Skip to main content

Advertisement

SpringerLink
Log in

A machine learning model for predicting risk of hospital readmission within 30 days of discharge: validated with LACE index and patient at risk of hospital readmission (PARR) model

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

The objective of this study was to design and develop a predictive model for 30-day risk of hospital readmission using machine learning techniques. The proposed predictive model was then validated with the two most commonly used risk of readmission models: LACE index and patient at risk of hospital readmission (PARR). The study cohort consisted of 180,118 admissions with 22,565 (12.5%) of actual readmissions within 30 days of hospital discharge, from 01 Jan 2015 to 31 Dec 2016 from two Auckland-region hospitals. We developed a machine learning model to predict 30-day readmissions using the model types XGBoost, Random Forests, and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the F1-score (0.386 ± 0.006), sensitivity (0.598 ± 0.013), positive predictive value (PPV) (0.285 ± 0.004), and negative predictive value (NPV) (0.932 ± 0.002). When compared with LACE and PARR(NZ) models, the proposed model achieved better F1-score by 12.7% compared with LACE and 23.2% compared with PARR(NZ). The mean sensitivity of the proposed model was 6.0% higher than LACE and 41% higher than PARR(NZ). The mean PPV was 15.9% and 14.6% higher than LACE and PARR(NZ) respectively. We presented an all-cause predictive model for 30-day risk of hospital readmission with an area under the receiver operating characteristics (AUROC) of 0.75 for the entire dataset.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Hernandez AF, Greiner MA, Fonarow GC, Hammill BG, Heidenreich PA, Yancy CW, Peterson ED, Curtis LH (2010) Relationship between early physician follow-up and 30-day readmission among Medicare beneficiaries hospitalized for heart failure. Jama 303(17):1716–1722

    Article  CAS  Google Scholar 

  2. Lindenauer PK, Bernheim SM, Grady JN, Lin Z, Wang Y, Wang Y, Merrill AR, Han LF, Rapp MT, Drye EE, Normand SL, Krumholz HM (2010) The performance of US hospitals as reflected in risk-standardized 30-day mortality and readmission rates for Medicare beneficiaries with pneumonia. J Hosp Med 5(6):E12–E18

    Article  Google Scholar 

  3. Blakely T et al (2015) Updated New Zealand health system cost estimates from health events by sex, age and proximity to death: further improvements in the age of ‘big data’. N Z Med J 128(1422):13–23

    PubMed  Google Scholar 

  4. Devlin N, Maynard A, Mays N (2001) New Zealand’s new health sector reforms: back to the future? BMJ: Br Med J 322(7295):1171

    Article  CAS  Google Scholar 

  5. Ali AM et al (2017) Factors associated with 30-day readmission after primary total hip arthroplasty: analysis of 514 455 procedures in the UK National Health Service. JAMA Surg 152(12):e173949–e173949

    Article  Google Scholar 

  6. Jurawan N, Pankhurst T, Ferro C, Nightingale P, Coleman J, Rosser D, Ball S (2017) Hospital acquired acute kidney injury is associated with increased mortality but not increased readmission rates in a UK acute hospital. BMC Nephrol 18(1):317

    Article  Google Scholar 

  7. Rumball-Smith J, Hider P (2009) The validity of readmission rate as a marker of the quality of hospital care, and a recommendation for its definition. N Z Med J(Online) 122(1289)

  8. Shulan M, Gao K, Moore CD (2013) Predicting 30-day all-cause hospital readmissions. Health Care Manag Sci 16(2):167–175. https://doi.org/10.1007/s10729-013-9220-8

  9. Yam C et al (2010) Measuring and preventing potentially avoidable hospital readmissions: a review of the literature. Hong Kong Medical Journal = Xianggang yi xue za zhi 16(5):383–389

  10. Kansagara D et al (2011) Risk prediction models for hospital readmission: a systematic review. Jama 306(15):1688–1698

    Article  CAS  Google Scholar 

  11. Holloway JJ, Thomas JW (1989) Factors influencing read mission risk: implications for quality monitoring. Health Care Financ Rev 11(2):19–32

    CAS  PubMed  PubMed Central  Google Scholar 

  12. Maali Y, Perez-Concha O, Coiera E, Roffe D, Day RO, Gallego B (2018) Predicting 7-day, 30-day and 60-day all-cause unplanned readmission: a case study of a Sydney hospital. BMC Med Inform Decis Mak 18(1):1

