دورية أكاديمية
أعرض في EDS

Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA).

التفاصيل البيبلوغرافية
العنوان: Identifying low acuity Emergency Department visits with a machine learning approach: The low acuity visit algorithms (LAVA).
المؤلفون: Chen AT; Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.; Health Care Management Department, The Wharton School, University of Pennsylvania, Philadelphia, Pennsylvania, USA.; Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania, USA., Kuzma RS; Emergency Medicine Department, University of Pennsylvania, Philadelphia, Pennsylvania, USA., Friedman AB; Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.; Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, Pennsylvania, USA.; Emergency Medicine Department, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
المصدر: Health services research [Health Serv Res] 2024 Aug; Vol. 59 (4), pp. e14305. Date of Electronic Publication: 2024 Mar 30.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Blackwell Country of Publication: United States NLM ID: 0053006 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1475-6773 (Electronic) Linking ISSN: 00179124 NLM ISO Abbreviation: Health Serv Res Subsets: MEDLINE
أسماء مطبوعة: Publication: Malden, MA : Blackwell
Original Publication: Chicago, Hospital Research and Educational Trust.
مواضيع طبية MeSH: Emergency Service, Hospital*/statistics & numerical data , Machine Learning* , Algorithms*, Humans ; Male ; Female ; Middle Aged ; Adult ; Aged ; Adolescent ; Patient Acuity ; International Classification of Diseases ; Young Adult ; Child ; United States ; Logistic Models ; Age Factors ; Child, Preschool ; Sex Factors ; Emergency Room Visits
مستخلص: Objective: To improve the performance of International Classification of Disease (ICD) code rule-based algorithms for identifying low acuity Emergency Department (ED) visits by using machine learning methods and additional covariates.
Data Sources: We used secondary data on ED visits from the National Hospital Ambulatory Medical Survey (NHAMCS), from 2016 to 2020.
Study Design: We established baseline performance metrics with seven published algorithms consisting of International Classification of Disease, Tenth Revision codes used to identify low acuity ED visits. We then trained logistic regression, random forest, and gradient boosting (XGBoost) models to predict low acuity ED visits. Each model was trained on five different covariate sets of demographic and clinical data. Model performance was compared using a separate validation dataset. The primary performance metric was the probability that a visit identified by an algorithm as low acuity did not experience significant testing, treatment, or disposition (positive predictive value, PPV). Subgroup analyses assessed model performance across age, sex, and race/ethnicity.
Data Collection: We used 2016-2019 NHAMCS data as the training set and 2020 NHAMCS data for validation.
Principal Findings: The training and validation data consisted of 53,074 and 9542 observations, respectively. Among seven rule-based algorithms, the highest-performing had a PPV of 0.35 (95% CI [0.33, 0.36]). All model-based algorithms outperformed existing algorithms, with the least effective-random forest using only age and sex-improving PPV by 26% (up to 0.44; 95% CI [0.40, 0.48]). Logistic regression and XGBoost trained on all variables improved PPV by 83% (to 0.64; 95% CI [0.62, 0.66]). Multivariable models also demonstrated higher PPV across all three demographic subgroups.
Conclusions: Machine learning models substantially outperform existing algorithms based on ICD codes in predicting low acuity ED visits. Variations in model performance across demographic groups highlight the need for further research to ensure their applicability and fairness across diverse populations.
(© 2024 The Authors. Health Services Research published by Wiley Periodicals LLC on behalf of Health Research and Educational Trust.)
References: JAMA. 2023 Sep 5;330(9):807-808. (PMID: 37566405)
BMC Health Serv Res. 2020 Aug 24;20(1):775. (PMID: 32838764)
Health Aff (Millwood). 2010 Sep;29(9):1630-6. (PMID: 20820018)
Health Serv Res. 2018 Aug;53 Suppl 1:3189-3206. (PMID: 29244202)
Epidemiol Rev. 2013;35:75-83. (PMID: 23372025)
Health Aff (Millwood). 1993 Spring;12(1):162-73. (PMID: 8509018)
Am J Emerg Med. 2014 Feb;32(2):175-7. (PMID: 24332901)
Am J Epidemiol. 2013 Mar 1;177(5):443-52. (PMID: 23364879)
JAMA Netw Open. 2023 Oct 2;6(10):e2337557. (PMID: 37824142)
Ann Emerg Med. 2007 Mar;49(3):257-64, 264.e1. (PMID: 17049408)
Health Aff (Millwood). 2013 Dec;32(12):2116-21. (PMID: 24301394)
JAMA Netw Open. 2018 Oct 5;1(6):e183731. (PMID: 30646254)
J Ambul Care Manage. 2008 Oct-Dec;31(4):370-6. (PMID: 18806596)
CJEM. 2015 Jul;17(4):359-66. (PMID: 26134052)
Eur J Public Health. 2019 Dec 1;29(6):1024-1030. (PMID: 31089678)
Health Policy. 2015 Nov;119(11):1415-23. (PMID: 26428441)
Age Ageing. 2018 Sep 1;47(5):727-733. (PMID: 29788032)
Ann Emerg Med. 2013 Nov;62(5):498-505.e3. (PMID: 23623558)
SSM Popul Health. 2016 Aug 03;2:512-524. (PMID: 29349167)
J Am Coll Emerg Physicians Open. 2021 Jan 14;2(1):e12349. (PMID: 33490998)
JAMA Health Forum. 2023 Jun 2;4(6):e231197. (PMID: 37266959)
Health Serv Res. 2022 Aug;57(4):979-989. (PMID: 35619335)
Ann Intern Med. 2015 Jan 6;162(1):55-63. (PMID: 25560714)
Health Serv Res. 2016 Dec;51(6):2358-2374. (PMID: 26891974)
J Emerg Nurs. 2020 Jul;46(4):478-487. (PMID: 32507725)
Health Serv Res. 2024 Aug;59(4):e14305. (PMID: 38553999)
Cad Saude Publica. 2009 Jan;25(1):7-28. (PMID: 19180283)
Health Aff (Millwood). 2012 Aug;31(8):1757-66. (PMID: 22869654)
N Engl J Med. 2020 Aug 27;383(9):874-882. (PMID: 32853499)
Acad Emerg Med. 2001 Nov;8(11):1030-6. (PMID: 11691664)
معلومات مُعتمدة: R03 AG078933 United States AG NIA NIH HHS; T32 AG051090 United States AG NIA NIH HHS; Wharton School, University of Pennsylvania (Wharton AI and Analytics for Business); 1R03AG078933-01 United States AG NIA NIH HHS
فهرسة مساهمة: Keywords: Emergency Department; ICD‐10; algorithms; low acuity; machine learning; predictive modeling
تواريخ الأحداث: Date Created: 20240330 Date Completed: 20240716 Latest Revision: 20240718
رمز التحديث: 20240718
مُعرف محوري في PubMed: PMC11249839
DOI: 10.1111/1475-6773.14305
PMID: 38553999
قاعدة البيانات: MEDLINE
الوصف
تدمد:1475-6773
DOI:10.1111/1475-6773.14305