Skip to main content
SpringerLink
Log in

Combining Process Mining and Time Series Forecasting to Predict Hospital Bed Occupancy

  • Conference paper
  • First Online:
Health Information Science (HIS 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13705))

Included in the following conference series:

  • 632 Accesses

Abstract

This research investigates in how far AI methods can support the prediction of bed occupancy in hospital units based on individual patient data. We combine process mining and a Deep Spatial-Temporal Graph Modeling algorithm and show that this improves the performance of the prediction over existing approaches. To improve the model even more it is extended with knowledge available from patient records, like the day of the week, the time of the day, whether it is a vacation day or not and the amount of emergency cases per data point.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 84.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Despite these fluctuations, we still chose to keep the data from when the pandemic started in the dataset, since COVID-19 is not completely gone yet, it is still possible that there are patients with COVID-19 in the hospital.

  2. 2.

    We can see that during the Christmas holidays at the end of the year there is a decrease in occupied beds in the hospital. This is recurring every year.

  3. 3.

    A prediction looks at the number of patients of the last week (seven days).

  4. 4.
    figure a

    Where n is the number of observation, \(F_t\) is the predicted output value, \(A_t\) is the actual output value and t is the time point the value is predicted for.

References

  1. Akdemir, B., Çetinkaya, N.: Long-term load forecasting based on adaptive neural fuzzy inference system using real energy data. Energy Procedia 14, 794–799 (2012)

    Article  Google Scholar 

  2. Chatfield, C.: Time-Series Forecasting. Chapman and Hall/CRC (2000)

    Google Scholar 

  3. Daghistani, T.A., Elshawi, R., Sakr, S., Ahmed, A.M., Al-Thwayee, A., Al-Mallah, M.H.: Predictors of in-hospital length of stay among cardiac patients: a machine learning approach. Int. J. Cardiol. 288, 140–147 (2019)

    Article  Google Scholar 

  4. Dart, T., Cui, Y., Chatellier, G., Degoulet, P.: Analysis of hospitalised patient flows using data-mining. In: Studies in Health Technology and Informatics, pp. 263–268 (2003)

    Google Scholar 

  5. Domova, V., Sander-Tavallaey, S.: Visualization for quality healthcare: patient flow exploration. In: 2019 IEEE International Conference on Big Data (Big Data), pp. 1072–1079. IEEE (2019)

    Google Scholar 

  6. Gentimis, T., Ala’J, A., Durante, A., Cook, K., Steele, R.: Predicting hospital length of stay using neural networks on MIMIC III data. In: 2017 IEEE 15th International Conference on Dependable, Autonomic and Secure Computing, 15th International Conference on Pervasive Intelligence and Computing, 3rd International Conference on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech), pp. 1194–1201. IEEE (2017)

    Google Scholar 

  7. Hachesu, P.R., Ahmadi, M., Alizadeh, S., Sadoughi, F.: Use of data mining techniques to determine and predict length of stay of cardiac patients. Healthc. Inform. Res. 19(2), 121–129 (2013)

    Article  Google Scholar 

  8. Hall, R.: Patient flow. AMC 10, 12 (2013)

    Google Scholar 

  9. Hanne, T., Melo, T., Nickel, S.: Bringing robustness to patient flow management through optimized patient transports in hospitals. Interfaces 39(3), 241–255 (2009)

    Article  Google Scholar 

  10. Haraden, C., Resar, R.: Patient flow in hospitals: understanding and controlling it better. Front. Health Serv. Manag. 20(4), 3 (2004)

    Article  Google Scholar 

  11. Jay, N., Kohler, F., Napoli, A.: Using formal concept analysis for mining and interpreting patient flows within a healthcare network. In: Yahia, S.B., Nguifo, E.M., Belohlavek, R. (eds.) CLA 2006. LNCS (LNAI), vol. 4923, pp. 263–268. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78921-5_19

    Chapter  MATH  Google Scholar 

  12. Kalogirou, S.A.: Solar thermal systems: components and applications-introduction. Elsevier Ltd. (2012)

    Google Scholar 

  13. Klassen, R.D., Menor, L.J.: The process management triangle: an empirical investigation of process trade-offs. J. Oper. Manag. 25(5), 1015–1034 (2007)

    Article  Google Scholar 

  14. Leemans, S.J., Poppe, E., Wynn, M.T.: Directly follows-based process mining: exploration and a case study. In: 2019 International Conference on Process Mining (ICPM), pp. 25–32. IEEE (2019)

