APPLICATION OF NEURAL NETWORKS IN THE INTERPRETATION OF IMPEDANCE CARDIOVASOGRAMS FOR THE DIAGNOSES OF PERIPHERAL VASCULAR DISEASES Sunil Karamchandani a , M.Y.Dixit b , R.K.Jain b , Mita Bhowmick c a Bombay Institute Of Technology Bandra, Mumbai, India. b Bhabha Atomic Research Center Trombay, Mumbai, India c Thadomal Shahani Engineering College Bandra, Mumbai, India E-mail: skaramchandani@rediffmail.com, m_bhowmick @rediffmail.com ABSTRACT An Impedance Cardio-vasograph (ICVG) system has been developed at the Electronics Division, Bhabha Atomic Research Centre (B.A.R.C) for the assessment of Peripheral Blood Flow and has been installed at the Department of Medicine, J.J. Hospital, Mumbai, India. Impedance cardio-vasography (ICVG) gives an indirect assessment of blood volume changes by measurement of normalized rate of change of electrical impedance (N dZ/dt) of the body segment. Parameters like Blood Flow Index (BFI) and Differential Pulse Arrival Time (DPAT) at different locations in both lower extremities (upper thigh, knee, calf and ankle) can be computed from these measurements. This work deals with the analysis of these parameters by a neural network system for obtaining proper diagnosis of subjects with peripheral vascular diseases. The designed network identified the presence of anatomical block or narrowing for most of cases presented to it during testing and also the status of collateral circulation in the lower limbs. The neural network was trained again, with the few cases, which were not predicted correctly. The collaterals after the site of occlusion were classified as good, moderate or poor as an aid to the physician. The network identified cases with athero-sclerotic narrowing satisfactorily and was also able to categorize cases where changes are observed only in one extremity, other remaining normal as in the cases of hemi-Leriche’s syndrome. An additional parameter CVS (Coefficient of venous Statis) was calculated which is useful for the diagnosis of primary and secondary varicosity of the veins. INTRODUCTION The incidences of peripheral vascular diseases are increasing day by day probably due to more stressful life and modern living. The conventional method to detect such obstructions is angiography, an invasive technique, which requires surgical exposure of arteries. Therefore, there is a need to develop a simple and non-invasive method to track obstructions to blood flow in the arteries and veins. Non-invasive techniques like vascular Doppler, venous occlusion method and Plethysmography are able to track the obstructions in the blood flow in the arteries and veins and thus assist in the diagnosis of peripheral vascular diseases [1]. Among the plethysmographic techniques the commonly used ones is Impedance Plethysmography, which gives an indirect assessment of blood volume changes in a body segment by measurement of its electrical impedance as a function of time. This technique was first introduced by Nyboer, who correlated the change in impedance with the volume of the blood flow in both invitro and vivo studies [2]. The error in measuring the blood component of resistivity caused by this method is less than + 2%, which shows that impedance plethysmography signals can be measured with high accuracy [3]. Impedance techniques further received an impetus from Kubicek who introduced the first time derivative of the impedance dZ/dt, which is obtained by electronically differentiating the impedance (Z) signal [4]. The product of the maximum value of the dZ/dt signal with the left ventricular ejection time T gives the total change in impedance for the entire systolic period. The dZ/dt waveform was extended for assessment of peripheral blood flow, using Kubicek’s formula [5] dV = T * (dZ/dt) m (1) V Z The Minnesota Impedance device developed on the basis of Kubicek’s model, involved many hand calculations and suffered from the drawback of respiratory artifacts. In view of the technological advancements, Babu et al developed PC Based Impedance Cardiovasograph System which not only provides an impedance signal free from any geometrical variations in the body segment but also gives a real time calibration of the waveform [6, 7]. An impedance change upto 5 ohms/sec can be easily obtained [8]. The system has been installed at the Isotope Unit, Department of Medicine, J.J.Hospital, Mumbai, India for clinical evaluation. MATERIALS AND METHODS Fig. 1 shows typical ICVG waveforms recorded from neck, thorax and various locations such as thigh, knee calf and ankle in both the lower extremities with the patient (PKR-60-F) in the supine position. The waveforms represent the ensemble average of 50 IPG cycles and have been recorded during the normal breathing of the subject. The impedance signal is measured at 100 KHz Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference Shanghai, China, September 1-4, 2005 0-7803-8740-6/05/$20.00 ©2005 IEEE. 7537