View Item 

Show simple item record

Nonlinear association of nurse staffing and readmissions uncovered in machine learning analysis
dc.contributor.authorYakusheva, Olga
dc.contributor.authorBang, James T.
dc.contributor.authorHughes, Ronda G.
dc.contributor.authorBobay, Kathleen L.
dc.contributor.authorCosta, Linda
dc.contributor.authorWeiss, Marianne E.
dc.date.accessioned2022-04-08T18:06:00Z
dc.date.available2023-05-08 14:05:58en
dc.date.available2022-04-08T18:06:00Z
dc.date.issued2022-04
dc.identifier.citationYakusheva, Olga; Bang, James T.; Hughes, Ronda G.; Bobay, Kathleen L.; Costa, Linda; Weiss, Marianne E. (2022). "Nonlinear association of nurse staffing and readmissions uncovered in machine learning analysis." Health Services Research 57(2): 311-321.
dc.identifier.issn0017-9124
dc.identifier.issn1475-6773
dc.identifier.urihttps://hdl.handle.net/2027.42/172056
dc.description.abstractObjectiveSeveral studies of nurse staffing and patient outcomes found a curvilinear or U‐shaped relationship, with benefits from additional nurse staffing diminishing or reversing at high staffing levels. This study examined potential diminishing returns to nurse staffing and the existence of a “tipping point” or the level of staffing after which higher nurse staffing no longer improves and may worsen readmissions.Data Sources/Study SettingThe Readiness Evaluation And Discharge Interventions (READI) study database of over 130,000 adult (18+) inpatient discharges from 62 medical, surgical, and medical‐surgical (noncritical care) units from 31 United States (US) hospitals during October 2014–March 2017.Study DesignObservational cross‐sectional study using a fully nonparametric random forest machine learning method. Primary exposure was nurse hours per patient day (HPPD) broken down by registered nurses (nonovertime and overtime) and nonlicensed nursing personnel. The outcome was 30‐day all‐cause same‐hospital readmission. Partial dependence plots were used to visualize the pattern of predicted patient readmission risk along a range of unit staffing levels, holding all other patient characteristics and hospital and unit structural variables constant.Data Collection/Extraction methodsSecondary analysis of the READI data. Missing values were imputed using the missing forest algorithm in R.Principal FindingsPartial dependence plots were U‐shaped, showing the readmission risk first declining and then rising with additional nurse staffing. The tipping points were at 6.95 and 0.21 HPPD for registered nurse staffing (nonovertime and overtime, respectively) and 2.91 HPPD of nonlicensed nursing personnel.ConclusionsThe U‐shaped association was consistent with diminishing returns to nurse staffing suggesting that incremental gains in readmission reduction from additional nurse staffing taper off and could reverse at high staffing levels. If confirmed in future causal analyses across multiple outcomes, accompanying investments in infrastructure and human resources may be needed to maximize nursing performance outcomes at higher levels of nurse staffing.
dc.publisherBlackwell Publishing Ltd
dc.publisherWiley Periodicals, Inc.
dc.subject.othernursing
dc.subject.otherreadmissions
dc.subject.otherunit staffing
dc.subject.othermachine learning
dc.subject.otherdiminishing returns
dc.titleNonlinear association of nurse staffing and readmissions uncovered in machine learning analysis
dc.typeArticle
dc.rights.robotsIndexNoFollow
dc.subject.hlbsecondlevelPublic Health
dc.subject.hlbtoplevelHealth Sciences
dc.description.peerreviewedPeer Reviewed
dc.description.bitstreamurlhttp://deepblue.lib.umich.edu/bitstream/2027.42/172056/1/hesr13695.pdf
dc.description.bitstreamurlhttp://deepblue.lib.umich.edu/bitstream/2027.42/172056/2/hesr13695_am.pdf
dc.identifier.doi10.1111/1475-6773.13695
dc.identifier.sourceHealth Services Research
dc.identifier.citedreferenceTang A, Foong J. A qualitative evaluation of random forest feature learning. In: Herawan T, Ghazali R, Deris M, editors. Recent Advances on Soft Computing and Data Mining Advances in Intelligent Systems and Computing; New York City, NY: Springer; 2014. p. 359 – 68.
