Solving the Revolving Door Problem: Machine Learning for Readmission Risk Assessment (original) (raw)

Abstract

In 2012 the United States passed legislation, penalizing hospitals for readmission of patients discharged within 30 days. However, many unknowns mean that hospitals cannot predict when each patient is appropriate to discharge. Through researching readmissions across the Thomas Jefferson University Hospital enterprise, we found that staff must make judgement calls based on their own clinical perspectives. Rather than expecting doctors to somehow intuit the interaction effects from thousands of variables, we surface trends and present strategies for mitigating readmission risks through machine learning (ML). Commonly, ML models are trained against data aggregated from various sources. This method of sourcing interferes with responding to population-based risk factors and variables that are specific to the hospital of interest. However, creating a custom model presents its own set of hurdles. The work of our team provides hospitals everywhere with an end-to-end pipeline to create a readmissions assessment tool, using their own data.

Similar content being viewed by others

References

  1. Robinson, R., Hudali, T.: The HOSPITAL score and LACE index as predictors of 30-day readmission in a retrospective study at a university-affiliated community hospital. PeerJ 5, e3137 (2017). https://doi.org/10.7717/peerj.3137
    Article Google Scholar
  2. van Walraven, C., Dhalla, I.A., Bell, C., Etchells, E., Stiell, I.G., Zarnke, K., Forster, A.J.: Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. Cmaj 182(6), 551–557 (2010). https://doi.org/10.1503/cmaj.091117
    Article Google Scholar
  3. Donzé, J.D., Williams, M.V., Robinson, E.J., et al.: International validity of the HOSPITAL score to predict 30-day potentially avoidable hospital readmissions. JAMA Intern. Med. 176(4), 496–502 (2016). https://doi.org/10.1001/jamainternmed.2015.8462
    Article Google Scholar
  4. Morgan, D.J., Bame, B., Zimand, P., et al.: Assessment of machine learning vs standard prediction rules for predicting hospital readmissions. JAMA Netw. Open. 2(3), e190348 (2019). 10.1001/jamanetworkopen.2019.0348
    Article Google Scholar
  5. Amarasingham, R., Moore, B.J., Tabak, Y.P., Drazner, M.H., Clark, C.A., Zhang, S., Halm, E.A.: An automated model to identify heart failure patients at risk for 30-day readmission or death using electronic medical record data. Med. Care 48(11), 981–988 (2010). https://doi.org/10.1097/MLR.0b013e3181ef60d9. PMID: 20940649. Issn Print: 0025-7079
    Article Google Scholar
  6. Holloway, J.J., Thomas, J.W., Shapiro, L.: Clinical and sociodemographic risk factors for readmission of medicare beneficiaries. Health Care Finan. Rev. 10(1), 27–36 (1988)
    Google Scholar
  7. Makam, A.N., Nguyen, O.K., Clark, C., Zhang, S., Xie, B., Mark Weinreich, M.D., Mortensen, E.M., Halm, E.A.: Predicting 30-day pneumonia readmissions using electronic health record data. J. Hosp. Med. 4, 209–216 (2017). https://doi.org/10.12788/jhm.2711
    Article Google Scholar
  8. Steventon, A., Billings, J.: Preventing hospital readmissions: the importance of considering ‘impactibility’, not just predicted risk. BMJ Qual. Saf. 26, 782–785 (2017)
    Article Google Scholar
  9. Goldfield, N.I., McCullough, E.C., Hughes, J.S., et al.: Identifying potentially preventable readmissions. Health Care Finan. Rev. 30(1), 75–91 (2008)
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. The DICE Group, Thomas Jefferson University Hospital, Philadelphia, PA, 19103, USA
    Alexander Mitts, Tiffany D’souza, Bryan Sadler, Dominick Battistini & David Vuong

Authors

  1. Alexander Mitts
  2. Tiffany D’souza
  3. Bryan Sadler
  4. Dominick Battistini
  5. David Vuong

Corresponding author

Correspondence toAlexander Mitts .

Editor information

Editors and Affiliations

  1. Institute for Advanced Systems Engineering, University of Central Florida, Orlando, FL, USA
    Tareq Ahram
  2. Campus du Moulin de la Housse, Université de Reims Champagne Ardenne GRESPI, Reims Cedex, France
    Redha Taiar
  3. Département de l’appareil locomoteur, Champ de l’Air, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
    Vincent Gremeaux-Bader
  4. Laboratory of Movement Analysis and Measurement, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
    Kamiar Aminian

Rights and permissions

© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Cite this paper

Mitts, A., D’souza, T., Sadler, B., Battistini, D., Vuong, D. (2020). Solving the Revolving Door Problem: Machine Learning for Readmission Risk Assessment. In: Ahram, T., Taiar, R., Gremeaux-Bader, V., Aminian, K. (eds) Human Interaction, Emerging Technologies and Future Applications II. IHIET 2020. Advances in Intelligent Systems and Computing, vol 1152. Springer, Cham. https://doi.org/10.1007/978-3-030-44267-5\_15

Download citation

Keywords

Publish with us