or adverse events.

Pages: 68 to 69

Copyright: Copyright (c) IARIA, 2025

Publication date: October 26, 2025

Published in: conference

ISSN: 2519-8491

ISBN: 978-1-68558-312-5

Location: Barcelona, Spain

Dates: from October 26, 2025 to October 30, 2025