Document Open Access Logo

A Review of Dynamic Bayesian Network Techniques with Applications in Healthcare Risk Modelling

Authors Mohsen Mesgarpour, Thierry Chaussalet, Salma Chahed



PDF
Thumbnail PDF

File

OASIcs.SCOR.2014.89.pdf
  • Filesize: 393 kB
  • 12 pages

Document Identifiers

Author Details

Mohsen Mesgarpour
Thierry Chaussalet
Salma Chahed

Cite AsGet BibTex

Mohsen Mesgarpour, Thierry Chaussalet, and Salma Chahed. A Review of Dynamic Bayesian Network Techniques with Applications in Healthcare Risk Modelling. In 4th Student Conference on Operational Research. Open Access Series in Informatics (OASIcs), Volume 37, pp. 89-100, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2014)
https://doi.org/10.4230/OASIcs.SCOR.2014.89

Abstract

Coping with an ageing population is a major concern for healthcare organisations around the world. The average cost of hospital care is higher than social care for older and terminally ill patients. Moreover, the average cost of social care increases with the age of the patient. Therefore, it is important to make efficient and fair capacity planning which also incorporates patient centred outcomes. Predictive models can provide predictions which their accuracy can be understood and quantified. Predictive modelling can help patients and carers to get the appropriate support services, and allow clinical decision-makers to improve care quality and reduce the cost of inappropriate hospital and Accident and Emergency admissions. The aim of this study is to provide a review of modelling techniques and frameworks for predictive risk modelling of patients in hospital, based on routinely collected data such as the Hospital Episode Statistics database. A number of sub-problems can be considered such as Length-of-Stay and End-of-Life predictive modelling. The methodologies in the literature are mainly focused on addressing the problems using regression methods and Markov models, and the majority lack generalisability. In some cases, the robustness, accuracy and re-usability of predictive risk models have been shown to be improved using Machine Learning methods. Dynamic Bayesian Network techniques can represent complex correlations models and include small probabilities into the solution. The main focus of this study is to provide a review of major time-varying Dynamic Bayesian Network techniques with applications in healthcare predictive risk modelling.
Keywords
  • Healthcare Modelling
  • Dynamic Bayesian Network
  • Predictive Risk Modelling
  • Time-Varying
  • Hospital Administrative Data