    Article  Google Scholar 

  13. van Walraven C, Dhalla IA, Bell C, Etchells E, Stiell IG, Zarnke K, Austin PC, Forster AJ (2010) Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. Can Med Assoc J 182(6):551–557

    Article  Google Scholar 

  14. Billings J et al (2012) Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30). BMJ Open 2(4):e001667

    Article  Google Scholar 

  15. Vaithianathan R, Jiang N, Ashton T (2012) A model for predicting readmission risk in New Zealand. AUT University, Faculty of Business and Law

    Google Scholar 

  16. Ross, S., et al. Learning message-passing inference machines for structured prediction. in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. 2011. IEEE

  17. Rajkomar A et al (2018) Scalable and accurate deep learning with electronic health records. NPJ Digit Med 1(1):18

    Article  Google Scholar 

  18. Freitag D (2000) Machine learning for information extraction in informal domains. Mach Learn 39(2–3):169–202

    Article  Google Scholar 

  19. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139

    Article  Google Scholar 

  20. Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. ACM

  21. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  Google Scholar 

  22. Paul M, Bougouin W, Geri G, Dumas F, Champigneulle B, Legriel S, Charpentier J, Mira JP, Sandroni C, Cariou A (2016) Delayed awakening after cardiac arrest: prevalence and risk factors in the Parisian registry. Intensive Care Med 42(7):1128–1136

    Article  CAS  Google Scholar 

  23. Vaziri K, Pershing S, Albini TA, Moshfeghi DM, Moshfeghi AA (2015) Risk factors predictive of endogenous endophthalmitis among hospitalized patients with hematogenous infections in the United States. Am J Ophthalmol 159(3):498–504

    Article  Google Scholar 

  24. Carpenter CR, Shelton E, Fowler S, Suffoletto B, Platts-Mills TF, Rothman RE, Hogan TM (2015) Risk factors and screening instruments to predict adverse outcomes for undifferentiated older emergency department patients: a systematic review and meta-analysis. Acad Emerg Med 22(1):1–21

    Article  Google Scholar 

  25. Chan MK, Bhatti H, Meader N, Stockton S, Evans J, O'Connor RC, Kapur N, Kendall T (2016) Predicting suicide following self-harm: systematic review of risk factors and risk scales. Br J Psychiatry 209(4):277–283

    Article  Google Scholar 

  26. Berry JG, Gay JC, Maddox KJ, Coleman EA, Bucholz EM, O’Neill MR, Blaine K, Hall M (2018) Age trends in 30 day hospital readmissions: US national retrospective analysis. BMJ 360:k497

    Article  Google Scholar 

  27. Escobar GJ, Ragins A, Scheirer P, Liu V, Robles J, Kipnis P (2015) Nonelective rehospitalizations and postdischarge mortality: predictive models suitable for use in real time. Med Care 53(11):916

    Article  Google Scholar 

  28. van Walraven C, Wong J, Forster AJ, Hawken S (2013) Predicting post-discharge death or readmission: deterioration of model performance in population having multiple admissions per patient. J Eval Clin Pract 19(6):1012–1018

    Article  Google Scholar 

Download references

Acknowledgments

We would like to thank the clinicians at Waitemata District Health Board and Auckland District Health Board for their clinical advice. We would also like to thank researchers and data scientists for their contributions.

Funding

This research was supported by the Precision Driven Health research partnership.

Author information

Authors and Affiliations

  1. Data Science Team, Orion Health, 181, Grafton Road, Grafton, Auckland, New Zealand

    Mirza Mansoor Baig, Ning Hua, Edmond Zhang, Reece Robinson & Anna Spyker

  2. Clinical Research Team, North Shore Hospital, Waitemata District Health Board, Auckland, New Zealand

    Delwyn Armstrong, Robyn Whittaker & Tom Robinson

  3. Clinical Quality & Safety Service, Auckland City Hospital, Auckland District Health Board, Auckland, New Zealand

    Ehsan Ullah

Authors
  1. Mirza Mansoor Baig
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ning Hua
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Edmond Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Reece Robinson
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Anna Spyker
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Delwyn Armstrong
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Robyn Whittaker
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Tom Robinson
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Ehsan Ullah
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mirza Mansoor Baig.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants performed by any of the authors.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Baig, M.M., Hua, N., Zhang, E. et al. A machine learning model for predicting risk of hospital readmission within 30 days of discharge: validated with LACE index and patient at risk of hospital readmission (PARR) model. Med Biol Eng Comput 58, 1459–1466 (2020). https://doi.org/10.1007/s11517-020-02165-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-020-02165-1

Keywords

Search

Navigation