Machine learning in the prediction of medical inpatient length of stay - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2022 Feb;52(2):176-185.
doi: 10.1111/imj.14962. Epub 2021 Oct 27.

Machine learning in the prediction of medical inpatient length of stay

Stephen Bacchi  1   2 , Yiran Tan  1   2 , Luke Oakden-Rayner  1   2 , Jim Jannes  1   2 , Timothy Kleinig  1   2 , Simon Koblar  1   2
Affiliations
Review

Machine learning in the prediction of medical inpatient length of stay

Stephen Bacchi et al. Intern Med J. 2022 Feb.

Abstract

Length of stay (LOS) estimates are important for patients, doctors and hospital administrators. However, making accurate estimates of LOS can be difficult for medical patients. This review was conducted with the aim of identifying and assessing previous studies on the application of machine learning to the prediction of total hospital inpatient LOS for medical patients. A review of machine learning in the prediction of total hospital LOS for medical inpatients was conducted using the databases PubMed, EMBASE and Web of Science. Of the 673 publications returned by the initial search, 21 articles met inclusion criteria. Of these articles the most commonly represented medical specialty was cardiology. Studies were also identified that had specifically evaluated machine learning LOS prediction in patients with diabetes and tuberculosis. The performance of the machine learning models in the identified studies varied significantly depending on factors including differing input datasets and different LOS thresholds and outcome metrics. Common methodological shortcomings included a lack of reporting of patient demographics and lack of reporting of clinical details of included patients. The variable performance reported by the studies identified in this review supports the need for further research of the utility of machine learning in the prediction of total inpatient LOS in medical patients. Future studies should follow and report a more standardised methodology to better assess performance and to allow replication and validation. In particular, prospective validation studies and studies assessing the clinical impact of such machine learning models would be beneficial.

Keywords: artificial intelligence; deep learning; neural network; predictive analytics.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Robinson G, Davis L, Leifer R. Prediction of hospital length of stay. Health Serv Res 1966; 1: 287-300.
    1. Handelman GS, Kok HK, Chandra RV, Razavi AH, Lee MJ, Asadi H. eDoctor: machine learning and the future of medicine. J Intern Med 2018; 284: 603-19.
    1. Deo R. Machine learning in medicine. Circulation 2015; 123: 1920-30.
    1. Pinker E. Reporting accuracy of rare event classifiers. NPJ Digit Med 2018; 1: 56.
    1. Rajkomar A, Dai AM, Sun M, Hardt M, Chen K, Rough K et al. Reply: metrics to assess machine learning models. NPJ Digit Med 2018; 1: 57.

LinkOut - more resources