Accepted for/Published in: JMIR Formative Research
Date Submitted: Dec 29, 2023
Open Peer Review Period: Jan 12, 2024 - Mar 8, 2024
Date Accepted: Nov 7, 2024
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Chest X-Rays Done as Part of Hospital at Home Service Demonstrate Significant Consensus Between Imaging Specialists, Internal Medicine Specialists and Artificial Intelligence. A Prospective study of 260 Patients.
ABSTRACT
Background:
Home hospitalization is a modality growing in popularity worldwide. Telemedicine-controlled, hospital at home (HAH) services could replace traditional in-hospital departments for selected patients. The clinical data for such cases typically involves chest X-rays.
Objective:
The implementation, analysis and clinical assimilation of this modality into a HAH service has not been described yet. Our objective is to add this essential information to the realm of hospital-at-home, worldwide.
Methods:
A prospective follow-up, description, and analysis of our HAH patients’ population who underwent chest X-ray at home. We conducted a comparative analysis evaluating the level of agreement among three modalities: an imaging specialist, the attending physician and a designated algorithm of artificial intelligence (AI).
Results:
Between February 2021 and May 2023, 300 chest radiographs were performed at the homes of 260 patients with a median age of 78 years [IQR 65 – 87]. 95% of the X-rays were interpreted by the attending physician, round 10% by a specialized radiologist, and ~32% by an AI software. The raw agreement level among these three modalities was over 90%. The consensus level using the Cohen’s Kappa coefficient (Ϗ) showed substantial agreement (Ϗ value of 0.65) and moderate agreement (Ϗ value of 0.49) between the attending physician and the radiologist, as well as between the attending physician and the AI, respectively.
Conclusions:
Chest X-rays play a crucial role in the HAH setting. Interpretation by an experienced specialist in internal medicine demonstrates significant level of consensus with imaging specialists. However, interpretation by AI algorithms should be further developed and re-validated prior to clinical applications.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.