dc.identifier.citedreferenceMark BA, Harless DW, McCue M, Xu Y. A longitudinal examination of hospital registered nurse staffing and quality of care. Health Serv Res. 2004; 39 ( 2 ): 279 ‐ 300.
dc.identifier.citedreferenceLankshear AJ, Sheldon TA, Maynard A. Nurse staffing and healthcare outcomes: a systematic review of the international research evidence. ANS Adv Nurs Sci. 2005; 28 ( 2 ): 163 ‐ 174.
dc.identifier.citedreferenceNeedleman J, Shekelle PG. More ward nursing staff improves inpatient outcomes, but how much is enough? BMJ Qual Saf. 2019; 28 ( 8 ): 603 ‐ 605.
dc.identifier.citedreferenceDonabedian A. Evaluating the quality of medical care. 1966. Milbank Q. 2005; 83 ( 4 ): 691 ‐ 729.
dc.identifier.citedreferenceMitchell PH, Ferketich S, Jennings BM. Quality health outcomes model. American Academy of Nursing expert panel on quality health care. Image J Nurs Sch. 1998; 30 ( 1 ): 43 ‐ 46.
dc.identifier.citedreferenceCraig C, Harris R. Total productivity measurement at the firm level. Sloan Manage Rev. 1973; 1973: 13 ‐ 28.
dc.identifier.citedreferenceAHA Annual Survey American Hospital Association. Chicago, IL: American Hospital Association; 2020.
dc.identifier.citedreferenceBobay K, Bahr SJ, Weiss ME, Hughes R, Costa L. Models of discharge Care in Magnet® hospitals. J Nurs Adm. 2015; 45 ( 10 ): 485 ‐ 491.
dc.identifier.citedreferenceJames G, Witten D, Hastie T, Tibshirani R. An Introduction to Statistical Learning. New York, NY: Springer; 2013.
dc.identifier.citedreferenceBiecek P. DALEX: Explainers for Complex Predictive Models in R. Journal of Machine Learning Research. 2018; 19: 1 ‐ 15. https://www.jmlr.org/papers/volume19/18-416/18-416.pdf.
dc.identifier.citedreferenceKuhn M, Wing J, Weston S, Williams A, Keefer C, Engelhardt A, et al. Caret: Classification and Regression Training. R Package Version 60‐84. Vienna, Austria: Institute for Statistics and Mathematics, Vienna University for Economics and Business; 2019. https://CRAN.R-project.org/package=caret.
dc.identifier.citedreferenceKong Y, Yu TA. Deep neural network model using random forest to extract feature representation for gene expression data classification. Sci Rep. 2018; 8: 16477.
dc.identifier.citedreferenceVens C, Costa F, eds. Random forest based feature induction. Paper presented at: IEEE 11th International Conference on Data Mining (ICDM); 2011: Vancouver, Canada.
dc.identifier.citedreferenceVieira SM, Kaymak U, Sousa JMC. Cohen’s kappa coefficient as a performance measure for feature selection. Barcelona, Spain: World Congress on Computational Intelligence; 2010. https://ieeexplore.ieee.org/document/5584447.
dc.identifier.citedreferenceMold JW, Hamm RM, McCarthy LH. The law of diminishing returns in clinical medicine: how much risk reduction is enough? J Am Board Fam Med. 2010; 23 ( 3 ): 371 ‐ 375.
dc.identifier.citedreferenceBadgery‐Parker T, Pearson SA, Dunn S, Elshaug AG. Measuring hospital‐acquired complications associated with low‐value care. JAMA Intern Med. 2019; 179 ( 4 ): 499 ‐ 505.
dc.identifier.citedreferenceKorenstein D, Chimonas S, Barrow B, Keyhani S, Troy A, Lipitz‐Snyderman A. Development of a conceptual map of negative consequences for patients of overuse of medical tests and treatments. JAMA Intern Med. 2018; 178 ( 10 ): 1401 ‐ 1407.
dc.identifier.citedreferenceWeiss ME, Bobay KL, Bahr SJ, Costa L, Hughes RG, Holland DE. A model for hospital discharge preparation: from case management to care transition. J Nurs Adm. 2015; 45 ( 12 ): 606 ‐ 614.
dc.identifier.citedreferenceChen YC, Guo YL, Chin WS, Cheng NY, Ho JJ, Shiao JS. Patient‐nurse ratio is related to Nurses’ intention to leave their job through mediating factors of burnout and job dissatisfaction. Int J Environ Res Public Health. 2019; 16 ( 23 ): 1 ‐ 14.
dc.identifier.citedreferenceTaking Action against Clinician Burnout: a Systems Approach to Professional Well‐Being: Consensus Study Report. Washington, DC: National Academies Press; 2019.
dc.identifier.citedreferenceJiang HJ, Stocks C, Wong CJ. Disparities between two common data sources on hospital nurse staffing. J Nurs Scholarsh. 2006; 38 ( 2 ): 187 ‐ 193.
