Cristian Rotariu

Mental stress detection using heart rate variability and morphologic variability of EeG signals

Mental stress is one of the major risk factors for many diseases such as hypertension, coronary artery disease, heart attack, stroke, even sudden death. Conventionally, interviews, questionnaires or behavior observation are used to detect mental stress in an individual. In our study, we have investigated objective characteristics, like various short term heart rate variability (HRV) measures and morphologic variability (MV) of ECG signals for detecting mental stress. A number of HRV measures were investigated, both in time domain and frequency domain. Experiments involved 16 recordings of ECG signals during mental stress state and normal state, included in a multi-parameter data base on physionet.org portal. Results revealed that the HRV measures named mHR, mRR, normalized VLF/LF/HF, difference between normalized LF and normalized HF, and SVI are effective metrics for mental stress detection. Better results were obtained by using MV analysis and a decision-support module based on both methods, HRV and MV.

A Low Power Wireless Personal Area Network for Telemedicine

the current common goal in medical information technology today is the design and implementation of telemedicine solutions, which provide to patients services that enhance their quality of life. Recent technological advances in sensors, low-power integrated circuits, and wireless communications have enabled the design of low-cost, miniature, and intelligent physiological sensor modules. These modules are capable of measuring, processing, communicating one or more physiological parameters, and can be integrated into a wireless personal area network (WPAN). In this paper we present the realization of a wireless personal area network for patient monitoring, as a part of a telemedicine system, capable to measure and transmit physiological parameters such us blood pressure, heart rate, respiratory rhythm, pulse oximetry SpO2, body temperature, and three ECG leads. The use of WPAN is suitable for continuous long-time patient monitoring as a part of a diagnostic procedure, can achieve medical assistance of a chronic condition, or can be supervised during recovery from an acute event or surgical procedure. For instance, the computer-assisted rehabilitation involves unwieldy wires between sensors and monitoring device that are not very comfortable for normal activity. We use the intelligent wireless sensors, based on low power microcontrollers and RF transceivers that perform the measurements and computes the physiological parameters. Individual sensor monitors specific physiological parameter and communicates with the personal server. Personal server, in form of a wireless PDA that running a personal health monitor application, receives the information from wireless sensors, activates the alarms when the measured parameters are above the limits, and communicates periodically to the central server (part of the telemedicine system) by using WiFi or GSM/GPRS connection. The monitor reacts to potential health risks and records physiological information into a local database.

Automatic analysis of the fetal heart rate variability and uterine contractions

The aim of this study is the identification of the dynamic relationship between intrapartum fetal heart rate (FHR) variability and uterine pressure (UP) for normal and hypoxic fetuses. A new method for automatic analysis and identification of uterine contractions is developed and tested on 552 recordings. Using contractions, the fetal heart rate variations are established: accelerations and decelerations (early, late and prolonged). These allow a classification of the recordings analyzed into two categories: normal and pathological. The results are compared to documented fetal outcome results quantified by means of low pH and Apgar values. The developed method provides a series of quantitative measurements for the uterine contractions signal (total number of contractions, total contraction time, total percentage of contraction time, average values for contraction length, peak to peak values, area under curve). Based on these measurements we determine the Spearman correlation coefficients and the scatter matrix between the FHR and UP signals and the fetal outcome parameters: pH and Apgar scores. The correlation result show a strong relationship between decelerations presented on the FHR signal, increasing number of contractions and the low pH and Apgar values.

TELEMON - An Embedded Wireless Monitoring and Alert System for Homecare

The current common goal in medical information technology today is the design and implementation of monitoring solutions, which provide to patients services that enhance their quality of life. Developing of mobile information and communication technologies in home monitoring applications is becoming more useful. Advances in wireless sensor network technology, the overall miniaturization of their associated hardware low-power integrated circuits and wireless communications have enabled the design of low-cost, miniature, and intelligent physiological sensor modules with applications in the medical industry. These modules are capable of measuring, processing, communicating one or more physiological parameters, and can be integrated into a wireless monitoring system. This paper describes the architecture of TELEMON, an embedded medical monitoring and alert system for patients with high medical risk. The system includes continuous monitoring of multiple vital signs, intelligent multiple parameter medical emergency detection, and an Internet/GSM connection to the monitoring centre.

