Jr. Fernandez et Rc. Hermida, Computation of model-dependent tolerance bands for ambulatorily monitored blood pressure, CHRONOBIO I, 17(4), 2000, pp. 567-582
The construction of time-specified reference limits requires systematic sam
pling in clinical health, particularly for those variables characterized by
a circadian rhythm of large amplitude, as it is the case for blood pressur
e (BP). For the detection of false negatives, tolerance intervals (limits t
hat will include at least a specified proportion of the population with a s
tated confidence) are important and should substitute when possible for pre
diction limits. We have previously described a nonparametric method for the
computation of model-independent tolerance intervals that are constructed
by first dividing the sampling range in several time spans in which no appr
eciable changes in population characteristics (namely, mean and variance) t
ake place. The tolerance interval is then computed for each of the time spa
ns. The limits thus computed, as well as results of any comparison of a giv
en individual's profile against such tolerance intervals, are highly depend
ent on the sampling scheme of both the reference individuals and the test s
ubject. To avoid this problem, we have developed an alternative method that
allows the computation of model-dependent tolerance bands for hybrid time
series. Assuming that a set X of longitudinal series monitored from a given
group of reference individuals can be fitted with the same individual mode
l, a population model C(X,t) can be also determined, as well as the deviati
on S(X,t) of each individual curve from the population model. The tolerance
band will then have the form C(X,t) +/- kS(X,t), where k is here estimated
following a nonparametric approach based on bootstrap techniques. Alternat
ively, two different values of k can be estimated (for the lower and upper
limits of the tolerance interval, respectively) in cases for which we canno
t assume symmetry. The method is generally applicable for any population mo
del describing the reference population (including the fit of multiple sign
ificant components, nonsinusoidal waveforms, and/or trends). The method was
used to establish time-specified tolerance bands for time series of blood
pressure monitored automatically in healthy individuals of both genders. Mo
del-dependent intervals are preferred to the model-independent limits when
reliance on a specified sampling rate needs to be avoided. These limits may
serve for an objective and positive definition of health, for the screenin
g and diagnosis of disease, and for gauging the subject's response to treat
ment.