Personalised Medication Planning using PDDL+

Fares Khalid M Alaboud; Andrew Ian Coles

Personalised Medication Planning using PDDL+

Fares Khalid M Alaboud, Andrew Ian Coles

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

263 Downloads (Pure)

Abstract

Prescription medication is typically prescribed with a standardised set of instructions, to be followed regularly, with the aim being to manage symptoms while remaining within safe dosage limits. The caveat of such standardisation is that it is not tailored to the needs of the patient, in terms of their activities. In this paper, we take the first steps towards modelling medication pharmacokinetics as a PDDL+ hybrid planning problem. As pharmacokinetics are inherently non-linear, we present a planner-independent linearise--validate cycle, where tasks can be solved by iterative refinement of a linear approximation of the domain, by validation against the full non-linear semantics.

Original language	English
Title of host publication	Proceedings of the Scheduling and Planning Applications woRKshop (SPARK)
Subtitle of host publication	At the 28th International Conference on Automated Planning and Scheduling
Editors	Sara Bernadini, Simon Parkinson, Kartik Talamadupula
Publication status	Published - 24 Jun 2018

Keywords

Temporal Planning
Personalised medicine
Artificial intelligence planning

Access to Document

Personalised Medication Planning using_ALABOUD_Accepted30April2018_GREEN AAM Accepted author manuscript, 528 KB

Cite this

@inbook{2aefb56ab4c7423ebffbab1b6ecbde9f,

title = "Personalised Medication Planning using PDDL+",

abstract = "Prescription medication is typically prescribed with a standardised set of instructions, to be followed regularly, with the aim being to manage symptoms while remaining within safe dosage limits. The caveat of such standardisation is that it is not tailored to the needs of the patient, in terms of their activities. In this paper, we take the first steps towards modelling medication pharmacokinetics as a PDDL+ hybrid planning problem. As pharmacokinetics are inherently non-linear, we present a planner-independent linearise--validate cycle, where tasks can be solved by iterative refinement of a linear approximation of the domain, by validation against the full non-linear semantics.",

keywords = "Temporal Planning, Personalised medicine, Artificial intelligence planning",

author = "Alaboud, {Fares Khalid M} and Coles, {Andrew Ian}",

year = "2018",

month = jun,

day = "24",

language = "English",

editor = "Sara Bernadini and Simon Parkinson and Kartik Talamadupula",

booktitle = "Proceedings of the Scheduling and Planning Applications woRKshop (SPARK)",

}

Personalised Medication Planning using PDDL+. / Alaboud, Fares Khalid M ; Coles, Andrew Ian.
Proceedings of the Scheduling and Planning Applications woRKshop (SPARK): At the 28th International Conference on Automated Planning and Scheduling. ed. / Sara Bernadini; Simon Parkinson; Kartik Talamadupula. 2018.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

TY - CHAP

T1 - Personalised Medication Planning using PDDL+

AU - Alaboud, Fares Khalid M

AU - Coles, Andrew Ian

PY - 2018/6/24

Y1 - 2018/6/24

N2 - Prescription medication is typically prescribed with a standardised set of instructions, to be followed regularly, with the aim being to manage symptoms while remaining within safe dosage limits. The caveat of such standardisation is that it is not tailored to the needs of the patient, in terms of their activities. In this paper, we take the first steps towards modelling medication pharmacokinetics as a PDDL+ hybrid planning problem. As pharmacokinetics are inherently non-linear, we present a planner-independent linearise--validate cycle, where tasks can be solved by iterative refinement of a linear approximation of the domain, by validation against the full non-linear semantics.

AB - Prescription medication is typically prescribed with a standardised set of instructions, to be followed regularly, with the aim being to manage symptoms while remaining within safe dosage limits. The caveat of such standardisation is that it is not tailored to the needs of the patient, in terms of their activities. In this paper, we take the first steps towards modelling medication pharmacokinetics as a PDDL+ hybrid planning problem. As pharmacokinetics are inherently non-linear, we present a planner-independent linearise--validate cycle, where tasks can be solved by iterative refinement of a linear approximation of the domain, by validation against the full non-linear semantics.

KW - Temporal Planning

KW - Personalised medicine

KW - Artificial intelligence planning

M3 - Conference paper

BT - Proceedings of the Scheduling and Planning Applications woRKshop (SPARK)

A2 - Bernadini, Sara

A2 - Parkinson, Simon

A2 - Talamadupula, Kartik

ER -

Personalised Medication Planning using PDDL+

Abstract

Keywords

Access to Document

Fingerprint

Cite this