Search tips
Search criteria

Results 1-5 (5)

Clipboard (0)

Select a Filter Below

more »
Year of Publication
Document Types
1.  A noninvasive method for coronary artery diseases diagnosis using a clinically-interpretable fuzzy rule-based system 
Coronary heart diseases/coronary artery diseases (CHDs/CAD), the most common form of cardiovascular disease (CVD), are a major cause for death and disability in developing/developed countries. CAD risk factors could be detected by physicians to prevent the CAD occurrence in the near future. Invasive coronary angiography, a current diagnosis method, is costly and associated with morbidity and mortality in CAD patients. The aim of this study was to design a computer-based noninvasive CAD diagnosis system with clinically interpretable rules.
Materials and Methods:
In this study, the Cleveland CAD dataset from the University of California UCI (Irvine) was used. The interval-scale variables were discretized, with cut points taken from the literature. A fuzzy rule-based system was then formulated based on a neuro-fuzzy classifier (NFC) whose learning procedure was speeded up by the scaled conjugate gradient algorithm. Two feature selection (FS) methods, multiple logistic regression (MLR) and sequential FS, were used to reduce the required attributes. The performance of the NFC (without/with FS) was then assessed in a hold-out validation framework. Further cross-validation was performed on the best classifier.
In this dataset, 16 complete attributes along with the binary CHD diagnosis (gold standard) for 272 subjects (68% male) were analyzed. MLR + NFC showed the best performance. Its overall sensitivity, specificity, accuracy, type I error (α) and statistical power were 79%, 89%, 84%, 0.1 and 79%, respectively. The selected features were “age and ST/heart rate slope categories,” “exercise-induced angina status,” fluoroscopy, and thallium-201 stress scintigraphy results.
The proposed method showed “substantial agreement” with the gold standard. This algorithm is thus, a promising tool for screening CAD patients.
PMCID: PMC4468223  PMID: 26109965
Classification; clinical prediction rule; coronary artery disease; data mining; fuzzy logic
2.  An Electromyographic-driven Musculoskeletal Torque Model using Neuro-Fuzzy System Identification: A Case Study 
The purpose of this study was to estimate the torque from high-density surface electromyography signals of biceps brachii, brachioradialis, and the medial and lateral heads of triceps brachii muscles during moderate-to-high isometric elbow flexion-extension. The elbow torque was estimated in two following steps: First, surface electromyography (EMG) amplitudes were estimated using principal component analysis, and then a fuzzy model was proposed to illustrate the relationship between the EMG amplitudes and the measured torque signal. A neuro-fuzzy method, with which the optimum number of rules could be estimated, was used to identify the model with suitable complexity. Utilizing the proposed neuro-fuzzy model, the clinical interpretability was introduced; contrary to the previous linear and nonlinear black-box system identification models. It also reduced the estimation error compared with that of the most recent and accurate nonlinear dynamic model introduced in the literature. The optimum number of the rules for all trials was 4 ± 1, that might be related to motor control strategies and the % variance accounted for criterion was 96.40 ± 3.38 which in fact showed considerable improvement compared with the previous methods. The proposed method is thus a promising new tool for EMG-Torque modeling in clinical applications.
PMCID: PMC4236802  PMID: 25426427
Electromyography; musculoskeletal model; neuro-fuzzy system identification; voluntary isometric contraction
3.  Manipulating measurement scales in medical statistical analysis and data mining: A review of methodologies 
selecting the correct statistical test and data mining method depends highly on the measurement scale of data, type of variables, and purpose of the analysis. Different measurement scales are studied in details and statistical comparison, modeling, and data mining methods are studied based upon using several medical examples. We have presented two ordinal–variables clustering examples, as more challenging variable in analysis, using Wisconsin Breast Cancer Data (WBCD).
Ordinal-to-Interval scale conversion example:
a breast cancer database of nine 10-level ordinal variables for 683 patients was analyzed by two ordinal-scale clustering methods. The performance of the clustering methods was assessed by comparison with the gold standard groups of malignant and benign cases that had been identified by clinical tests.
the sensitivity and accuracy of the two clustering methods were 98% and 96%, respectively. Their specificity was comparable.
by using appropriate clustering algorithm based on the measurement scale of the variables in the study, high performance is granted. Moreover, descriptive and inferential statistics in addition to modeling approach must be selected based on the scale of the variables.
PMCID: PMC3963323  PMID: 24672565
Biostatistics; breast cancer; cluster analysis; data mining; research design
4.  First growth curves based on the World Health Organization reference in a Nationally-Representative Sample of Pediatric Population in the Middle East and North Africa (MENA): the CASPIAN-III study 
BMC Pediatrics  2012;12:149.
The World Health Organization (WHO) is in the process of establishing a new global database on the growth of school children and adolescents. Limited national data exist from Asian children, notably those living in the Middle East and North Africa (MENA). This study aimed to generate the growth chart of a nationally representative sample of Iranian children aged 10–19 years, and to explore how well these anthropometric data match with international growth references.
In this nationwide study, the anthropometric data were recorded from Iranian students, aged 10–19 years, who were selected by multistage random cluster sampling from urban and rural areas. Prior to the analysis, outliers were excluded from the features height-for-age and body mass index (BMI)-for-age using the NCHS/WHO cut-offs. The Box-Cox power exponential (BCPE) method was used to calculate height-for-age and BMI-for-age Z-scores for our study participants. Then, children with overweight, obesity, thinness, and severe thinness were identified using the BMI-for-age z-scores. Moreover, stunted children were detected using the height-for-age z-scores. The growth curve of the Iranian children was then generated from the z-scores, smoothed by cubic S-plines.
The study population comprised 5430 school students consisting of 2312 (44%) participants aged 10–14 years , and 3118 (58%) with 15–19 years of age. Eight percent of the participants had low BMI (thinness: 6% and severe thinness: 2%), 20% had high BMI (overweight: 14% and obesity: 6%), and 7% were stunted. The prevalence rates of low and high BMI were greater in boys than in girls (P < 0.001). The mean BMI-for-age, and the average height-for-age of Iranian children aged 10–19 years were lower than the WHO 2007 and United states Centers for Disease Control and Prevention 2000 (USCDC2000) references.
The current growth curves generated from a national dataset may be included for establishing WHO global database on children’s growth. Similar to most low-and middle income populations, Iranian children aged 10–19 years are facing a double burden of weight disorders, notably under- and over- nutrition, which should be considered in public health policy-making.
PMCID: PMC3471000  PMID: 22985219
Growth; Iran; Reference curve; Weight disorder
5.  Resolving Superimposed MUAPs using Particle Swarm Optimization 
This paper presents an algorithm to resolve superimposed action potentials encountered during the decomposition of electromyographic signals. The algorithm uses particle swarm optimization with a variety of features including randomization, cross-over, and multiple swarms. In a simulation study involving realistic superpositions of 2-5 motor-unit action potentials, the algorithm had an accuracy of 98%.
PMCID: PMC2673334  PMID: 19272923
Alignment; decomposition; electromyography; particle swarm optimization; superposition

Results 1-5 (5)