Information Technology Reference
In-Depth Information
Assumption:
we assume the following:
1.
All other components shown in Figure 5 are developed and working. The only
component that we are focusing on is the evidence based reasoning software.
2.
The diagnosis of the illness is already known.
3.
The component will answer only predefined set of questions (most important to a
patient) such as the cause of the disease (etiology), once diagnosed, how long a person
can live (prognosis), etc.
To emphasize the main point, our implementation uses a simple design. Without losing
generality, we loaded data from a file instead of asking the user to input them from a
keyboard. We also watered down some features for the sake of simplicity. For example, the
whole knowledge database is substituted by hard-coded logic.
7.5 A case example: Colorectal cancer
To help our presentation, we will use a medical case example to illustrate some features of
our evidence based reasoning system. The medical case used is the colorectal cancer. And
we will use the most common form of the colorectal cancer: the hereditary nonpolyposis
colon cancer (HNPCC). This form of cancer is also called
Lynch syndrome
. The following is
some facts related to this disease:
Some facts of colorectal cancer:
“Cancer of the large bowel is second only to lung cancer as
a cause of cancer death in the United States; 146,940 new cases occurred in 2004, and 56,730
deaths were due to colorectal cancer.” (Kasper, 2005, p. 527) This disease has hereditary
factors. “As many as 25% of patients with colorectal cancer have a family history of the
disease, suggesting a hereditary predisposition.” (Kasper, 2005, p. 527) Once diagnosed, the
prognosis “is related to the depth of tumor penetration into the bowel wall and the presence
of both regional lymph node involvement and distant metastases. These variables are
incorporated into the staging system introduced by Dukes and applied to a TNM
classification method, in which T represents the depth of tumor penetration, N the presence
of lymph node involvement, and M the presence or absence of distant metastases (Table 1).
Table 1. Staging of and Prognosis for Colorectal Cancer (Kasper, 2005, p. 529-530)
The prevalent belief of the cause of the disease is the interplay between the environment and
the cancer suppressing genes. The reason why we have colorectal cancers (in fact, any type
