Koray Çiftçi

Using lung sounds in classification of pulmonary diseases according to respiratory subphases

Auscultation-based diagnosis of pulmonary disorders relies heavily on the presence of adventitious sounds and on the altered transmission characteristics of the chest wall. The phase information of the respiratory cycle within which adventitious sounds occur is very helpful in diagnosing different diseases. In this study, respiratory sound data belonging to four pulmonary diseases, both restrictive and obstructive, along with healthy respiratory data are used in various classification experiments. The sound data are separated into six subphases, namely, early, mid, late inspiration and expiration and classification experiments using a neural classifier are carried out for each subphase. The AR parameters acquired from segmented sound signals, prediction error and the ratio of expiration to inspiration durations are used to construct the feature set to the neural classifier. Classification experiments are carried out between healthy and pathological sound segments, between restrictive and obstructive sound segments and between two different disease sound segments. The results indicate that the classifier performance demonstrates subphase dependence for different diseases. These results may shed light in eliminating redundant feature spaces in building an expert system using lung sounds for pulmonary diagnosis.

Association Among SNAP-25 Gene DdeI and MnlI Polymorphisms and Hemodynamic Changes During Methylphenidate Use A Functional Near-Infrared Spectroscopy Study

Objective: To investigate the interaction of treatment-related hemodynamic changes with genotype status for Synaptosomal associated protein 25 (SNAP-25) gene in participants with attention deficit hyperactivity disorder (ADHD) on and off single dose short-acting methylphenidate treatment with functional near-infrared spectroscopy (fNIRS). Method: A total of 15 right-handed adults and 16 right-handed children with DSM-IV diagnosis of ADHD were evaluated. Ten milligrams of short-acting methylphenidate was administered in a crossover design. Results: Participants with SNAP-25 DdeI T/T genotype had decreased right deoxyhemoglobin ([HHb]) with treatment. SNAP-25 MnlI genotype was also associated with right deoxyhemoglobin ([HbO2]) and [HHb] changes as well as left [HHb] change. When the combinations of these genotypes were taken into account, the participants with [DdeI C/C or T/C and MnlI G/G or T/G] genotype had increased right [HHb] with MPH use whereas the participants with [DdeI T/T and MnlI T/T] or [DdeI T/T and MnlI G/G or T/G] genotypes had decreased right prefrontal [HHb]. Conclusions: These results suggested that SNAP-25 polymorphism might be associated with methylphenidate induced brain hemodynamic changes in ADHD participants.

Comparison of different feature sets for respiratory sound classifiers

In this study, a comparison is made between the performances of k-NN classifiers with different feature sets derived from respiratory sound data acquired from four different fixed locations on the posterior chest area. The two class recognition problem between healthy and pathological subjects is addressed. Each subject is represented by a single respiration cycle divided into sixty segments from which three different feature sets consisting of 6th order AR model coefficients, percentile frequency parameters and principle components, respectively, are extracted. Performances of k-NN classifiers for these feature sets for four different microphone locations are considered in segment-wise and subject-wise results.

Respiratory airflow estimation by time varying autoregressive modeling

This study proposes an approach to estimate airflow from respiratory sounds using time varying autoregressive modeling. Exploiting the well-established relationship between respiratory sounds and airflow, the sound signals from posterior chest and trachea are modeled using TVAR with a Fourier basis set. It is hypothesized that TVAR coefficients will give us an estimate of the amount of respiratory airflow. The procedure was tested on a group of healthy subjects and good correlation coefficients between the estimated and actual airflow were obtained.

Complexity and functional clusters of the brain during mental arithmetic

Brain functions both in an integrated and segregated manner. This study employs the concept of neural complexity to investigate these two interrelated properties of the brain. It is also known that various parts of the brain regulate the performance of the cardiovascular system and the hemisphere asymmetry which has been observed for some cognitive tasks is known to be determinative in this regulative role. In this study, we studied the complexity of the near infrared spectroscopy signals obtained during mental arithmetic (MA) task from the prefrontal cortex and we have investigated the relationship between complexity and heart rate increase during MA. We used the concept of functional clustering in neural complexity. Thus we determined the lateralization of the brain activity during MA and the clustering pattern of the subjects. It is shown that information theoretic approaches can be fruitful for investigating the part-whole relationship in the brain.

Adaptive Modeling of Sound Transmission in the Respiratory System

In this study, adaptive filtering techniques have been used in an attempt to model the respiratory system. The respiratory system has been considered as a dynamic system for which input-output relationship is to be defined. Simultaneous measurement of the respiratory sounds over the trachea and posterior chest were made, with the signal from the trachea forming the input to a finite impulse response filter and the signal from the posterior chest forming the desired response of the filter. The chest cavity was stimulated with speech sounds. Least-mean square algorithm was used to update filter coefficients. The learning curves of the filter are presented in the paper. It can be concluded that adaptive filtering is a promising way to characterize transmission characteristics of the respiratory system and further improvement may be obtained if anatomical information is integrated in the modeling process.

Investigation of the default mode network of the brain during alzheimer's disease by minimum spanning tree

This study analyzes the connectivity pattern of the default mode network (DMN) in patients with Alzheimers disease (AD) in comparison with young and elderly controls using the minimum spanning tree (MST). The findings revealed that the alterations of the basic structure represented by the MST might provide valuable insights about the physiopathology of the disease. Additionally, by making use of the MST for functionally clustering the DMN, it was shown that the functional subnetworks comprising the DMN differed among the three subject groups. Nonetheless, there were intact prefrontal and temporal networks in elderly controls and AD patients, as well. The analysis shows that the DMN of the AD patients exhibit a higher segregation. We conclude that the MST can be used effectively for analyzing cortical networks.

Graph theoretical analysis of functional brain networks during Alzheimer's disease

In this study, the functional magnetic resonance imaging data from Alzheimers patients and nondemented older adults are investigated using graph theory. Voxel-based graphs were built on the data obtained from an international data center and their clustering coefficients and characteristic path lengths were calculated. No significant differences were found between the two groups in these two parameters. Afterwards, the voxels acting as hubs and their corresponding brain regions were determined. Some differences were observed with respect to the hub locations. These results point to the fact that rather than a change in the global organization of the brain, Alzheimers disease causes a functional change in some brain regions.

The Effect of Methylphenidate on Brain Hemodynamics of Attention-Deficit/Hyperactivity Disorder Measured by Functional Near Infrared Spectroscopy

15 ADHD adults were evaluated with fNIRS during Stroop task. The aim was to examine methylphenidate-induced hemodynamic changes during cognitive activity. It is found that methylphenidate decreased oxyhemoglobin levels. The reason may be vasoconstriction.

Bayesian Group Activation Analysis for Functional Neuroimaging

The main goal of hypothesis-based functional neuroimaging is to arrive at a group decision for a set of data measured in different sessions. Hierarchical general linear model (GLM) is commonly used for this type of multilevel statistical inference problems. This study proposes a method that employs Bayesian networks for analyzing hierarchical GLM. A major goal of the study is to put the main concepts of classical statistics, fixed-, random-, mixed-effects, into a Bayesian framework. The proposed method provides the posterior distributions for all the variables in the model. It is shown that it is possible to make generalizable inferences from a set of experimental data.