dc.identifier.citedreferenceFriese CR, Xia R, Ghaferi A, Birkmeyer JD, Banerjee M. Hospitals in ‘Magnet’ program show better patient outcomes on mortality measures compared to non‐‘Magnet’ hospitals. Health Aff (Millwood). 2015; 34 ( 6 ): 986 ‐ 992.
dc.identifier.citedreferenceStatistical Brief #248. Healthcare Cost and Utilization Project (HCUP). Rockville, MD: Agency for Healthcare Research and Quality; 2019.
dc.identifier.citedreferenceKelly LA, McHugh MD, Aiken LH. Nurse outcomes in magnet® and non‐magnet hospitals. J Nurs Adm. 2012; 42 ( 10 suppl ): S44 ‐ S49.
dc.identifier.citedreferenceHamadi HY, Martinez D, Palenzuela J, Spaulding AC. Magnet hospitals and 30‐day readmission and mortality rates for Medicare beneficiaries. Med Care. 2021; 59 ( 1 ): 6 ‐ 12.
dc.identifier.citedreferenceJayawardhana J, Welton JM, Lindrooth RC. Is there a business case for magnet hospitals? Estimates of the cost and revenue implications of becoming a magnet. Med Care. 2014; 52 ( 5 ): 400 ‐ 406.
dc.identifier.citedreferenceGiuliano KK, Danesh V, Funk M. The relationship between nurse staffing and 30‐day readmission for adults with heart failure. J Nurs Adm. 2016; 46 ( 1 ): 25 ‐ 29.
dc.identifier.citedreferenceMcHugh M, Ma C. Hospital nursing and 30‐day readmissions among Medicare patients with heart failure, acute myocardial infarction, and pneumonia. J Nurs Adm. 2013; 43 ( 10 suppl ): S11 ‐ S18.
dc.identifier.citedreferenceWeiss ME, Yakusheva O, Bobay KL. Quality and cost analysis of nurse staffing, discharge preparation, and postdischarge utilization. Health Serv Res. 2011; 46 ( 5 ): 1473 ‐ 1494.
dc.identifier.citedreferenceMcHugh MD, Berez J, Small DS. Hospitals with higher nurse staffing had lower odds of readmissions penalties than hospitals with lower staffing. Health Aff (Millwood). 2013; 32 ( 10 ): 1740 ‐ 1747.
dc.identifier.citedreferenceAiken LH, Clarke SP, Sloane DM, Sochalski J, Silber JH. Hospital nurse staffing and patient mortality, nurse burnout, and job dissatisfaction. JAMA. 2002; 288 ( 16 ): 1987 ‐ 1993.
dc.identifier.citedreferenceAiken LH, Sloane DM, Bruyneel L, et al. Nurse staffing and education and hospital mortality in nine European countries: a retrospective observational study. Lancet. 2014; 383 ( 9931 ): 1824 ‐ 1830.
dc.identifier.citedreferenceGriffiths P, Maruotti A, Recio Saucedo A, et al. Nurse staffing, nursing assistants and hospital mortality: retrospective longitudinal cohort study. BMJ Qual Saf. 2019; 28 ( 8 ): 609 ‐ 617.
dc.identifier.citedreferenceNeedleman J, Buerhaus P, Pankratz VS, Leibson CL, Stevens SR, Harris M. Nurse staffing and inpatient hospital mortality. N Engl J Med. 2011; 364 ( 11 ): 1037 ‐ 1045.
dc.identifier.citedreferenceKane RL, Shamliyan TA, Mueller C, Duval S, Wilt TJ. The association of registered nurse staffing levels and patient outcomes: systematic review and meta‐analysis. Med Care. 2007; 45 ( 12 ): 1195 ‐ 1204.
dc.identifier.citedreferenceNeedleman J, Buerhaus P, Mattke S, Stewart M, Zelevinsky K. Nurse‐staffing levels and the quality of care in hospitals. N Engl J Med. 2002; 346 ( 22 ): 1715 ‐ 1722.
dc.identifier.citedreferenceNeedleman J, Buerhaus PI, Stewart M, Zelevinsky K, Mattke S. Nurse staffing in hospitals: is there a business case for quality? Health Aff (Millwood). 2006; 25 ( 1 ): 204 ‐ 211.
dc.identifier.citedreferenceOppel EM, Young GJ. Nurse staffing patterns and patient experience of care: an empirical analysis of U.S. hospitals. Health Serv Res. 2018; 53 ( 3 ): 1799 ‐ 1818.
dc.identifier.citedreferenceBlegen MA, Goode CJ, Reed L. Nurse staffing and patient outcomes. Nurs Res. 1998; 47 ( 1 ): 43 ‐ 50.
dc.working.doiNOen
dc.owningcollnameInterdisciplinary and Peer-Reviewed


Files in this item

Name:
hesr13695.pdf
Size:
1.992MB
Format:
PDF
View/Open
Name:
hesr13695_am.pdf
Size:
635.1KB
Format:
PDF
View/Open

Show simple item record

Remediation of Harmful Language

The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.

Accessibility

If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.