Spectral analysis of fetal heart rate variability associated with fetal acidosis and base deficit values

The physiological response during fetal distress caused by labor varies from case to case and it is reflected both in the umbilical cord pH value and the fetal cord arterial base deficit (BDecf). The purpose of this study is to reveals the changes in fetal heart rate variability in abnormal cases (pH <; 7.2 and BDecf > 8 mmol/L). Fetal heart rate variability (fHRV) was computed in 289 records with both normal and abnormal fetal outcome. The records were divided into two groups, the control group and the test group. Next we computed the Fast Fourier Transform for each group to obtain the spectra for low, mid, and high frequency bands. We have used the normalized values of the mid and high frequency bands and the mid and high frequency ratio. We applied a t-test to divide the test group into two classes, and the pH and BDecf values were used to validate the results. Finally, we obtained a sensitivity of 96% and a specificity of 87.6%. The Spearman correlation coefficients and the scatter matrix also point to a very strong relationship between the fHRV metrics and the three outcome parameters: pH, BDecf, and Apgar scores.

Atrial fibrillation onset prediction using variability of ECG signals

This study presents the use of two different methods for the automatic prediction of the onset of paroxysmal atrial fibrillation (PAF) by means of surface electrocardiographic (ECG) signal. The first method is commonly used and consists in the analysis of the heart rate variability (HRV) of the ECG signal. Two significant parameters are taken into consideration: the time domain metric standard deviation of average five minute window of the time series (SDANN) and the frequency-domain metric low-frequency/high-frequency (LF/HF) ratio of the RR interval. The second analysis method, which is based on the morphological timing characteristics of the QRS complex, is called morphologic variability (MV) of the ECG signal, and was not used before for PAF prediction. Parameters similar to those of HRV analysis are determined in this case. Both methods are applied on 198 Holter records taken from the PAF Database from physionet.org portal. The results show a better accuracy of the MV analysis than that obtained by means of HRV technique alone. Moreover, by using an appropriate decision rule, both methods were “fused” and the overall accuracy of PAF onset prediction was raised up to 90%. Experimental results also indicate that our method is applicable for usual Holter recordings and is robust against noise and common artifacts. Its high prediction accuracy is comparable with that obtained by manual annotation made by experts and therefore is suitable to be used in clinical practice.

TELEMON — A Complex System for Real Time Telemonitoring of Chronic Patients and Elderly People

This paper presents a project that has as main goal researches, design and implementation of an electronicinformatics- telecom and scalable system, that allows the automatic, complex and real time telemonitoring, everywhere and every time (at home, in hospitals, at work, etc.), using several communication paths, of (mobile) persons with chronic illnesses, of elderly people, of those having high medical risk and of those with neuro-locomotor disabilities. The monitored features are electrophysiological (vital) signs, signals for domotics (home surveillance, access control in a certain area), and the systems also performs automatic image analysis of the movements of the subjects.

Pupil centre coordinates detection using the circular Hough transform technique

This paper presents a robust technique for pupil center coordinates detection that uses the circular Hough transform technique. The algorithm of the proposed application is based on detecting the circle which represents the pupil edge from a set of eye images captured using an infrared camera which employs the dark-pupil technique. The accuracy of the pupil detection algorithm is evaluated on the basis of the pupil center positioning error for a set of 52 eye images of the same subject, with gaze oriented in all directions.

Wireless remote monitoring system for patients with cardiac pacemakers

This paper describes the design and implementation of a wireless remote monitoring system for patients with temporary cardiac pacemakers. The system is built around a low power cardiac pacemaker with wireless data transmission capability, used for patient monitoring in to a limited area. The proposed system is designed to be used in emergency situations, in healthcare institutes, helping to keep the patients heartbeat stable. The status of each heartbeat is wirelessly transmitted to a monitoring station via a wireless sensor network. The monitoring station runs a patient monitor application that receives the data from wireless sensor network and activates the alarms when these values exceed the preset limits. An experimental wireless pacemaker was implemented and tested.

Telemonitoring of Vital Signs – An Effective Tool for Ambient Assisted Living

Telemedicine and e-health solutions provide (chronic) patients and elderly people services that enhance their quality of life. Advances in wireless sensor network technology and the overall miniaturization of their associated hardware low-power integrated circuits have enabled the design of low-cost, miniature and precise physiological sensor modules. These modules are capable of measuring, processing, communicating one or more physiological parameters, and can be integrated into a wireless personal area network (WPAN). This paper is dedicated to the most complex Romanian telemedical pilot project, TELEMON, that implemented a system for automatic and complex telemonitoring, everywhere and every time, in real time, of the vital signs of persons with chronic illnesses, of elderly people, of those having high medical risk and of those living in isolated regions. The main objective of this pilot project is to enable personalized medical teleservices delivery, and to act as a basis for a public service for telemedical procedures in Romania and abroad.