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Shola Adeyemi and Thierry J Chaussalet. Models for extracting information on patient pathways. In Intelligent Patient Management, pages 171-182. Springer, 2009. Google Scholar
  2. Shola Adeyemi, Eren Demir, and Thierry Chaussalet. Towards an evidence-based decision making healthcare system management: Modelling patient pathways to improve clinical outcomes. Decision Support Systems, 55, 1:117-125, 2013. Google Scholar
  3. Amr Ahmed and Eric P Xing. Recovering time-varying networks of dependencies in social and biological studies. Proceedings of the National Academy of Sciences, 106(29):11878-11883, 2009. Google Scholar
  4. Paul Aylin, Alex Bottle, and Azeem Majeed. Use of administrative data or clinical databases as predictors of risk of death in hospital: comparison of models. BMJ: British Medical Journal, 334(7602):1044, 2007. Google Scholar
  5. Martin Bardsley, Theo Georghiou, Ludovic Chassin, Geraint Lewis, Adam Steventon, and Jennifer Dixon. Overlap of hospital use and social care in older people in england. Journal of health services research and policy, 17(3):133-139, 2012. Google Scholar
  6. John Billings, Ian Blunt, Adam Steventon, Theo Georghiou, Geraint Lewis, and Martin Bardsley. Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (parr-30). BMJ Open: e001667, 2(4), 2012. Google Scholar
  7. Christopher M Bishop and Nasser M Nasrabadi. Pattern recognition and machine learning, volume 1. springer New York, 2006. Google Scholar
  8. A. Blake, B. North, and M. Isard. Learning multi-class dynamics. In Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems II, pages 389-395, Cambridge, MA, USA, 1999. MIT Press. Google Scholar
  9. Ian Blunt, Martin Bardsley, Amy Grove, and Aileen Clarke. Classifying emergency 30-day readmissions in england using routine hospital data 2004-2010: what is the scope for reduction? Journal of Epidemiology and Community Health, 66(Suppl 1):A45-A45, 2012. Google Scholar
  10. Michael Caley and Khesh Sidhu. Estimating the future healthcare costs of an aging population in the uk: expansion of morbidity and the need for preventative care. Journal of Public Health, 33(1):117-122, 2011. Google Scholar
  11. S Chattopadhyay, P Ray, HS Chen, MB Lee, and HC Chiang. Suicidal risk evaluation using a similarity-based classifier. In Advanced Data Mining and Applications, pages 51-61. Springer, 2008. Google Scholar
  12. Xavier Chitnis, T Georghiou, A Steventon, and M Bardsley. The impact of the marie curie nursing service on place of death andhospital use at the end of life. https://www.mariecurie.org.uk/Documents/HEALTHCARE-PROFESSIONALS/Our%20impact/Marie%20Curie_Full%20Report_Final_Web.pdf, 2012.
  13. Richard J Cook and Jerald F Lawless. Statistical issues in modeling chronic disease in cohort studies. Statistics in Biosciences, 6:127-161, 2013. Google Scholar
  14. Chiara Cornalba. Clinical and operational risk: A bayesian approach. Methodology and Computing in Applied Probability, 11(1):47-63, 2009. Google Scholar
  15. Anthony J. Culyer and Joseph P. Newhouse. Handbook of Health Economics: Vol. 1A. Elsevier, 2000. Google Scholar
  16. Anthony J. Culyer, Mark V. Pauly, Joseph P. Newhouse, Thomas G. McGuire, and Pedro P. Barros. Handbook of Health Economics: Vol. 2. Elsevier, 2012. Google Scholar
  17. Thomas Dean and Keiji Kanazawa. A model for reasoning about persistence and causation. Computational intelligence, 5(2):142-150, 1989. Google Scholar
  18. DoH. Long term conditions compendium of information (third edition). https://www.gov.uk/government/uploads/system/uploads/attachment_data/file/216528/dh_134486.pdf, Apr. 2012.
  19. DoH. Business case: for the health and care modernisation transition programme. https://www.gov.uk/government/uploads/system/uploads/attachment_data/file/224140/TP_business_case_docx.pdf, 2013.
  20. Thi Duong, Dinh Phung, Hung Bui, and Svetha Venkatesh. Efficient duration and hierarchical modeling for human activity recognition. Artificial Intelligence, 173(7):830-856, 2009. Google Scholar
  21. Shahram Ebadollahi, Jimeng Sun, David Gotz, Jianying Hu, Daby Sow, and Chalapathy Neti. Predicting patient’s trajectory of physiological data using temporal trends in similar patients: A system for near-term prognostics. In AMIA Annual Symposium Proceedings, volume 2010, page 192. American Medical Informatics Association, 2010. Google Scholar
