AUTHOR=Gokhale Swapna , Taylor David , Gill Jaskirath , Hu Yanan , Zeps Nikolajs , Lequertier Vincent , Prado Luis , Teede Helena , Enticott Joanne 

TITLE=Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis

JOURNAL=Frontiers in Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1192969

DOI=10.3389/fmed.2023.1192969

ISSN=2296-858X

ABSTRACT=Background: Unwarranted extended length of stay (LOS) increases the risk of hospital acquired complications, morbidity and all-cause mortality, and needs to be recognised and addressed proactively.Objective: Systematic review to identify validated prediction variables and methods used in tools that predict risk of prolonged LOS in all hospital admissions and specifically General Medicine (GenMed) admissions.Method: LOS prediction tools published since 2010 were identified in 5 major research databases. Main outcomes: model performance metrics, prediction variables and level of validation. Meta-analysis was completed for validated models. Risk of bias was assessed using PROBAST checklist.Results: 22 all admission studies and 13 GenMed studies were identified. Statistical and machine learning methods were used almost equally in both groups. Calibration metrics were reported infrequently, with only 2/35 studies performing external validation. Meta-analysis of all admissions validation studies revealed 95% prediction interval for theta of 0.596, 0.798 for area under curve. Important predictor categories: comorbidity diagnoses and illness severity risk scores, demographics and admission characteristics. Overall study quality was deemed low due to poor data processing and analysis reporting.To our knowledge, this is the first systematic review assessing the quality of risk prediction models for hospital LOS in GenMed and All Admissions groups. Notably, both machine learning and statistical modelling demonstrated good predictive performance, but models were infrequently externally validated and had poor overall study quality was low. Moving forward, a focus on quality methods by adoption of existing guidelines and external validation are needed before clinical application.Registration: PROSPERO (https://www.crd.york.ac.Ffundingk/PROSPERO/) (#CRD42021272198).