Cardiovascular mortality is significantly
increased in patients suffering from schizophrenia. How-
ever, psychotic symptoms are quantified by means of the
scale for the assessment of positive and negative symp-
toms, but many investigations try to introduce new etiol-
ogy for psychiatric disorders based on combination of
biological, psychological and social causes. Classification
between healthy and paranoid cases has been achieved by
time, frequency, Hilbert–Huang (HH) and a combination
between those features as a hybrid features. Those features
extracted from the Hilbert–Huang transform for each
intrinsic mode function (IMF) of the detrended time series for each healthy case and paranoid case. Short-term ECG
recordings of 20 unmedicated patients suffering from
acute paranoid schizophrenia and those obtained from
healthy matched peers have been utilized in this investi-
gation. Frequency features: very low frequency (VLF),
low frequency (LF), high frequency (HF) and HF/LF
(ratio) produced promising success rate equal to 97.82 %
in training and 97.77 % success rate in validation by
means of IMF1 and ninefolds. Time–frequency features
[LF, HF and ratio, mean, maximum (max), minimum
(min) and standard deviation (SD)] provided 100 % suc-
cess in both training and validation trials by means of
ninefolds for IMF1 and IMF2. By utilizing IMF1 and
ninefolds, frequency and Hilbert–Hang features [LF, HF,
ratio, mean value of envelope ( a)] produced 96.87 and
95.5 % for training and validation, respectively. By ana-
lyzing the first IMF and using ninefolds, time and Hilbert–
Hang features [mean, max, min, SD, median, first quartile
(Q1), third quartile (Q3), kurtosis, skewness, Shannon
entropy, approximate entropy and energy, ( a), level of
envelope variation ([ _ a(t)]^2), central frequency ð W Þ and
number of zero signal crossing ð W j jÞ ] produced a 100 %
success rate in training and 90 % success rate in valida-
tion. Time, frequency and HH features [energy, VLF, LF,
HF, ratio and ( a)] provided 97.5 % success rate in training
and 95.24 % success rate in validation using IMF1 and
sixfolds. However, frequency features have produced
promising classification success rate, but hybrid features
emerged the highest classification success rate than using
features in each domain separately. |