Lv. Philosophov et Lg. Ryabinina, MEDICAL DIAGNOSTIC DECISION RULES BASED ON MUTUALLY DEPENDENT DIAGNOSTIC FACTORS, Computers in biology and medicine, 27(4), 1997, pp. 329-347
There are numerous situations in which clinicians are not free to choo
se informative and independent factors (tests) in the solution of thei
r diagnostic or prognostic problems. It is vital to use a combination
of several mutually dependent factors in such cases. The paper develop
s a Bayesian approach to the creation of diagnostic and prognostic rul
es based on mutually dependent factors. Following the work of Philosop
hov (Philosophov, Medical Decision Making, 15, 264-275, 1995), we dist
inguish between true factor values and factor estimates-the result of
factor measurement by means of an imperfect medical instrument (techno
logy). A constructive solution of the problem is achieved by introduci
ng the concept of clinical variants of a disease-a set of possible for
ms of disease, each of which is described by a specific combination of
prognostic and other relevant factors. The appropriate use of mutuall
y dependent factors can yield gains in decision efficiency, even in th
e simplest case of two binary factors. The gain achieved can increase
with the number of factors used and variety of factor values. An examp
le based on real clinical material illustrates the approach and the ga
ins it can achieve. (C) 1997 Elsevier Science Ltd.