IEEE Computational Intelligence Magazine - November 2020 - 66

A TCM prescription can have dozens of ingredients,
and a drug can have dozens of alternative drugs.
Therefore, the solution space of the problem
can be very large.
may also develop a prevention program for two similar clusters
as they consider appropriate. For a cluster with high-risk residents (with suspected symptoms of COVID-19 or serious
underlying illnesses), they can decide to develop one prevention
program for each resident.
When developing initial programs, the TCM experts aim
to maximize the prevention effect on residents of each cluster without considering the limits of medical resources
including herbal medicines, patent medicines, medical devices, pharmacists, and other paramedical personnel. If the
demands of the programs exceed the available resources, we
use an intelligent optimization algorithm to optimize the
programs subject to the resource constraints. However, any
prevention program produced by computer algorithms must
be checked and, if necessary, modified by the TCM experts
before implementation. The above process continues until all
prevention programs satisfy the resource constraints and are
approved by the TCM experts. Fig. 1 illustrates the interactive optimization process.

Perform FCM Clustering to Group Residents
Develop Prevention Programs Based
on Clustering Results
Calculate the Resources
Required by the Programs
Satisfy
Resource Constraints?

Optimize the Programs
Subject to the Constraints
Check the Updated Programs
Modify
the Programs

Approved?
Y

Put into Implementation
FIGURE 1 Flowchart of the interactive optimization of TCM prevention
programs. Rectangles with dash borders are performed by TCM experts,
while rectangles with solid borders are performed by computer.

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | NOVEMBER 2020

A. Optimization Problem

The prevention program optimization problem is formulated as follows. TCM experts
have developed N basic prevention programs,
denoted by {P1, P2, f, PN }, for residents from
M communities. The programs involve K
types of drugs, K1 types of other medical
resources (such as TCM material and movable
devices) that can be shared among the communities, and K2
types of other medical resources (such as immovable devices
and staff belonging to given communities) that cannot be
shared among the communities. When there is no confusion,
we use k as the index for the above three classes of resources.
The problem is to optimize the distribution of medical
resources among the prevention programs for the M communities. In the local region, the total available quantity of each drug
k is qt Dk ^1 # k # K h, total available quantity of each other
sharable resource k is qt Gk ^1 # k # K 1h, and available quantity
of each non-sharable resource k in community i is qt Fik
^1 # k # K 2; 1 # i # M h .
Each prevention program Pj has the following attributes
^1 # j # N h:
❏❏ The number nj of residents using the program;
❏❏ The set H j of communities that have residents using the
program; for each community i ! H j, the number of residents using the program is n ij;
❏❏ The set U j of drugs used by the program; for each drug
k ! U j, the quantity used per prescription is q Djk;
❏❏ The set W j of other sharable resources used by the program;
for each resource k ! W j, the quantity used per prescription
is q Gjk;
❏❏ The set X j of other non-sharable resources used by the
program; for each resource k ! X j, the quantity used per
prescription is q Fjk;
In a TCM prescription, many ingredients have alternatives.
We use Ulj 1 U j to denote the subset of drugs that have alternatives in P j; for each drug k ! Ulj , we use a list Kk to store its
alternative drugs in decreasing order of priority, which are
determined by TCM drug properties and effects to the disease
(COVID-19 belongs to pulmonary disease in TCM). We consider two types of updates on a TCM prescription:
❏❏ Replacing an auxiliary drug k ! Ulj with an alternative
drug kl ! K k, for example, replacing coix seed with winter
melon seed;
❏❏ Replacing a main drug k ! Ulj with an alternative drug
kl ! K k; however, according to compatibility of TCM, a
main drug is related to one or more auxiliary drugs, and the
corresponding auxiliary drugs should also be reapplied; an
example is replacing "astragalus membranaceus (main) +
cinnamon (auxiliary)" with "codonopsis pilosula (main) +
yam (auxiliary)."
To prevent the updated prescriptions from deviating too
much from the original prescriptions developed by TCM
experts, for each prevention program, we allow at most one
drug (except auxiliary drugs related to a main updated drug) to

IEEE Computational Intelligence Magazine - November 2020

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - November 2020