Abstract
Treatment of patients with multimorbidity is one of the greatest challenges for clinical decision support. While evidence-based management of specific diseases is supported by clinical practice guidelines, concurrent application of multiple guidelines requires checking for possible adverse interactions between interventions and mitigating them, before a management plan is constructed. In earlier work, we developed an approach that casts the problem of multimorbidity management as an AI planning problem. In this paper we build on this earlier work and make progress towards creating a pipeline that inputs disease and patient-specific information and outputs a management plan. We describe research focused on selected aspects of pipeline development and illustrate these aspects with a clinical case implemented using the PDDL planning language and the OPTIC planner.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alaboud, F.K., Coles, A.: Personalized medication and activity planning in PDDL+. In: Proceedings of 29nd International Conference on Automated Planning and Scheduling (ICAPS), pp. 492–500 (2019)
Barnett, K., Mercer, S., Norbury, M., Watt, G., Wyke, S., Guthrie, B.: Epidemiology of multimorbidity and implications for health care, research, and medical education: a cross-sectional study. Lancet 380, 37–43 (2012)
Benton, J., Coles, A.J., Coles, A.: Temporal planning with preferences and time-dependent continuous costs. In: Proceedings of 22nd International Conference on Automated Planning and Scheduling (ICAPS), vol. 22, pp. 2–10. AAAI Publications (2012)
Blais-Amyot, J.L., Cote-Gagne, M.: MitPlan generation of PDDL based on CPGS. Honours Project report, University of Ottawa (2021)
Fernandez-Olivares, J., Onaindia, E., Castillo, L., Jordan, J., Cozar, J.: Personalized conciliation of clinical guidelines for comorbid patients through multi-agent planning. Artif. Intell. Med. 96, 167–186 (2019)
Fox, M., Long, D.: PDDL2.1: an extension to PDDL for expressing temporal planning domains. J. Artif. Intell. Res. 20, 61–124 (2003). https://doi.org/10.1613/jair.1129
Fox, M., Long, D.: Modelling mixed discrete-continuous domains for planning. J. Artif. Intell. Res. 27, 235–297 (2006)
Jafarpour, B., Raza, S., Van Woensel, W., Sibte, S., Abidi, R.: Execution-time integration of clinical practice guidelines to provide decision support for comorbid conditions. Artif. Intell. Med. 94, 117–137 (2019)
Kogan, A., Peleg, M., Tu, S.W., Allon, R., Khaitov, N., Hochberg, I.: Towards a goal-oriented methodology for clinical-guideline-based management recommendations for patients with multimorbidity: GoCom and its preliminary evaluation. J. Biomed. Inf. 112, 103587 (2020)
Michalowski, M., Rao, M., Wilk, S., Michalowski, W., Carrier, M.: MitPlan 2.0: enhanced support for multi-morbid patient management using planning. In: Tucker, A., Henriques Abreu, P., Cardoso, J., Pereira Rodrigues, P., Riaño, D. (eds.) AIME 2021. LNCS (LNAI), vol. 12721, pp. 276–286. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77211-6_31
Michalowski, M., Wilk, S., Michalowski, W., Carrier, M.: A planning approach to mitigating concurrently applied clinical practice guidelines. Artif. Intell. Med. 112 (2021)
O’Sullivan, D., et al.: Towards a framework for comparing functionalities of multimorbidity clinical decision support: a literature-based feature set and benchmark cases. To appear in AMIA 2021 (2021)
Piovesan, L., Terenziani, P., Molino, G.: GLARE-SSCPM: an intelligent system to support the treatment of comorbid patients. IEEE Intell. Syst. 33(6), 37–46 (2018)
Van Woensel, W., Abidi, S., Abidi, S.: Decision support for comorbid conditions via execution-time integration of clinical guidelines using transaction-based semantics and temporal planning. Artif. Intell. Med. 118, 102127 (2021)
Wilk, S., Michalowski, M., Michalowski, W., Rosu, D., Carrier, M., Kezadri-Hamiaz, M.: Comprehensive mitigation framework for concurrent application of multiple clinical practice guidelines. J. Biomed. Inform. 66, 52–71 (2017)
Acknowledgements
We thank Jean-Luc Blais-Amyot and Maxime Côté-Gagné for their programming work on the automated translation component. We thank the reviewers for their helpful feedback. This research was supported by funding from the Telfer Health Transformation Exchange and the Natural Sciences and Engineering Research Council of Canada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rao, M., Michalowski, M., Wilk, S., Michalowski, W., Coles, A., Carrier, M. (2022). Towards an AI Planning-Based Pipeline for the Management of Multimorbid Patients. In: Michalowski, M., Abidi, S.S.R., Abidi, S. (eds) Artificial Intelligence in Medicine. AIME 2022. Lecture Notes in Computer Science(), vol 13263. Springer, Cham. https://doi.org/10.1007/978-3-031-09342-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-09342-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09341-8
Online ISBN: 978-3-031-09342-5
eBook Packages: Computer ScienceComputer Science (R0)