  22. Norman E Fenton and Martin D Neil. Risk Assessment and Decision Analysis with Bayesian Networks. CRC Press, 2012. Google Scholar
  23. Jonathan Agner Forsberg, Rikard Wedin, Bjarne H Bauer, Henrik CF andHansen, Minna Laitinen, Clement S Trovik, Johnny Keller, Patrick J Boland, and John H Healey. External validation of the bayesian estimated tools for survival (bets) models in patients with surgically treated skeletal metastases. BMC cancer, 12(1):493, 2012. Google Scholar
  24. G David Garson. Hierarchical linear modeling: Guide and applications. Sage, 2012. Google Scholar
  25. Seymour Geisser. Predictive interference: an introduction, volume 55. CRC Press, 1993. Google Scholar
  26. Deniz Gencaga, Ercan E. Kuruoglu, and Aysin Ertuzun. Modeling non-gaussian time-varying vector autoregressive processes by particle filtering. Multidimensional Systems and Signal Processing, 21(1):73-85, 2010. Google Scholar
  27. Theo. Georghiou, Sian Davies, Alisha Davies, and Martin Bradley. Understanding patterns of health and social care at the end of life. http://www.nuffieldtrust.org.uk/sites/files/nuffield/121016_understanding_patterns_of_health_and_social_care_full_report_final.pdf, Oct. 2012.
  28. Zoubin Ghahramani and Geoffrey E Hinton. Variational learning for switching state-space models. Neural computation, 12(4):831-864, 2000. Google Scholar
  29. David Gotz, Jimeng Sun, Nan Cao, and Shahram Ebadollahi. Visual cluster analysis in support of clinical decision intelligence. In AMIA Annual Symposium Proceedings, volume 2011, pages 481-490. American Medical Informatics Association, 2011. Google Scholar
  30. Susan Graham, Deborah Estrin, Eric Horvitz, Isaac Kohane, Elizabeth Mynatt, and Ida Sim. Information technology research challenges for healthcare: From discovery to delivery. ACM SIGHIT Record, 1(1):4-9, 2011. Google Scholar
  31. Fan Guo, Steve Hanneke, Wenjie Fu, and Eric P Xing. Recovering temporally rewiring networks: A model-based approach. In Proceedings of the 24th international conference on Machine learning, pages 321-328. ACM, 2007. Google Scholar
  32. Steve Hanneke, Wenjie Fu, Eric P Xing, et al. Discrete temporal models of social networks. Electronic Journal of Statistics, 4:585-605, 2010. Google Scholar
  33. Dawn E Holmes and Lakhmi C Jain. Data Mining: Foundations and Intelligent Paradigms: Volume 3: Medical, Health, Social, Biological and Other Applications, volume 3. Springer, 2012. Google Scholar
  34. Eric Horvitz. From data to predictions and decisions: Enabling evidence-based healthcare. http://research.microsoft.com/pubs/141911/Evidence_based_healthcare_essay.pdf, 2010.
  35. Lorne D Johnson and Georgios Sakoulis. Maximizing equity market sector predictability in a bayesian time-varying parameter model. Computational Statistics and Data Analysis, 52(6):3083-3106, 2008. Google Scholar
  36. Linda T Kohn, Janet M Corrigan, Molla S Donaldson, et al. To err is human: building a safer health system, volume 627. National Academies Press, 2000. Google Scholar
  37. Daphne Koller and Nir Friedman. Probabilistic Graphical Models: Principles and Techniques. MIT Press, 2009. Google Scholar
  38. Max Kuhn and Kjell Johnson. Applied Predictive Modeling. Springer, 2013. Google Scholar
  39. Elena Kulinskaya, Diana Kornbrot, and Haiyan Gao. Length of stay as a performance indicator: robust statistical methodology. IMA Journal of Management Mathematics, 16(4):369-381, 2005. Google Scholar
  40. Martijn Lappenschaar, Arjen Hommersom, Peter JF Lucas, Joep Lagro, and Stefan Visscher. Multilevel bayesian networks for the analysis of hierarchical health care data. Artificial intelligence in medicine, 57, 3:171-183, 2013. Google Scholar
  41. Martijn Lappenschaar, Arjen Hommersom, Peter JF Lucas, Joep Lagro, Stefan Visscher, Joke C Korevaar, and François G Schellevis. Multilevel temporal bayesian networks can model longitudinal change in multimorbidity. Journal of clinical epidemiology, 66(12):1405-1416, 2013. Google Scholar
  42. Charles Leadbeater and Jake Garber. Dying for change. http://www.demos.co.uk/files/Dying_for_change_-_web_-_final_1_.pdf, 2010.