    Google Scholar 

  15. Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. arXiv preprint arXiv:1707.01926 (2017)

  16. Liu, F., Ren, X., Zhang, Z., Sun, X., Zou, Y.: Rethinking skip connection with layer normalization. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 3586–3598 (2020)

    Google Scholar 

  17. Moeke, D.: De meerwaarde van process mining bij het optimaliseren van de patient flow (2021)

    Google Scholar 

  18. de Murillas, E., Reijers, H.A., van der Aalst, W.M.: Case notion discovery and recommendation: automated event log building on databases. Knowl. Inf. Syst. 62(7), 2539–2575 (2020). https://doi.org/10.1007/s10115-019-01430-6

    Article  Google Scholar 

  19. Pofahl, W.E., Walczak, S.M., Rhone, E., Izenberg, S.D.: Use of an artificial neural network to predict length of stay in acute pancreatitis. Am. Surg. 64(9), 868 (1998)

    Google Scholar 

  20. Rado, O., Lupia, B., Leung, J.M.Y., Kuo, Y.-H., Graham, C.A.: Using simulation to analyze patient flows in a hospital emergency department in Hong Kong. In: Matta, A., Li, J., Sahin, E., Lanzarone, E., Fowler, J. (eds.) Proceedings of the International Conference on Health Care Systems Engineering. SPMS, vol. 61, pp. 289–301. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-01848-5_23

    Chapter  Google Scholar 

  21. Rojas, E., Munoz-Gama, J., Sepúlveda, M., Capurro, D.: Process mining in healthcare: a literature review. J. Biomed. Inform. 61, 224–236 (2016)

    Article  Google Scholar 

  22. Van Der Aalst, W.: Process mining. Commun. ACM 55(8), 76–83 (2012)

    Article  Google Scholar 

  23. Villa, S., Barbieri, M., Lega, F.: Restructuring patient flow logistics around patient care needs: implications and practicalities from three critical cases. Health Care Manag. Sci. 12(2), 155–165 (2009). https://doi.org/10.1007/s10729-008-9091-6

    Article  Google Scholar 

  24. Villa, S., Prenestini, A., Giusepi, I.: A framework to analyze hospital-wide patient flow logistics: evidence from an Italian comparative study. Health Policy 115(2–3), 196–205 (2014)

    Article  Google Scholar 

  25. Walczak, S., et al.: Predicting hospital length of stay with neural networks. In: FLAIRS Conference, pp. 333–337 (1998)

    Google Scholar 

  26. Walley, P., Silvester, K., Steyn, R., Conway, J.B.: Managing variation in demand: lessons from the UK national health service/practitioner application. J. Healthc. Manag. 51(5), 309 (2006)

    Google Scholar 

  27. Weisstein, E.W.: Adjacency matrix (2007). https://mathworld.wolfram.com/

  28. Wu, Z., Pan, S., Long, G., Jiang, J., Zhang, C.: Graph WaveNet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121 (2019)

Download references

Author information

Authors and Affiliations

  1. Vrije Universiteit Amsterdam, De Boelelaan 1105, 1081 HV, Amsterdam, The Netherlands

    Annelore Jellemijn Pieters & Stefan Schlobach

Authors
  1. Annelore Jellemijn Pieters
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stefan Schlobach
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Stefan Schlobach .

Editor information

Editors and Affiliations

  1. University of São Paulo, São Carlos, Brazil

    Agma Traina

  2. Victoria University, Melbourne, VIC, Australia

    Hua Wang

  3. Tsinghua University, Beijing, China

    Yong Zhang

  4. Victoria University, Footscray, VIC, Australia

    Siuly Siuly

  5. Swinburne University of Technology, Hawthorn, VIC, Australia

    Rui Zhou

  6. Swinburne University of Technology, Hawthorn, VIC, Australia

    Lu Chen

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Pieters, A.J., Schlobach, S. (2022). Combining Process Mining and Time Series Forecasting to Predict Hospital Bed Occupancy. In: Traina, A., Wang, H., Zhang, Y., Siuly, S., Zhou, R., Chen, L. (eds) Health Information Science. HIS 2022. Lecture Notes in Computer Science, vol 13705. Springer, Cham. https://doi.org/10.1007/978-3-031-20627-6_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20627-6_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20626-9

  • Online ISBN: 978-3-031-20627-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation