LISA is a web-based patient information and decision support system designed to provide advice about dose adjustments in the treatment of
acute childhood lymphoblastic leukaemia. LISA has been implemented using PROforma
guideline development and enactment technology.
The LISA demonstrator
The decision support module of the demonstration version of LISA is the same as the one on the live version of the system.
The only significant difference between the two versions is that the demonstrator is not connected to
a patient database.
LISA encapsulates the dose adjustment rules
defined in the Medical Research Council (UK) Acute Lymphoblastic Leukaemia Trial ALL97 guideline (version 1.1 revised November 1999).
These rules have been modelled
in the PROforma language for specifying decisions, plans and other
tasks that make up the components of clinical guidelines and protocols, and are enacted by the associated PROforma decision support engine.
LISA is primarily designed to provide dosage decision support in the 2-3 year maintenance period of treatment for
Acute Lymphoblastic Leukaemia (ALL).
The LISA demonstrator allows the user to simulate making dose decisions whilst taking a patient through this maintenance phase.
LISA Decision support
During the maintenance phase of treatment for ALL,
drug dose adjustments decisions have to be made weekly and the main treatment consists of regular administration of two oral
chemotherapy agents: 6-mercaptopurine (MP) which is administered daily, and meth-otrexate (MTX) which is given weekly.
Doses have to be continually monitored and adjusted as responses to these drugs vary significantly from patient to patient.
The MRC protocol specifies eight separate "states" for categorising patients' treatment needs over the course of the maintenance phase.
Each state represents a drug and dose combination of MP and MTX to be administered. The goal of the system is to recommend the most appropriate
combination for each individual case at any time. The system therefore monitors transitions between states.
The eight states are: 0% MP and 0% MTX
("omit oral chemotherapy"),
50% MP and 50% MTX, 75% MP and 75% MTX, 100% MP and 100% MTX, 125% MP and 100% MTX, 125% MP and 125% MTX, 150% MP and 125% MTX and 150%
MP and 150% MTX. A ninth option is also allowed to enable a clinician to prescribe a drug combination not defined in the protocol.
Drug dose combination decisions in LISA are based on five data inputs:
When these patient data have been entered in LISA, the PROforma decision engine evaluates the logical condition associated with
each argument and
then "aggregates" those arguments that are true in order to arrive at an overall measure of support for each candidate
course of treatment.
Each candidate is allocated a priority level
so that if more than one is recommended, the one with the highest priority is given precedence.
A caption is associated
with each argument to enable the reasons justifying the most strongly recommended treatment
option can be displayed.
- current state
- current platelet count of the blood result on which the decision is being based
- absolute neutrophil count of the blood result on which the decision is being based
- number of weeks that the patient has been at the current state
- number of weeks that
the patient has tolerated treatment.