  43. Geraint Lewis, Natasha Curry, and Martin Bardsley. Choosing a predictive risk model: a guide for commissioners in england. https://www.primis.nottingham.ac.uk/attachments/article/643/choosing_predictive_risk_model_guide_for_commissioners_nov11.pdf, 2011.
  44. Funding of Care and Support. Fairer care funding - the report of the commission on funding of care and support. http://www.ilis.co.uk/uploaded_files/dilnott_report_the_future_of_funding_social_care_july_2011.pdf, 2011.
  45. NHS England. Nhs england publishes ccg funding allocations for next two years following adoption of new formula. http://www.england.nhs.uk/2013/12/18/ccg-fund-allocs/, 2013.
  46. The King’s Fund. Briefing: The care bill - second reading in the house of commons. http://www.kingsfund.org.uk/sites/files/kf/field/field_publication_file/briefing-care-bill-house-of-commons-second-reading-kingsfund-dec13.pdf, 2013.
  47. The King’s Fund. The health and social care system in 2025 - a view of the future. http://www.kingsfund.org.uk/sites/files/kf/field/field_publication_file/The%20Health%20and%20Social%20Care%20System%20in%202025%20-%20supplementary%20note%20from%20The%20King's%20Fund.pdf, 2013.
  48. Joseph P Newhouse. Reimbursing health plans and health providers: efficiency in production versus selection. Journal of economic literature, 34(3):1236-1263, 1996. Google Scholar
  49. Andrew Y. Ng and Michael I. Jordan. On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. Advances in neural information processing systems, 14:841, 2002. Google Scholar
  50. Kenney Ng, Amol Ghoting, Steven R Steinhubl, Walter F Stewart, Bradley Malin, and Jimeng Sun. Paramo:a parallel predictive modeling platform for healthcare analytic research using electronic health records. Journal of Biomedical Informatics, 2013. Google Scholar
  51. NHS. Whole system partnership - end of life care engagement event. Presentation, Jul. 2012. Google Scholar
  52. NHS. Improving end of life care through early recognition of need. http://www.thewholesystem.co.uk/docs/eolc_predictive_modelling_report.pdf, 2013.
  53. Vladimir Pavlovic, James M Rehg, and John MacCormick. Learning switching linear models of human motion. In NIPS, pages 981-987. Citeseer, 2000. Google Scholar
  54. Judea Pearl. Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, 1988. Google Scholar
  55. Bruno-Edouard Perrin, Liva Ralaivola, Aurelien Mazurie, Samuele Bottani, Jacques Mallet, and Florence d'Alche Buc. Gene networks inference using dynamic bayesian networks. Bioinformatics, 19(suppl 2):ii138-ii148, 2003. Google Scholar
  56. Arvind Rao, Alfred O Hero III, James Douglas Engel, et al. Inferring time-varying network topologies from gene expression data. EURASIP Journal on Bioinformatics and Systems Biology, 2007:7-7, 2007. Google Scholar
  57. Joshua W. Robinson and Alexander J. Hartemink. Learning non-stationary dynamic bayesian networks. J. Mach. Learn. Res., 11:3647-3680, December 2010. Google Scholar
  58. Manuel A. Rodriguez. The failure of predictive modeling and why we follow the herd. http://www.cfclaw.com/files/r_201145133147.pdf, 2011.
  59. Le Song, Mladen Kolar, and Eric P Xing. Time-varying dynamic bayesian networks. In NIPS, pages 1732-1740, 2009. Google Scholar
  60. Roger Stedman. Scoring systems and outcomes. In Fang Gao Smith, editor, Core Topics in Critical Care Medicine, pages 27-33. Cambridge University Press, 2010. Google Scholar
  61. Zhaowen Wang, Ercan E Kuruoglu, Xiaokang Yang, Yi Xu, and Thomas S Huang. Time varying dynamic bayesian network for nonstationary events modeling and online inference. Signal Processing, IEEE Transactions on, 59(4):1553-1568, 2011. Google Scholar
  62. Zhu Wang, Wayne A Woodward, and Henry L Gray. The application of the kalman filter to nonstationary time series through time deformation. Journal of Time Series Analysis, 30(5):559-574, 2009. Google Scholar
  63. Stanley Xu, Richard H Jones, and Gary K Grunwald. Analysis of longitudinal count data with serial correlation. Biometrical journal, 49(3):416-428, 2007. Google Scholar
  64. Shuheng Zhou, John Lafferty, and Larry Wasserman. Time varying undirected graphs. arXiv preprint arXiv:0802.2758, 2008. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail