{"title":"Integration of real-time and off-line clinical data in the MIMIC database","authors":"G. Moody, R. Mark","doi":"10.1109/CIC.1997.648019","DOIUrl":"https://doi.org/10.1109/CIC.1997.648019","url":null,"abstract":"The MIMIC (Multi-parameter Intelligent Monitoring for Intensive Care) database is a collection of recorded physiological signals and clinical data that is intended to support the development and evaluation of automated decision support systems for intensive care settings. Each patient record typically includes 24 to 48 hours of continuous real-time signals (e.g. ECGs, blood pressure waveforms or respiration) and derived measurements (e.g. heart rate or systolic blood pressure), together with clinical data derived from the patient's medical record and from the hospital's clinical computing systems. The clinical data are encoded using structured HTML (readable using a standard Web browser, or by a decision support system or other automated application). An important element of this encoding is a reconstruction of the medical record in the form of a time-line of events, which permits a detailed and repeatable simulation of the inputs that are potentially available to a real-time \"intelligent\" ICU monitor.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127368604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Contrast-echocardiography and videodensitometry for assessing right ventricular hemodynamics","authors":"M. Suurkula, T. Gustavsson","doi":"10.1109/CIC.1997.647906","DOIUrl":"https://doi.org/10.1109/CIC.1997.647906","url":null,"abstract":"Available techniques for diagnosis and evaluation of right ventricular (RV) function are limited. In patients with arrhythmogenic right ventricular dysplasia (ARVD) it is of great importance to assess RV wall motion and function for diagnosis, prognosis and treatment. Contrast echocardiography and videodensitometry can be used to illustrate regional and global RV hemodynamics. The authors investigated patients with ARVD and healthy volunteers by this method. An off-line analysis system was used for calculation of time intervals and indices of contrast dynamics in different regions of the right ventricle. The data were also color-coded to illustrate, in one single image, the dynamic process of the contrast. The RV wall motion was also assessed by a visual score system. The patient group showed longer time intervals for the processing of the contrast in the right ventricle than the healthy group. The color pattern for the whole process showed regional disturbances in the patient group which corresponded to the wall motion abnormalities as compared to the normals. Color-coded contrast echocardiography with videodensitometry quickly and easily demonstrated disturbances in filling and elimination patterns as signs of abnormal RV function, both regional and global, in patients with ARVD compared to healthy controls.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130467963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Baruthio, A. Koenig, F. Wolff, J. P. Annspach, Jacques Chambron, Daniel Grucker
{"title":"Evaluation of aortic regurgitation with cine-MRI: automatic contour recognition and comparative study with other explorations","authors":"J. Baruthio, A. Koenig, F. Wolff, J. P. Annspach, Jacques Chambron, Daniel Grucker","doi":"10.1109/CIC.1997.647854","DOIUrl":"https://doi.org/10.1109/CIC.1997.647854","url":null,"abstract":"Turbulence and high blood velocity produce a signal loss in Cine-MRI. An automatic calculation of the regurgitant signal loss area is developed and results are correlated with the reference scores of severity, supplied by echography and angiography. This algorithm gives the maximal signal loss area. This absolute area leads to better correlations than the mean or the relative (to left ventricle) areas. Correlation between reference grades and grades obtained through visual observation of Cine-MRI is excellent (r=0.87, p<10/sup -5/), but correlation between reference grades and processed Cine-MRI areas is even better (r=0.92, p<10/sup -5/). An analysis of variance confirms a biunique relation between signal loss areas, and reference grades of severity: no doubt that Cine-MRI should avoid invasive methods to diagnose Aortic Regurgitation, and allow a precise quantification.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123252984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Azuaje, W. Dubitzky, X. Wu, P. Lopes, N. Black, K. Adamson, J. White
{"title":"A neural network approach to coronary heart disease risk assessment based on short-term measurement of RR intervals","authors":"F. Azuaje, W. Dubitzky, X. Wu, P. Lopes, N. Black, K. Adamson, J. White","doi":"10.1109/CIC.1997.647828","DOIUrl":"https://doi.org/10.1109/CIC.1997.647828","url":null,"abstract":"Using short-term heart rate variability (HRV) measurements, this study investigates the relationship between respiratory sinus arrhythmia (RSA) and Coronary Heart Disease (CHD) risk in asymptomatic patients who nevertheless exhibit CHD risk factors. The aim is to train an artificial neutral network (ANN) to recognise HRV patterns related to CHD risk via a Poincare plot encoding. The ANN correctly classified 6 out of 9 'high' 6 out of 9 'medium', and 6 out of 9 'low' risk test cases. It is expected that this result can be improved by increasing the number of input neurons and by using different preprocessing techniques. This study showed that an ANN approach can be successful in detecting individuals at varying risk of CHD based on short-term HRV measurements under controlled breathing.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123342912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Use of fuzzy techniques for the automatic identification of left ventricle contours from multi-slice short-axis MR imaging","authors":"A. Lalande, L. Legrand, P. Walker, F. Brunette","doi":"10.1109/CIC.1997.647852","DOIUrl":"https://doi.org/10.1109/CIC.1997.647852","url":null,"abstract":"An automatic left ventricle (LV) contouring method in multi-slice short-axis MR imaging making use of fuzzy logic and dynamic programming, is presented. Following the extraction of three parameters for each pixel, the membership degree of each pixel to the cardiac contour fuzzy set is calculated. The first parameter takes into account the pixel grey level, the second the presence of an edge and the third the information collected on the precedent slice. The cardiac contours are detected using dynamic programming on the matrix of membership degrees. The method has been tested on thirty image data sets. This preliminary study clearly demonstrates the interest of this method, especially in order to overcome the principal problems met in the automatic cardiac contour detection on MR imaging, such as poor image contrast or the presence of intra-cavity structures.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123012854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Detection of ventricular tachycardia risk by means of Wigner Distribution Interference Terms from the high resolution ECG","authors":"M. Reyna, R. Jané","doi":"10.1109/CIC.1997.648127","DOIUrl":"https://doi.org/10.1109/CIC.1997.648127","url":null,"abstract":"The majority of methods to detect tachycardia risk are aimed to analyze late potentials, as an indicator of sudden cardiac death. However, the majority of these methods present low predictive values. Certainly Wigner Distribution's Interference Terms are considered as troublesome artifacts, because they overlap several signal terms of the analyzed signal over the Time-Frequency Plane. Nevertheless, these interference terms can be used to analyze some kind of multicomponent signals, like signal averaged electrocardiograms. This paper proposes to quantify the Wigner Distribution's Interference Terms into the QRS complex of the Signal Averaged Electrocardiogram, to be used as a non invasive risk factor to predict Ventricular Tachycardia in Post Myocardial Infarcted patients.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123121771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
G. Winterfeldt, M. Berger, J. Lethor, M. Handschumacher
{"title":"Expert-model based 3D reconstruction of the beating left ventricle using echographic images","authors":"G. Winterfeldt, M. Berger, J. Lethor, M. Handschumacher","doi":"10.1109/CIC.1997.647892","DOIUrl":"https://doi.org/10.1109/CIC.1997.647892","url":null,"abstract":"Using a rotating probe combined with an ECG gating technique the authors acquire transthoracic datasets (20 Images per ECG cycle for 9-18 rotations). The aim of this research is the automated left ventricle (LV) reconstruction (3D+t) for later diagnoses. One of the main stages during the reconstruction process is the detection of the moving wall boundaries. Here, the authors propose an approach based on a pre-calculated model of the displacement field of the heart to guide the detection process in combination with active contours. The numerical model obtained during a learning phase can later be used for diagnoses as well.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"45 8 Pt 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125696633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A model of the topology of coronary perfusion based on self-organizing maps","authors":"G. Coppini, E. Tamburini, A. L'Abbate, G. Valli","doi":"10.1109/CIC.1997.648157","DOIUrl":"https://doi.org/10.1109/CIC.1997.648157","url":null,"abstract":"A model of the topology of coronary perfusion based on the theory of self-organizing maps is proposed. The model is based on general physical assumptions about the basic mechanisms of the spatial organization of arterial networks. On the basis of such assumptions the authors obtain a cost functional whose optimization leads to the computation of model parameters. Application to X-ray coronary angiography is described, a particular attention being paid to the assessment of the regions potentially perfused by each vessel. Moreover, in order to account for the potential adaptation of the heart vascular tree to pathological conditions such as vessel lumen reduction, the self-adaptation capabilities of the proposed model are analyzed. Preliminary results from clinical data are described.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121106408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A non-invasive pulse pressure method for the estimation of total arterial compliance","authors":"P. Segers, N. Stergiopulos, P. Verdonck","doi":"10.1109/CIC.1997.647858","DOIUrl":"https://doi.org/10.1109/CIC.1997.647858","url":null,"abstract":"With the Pulse Pressure Method (PPM; Stergiopulos et al., 1994), total arterial compliance can be estimated accurately from simultaneously measured aortic flow (Q/sub a0/) and pulse pressure (PP/sub a0/). The PPM is modified in 2 ways, yielding a non-invasive PPM (NIPPM): (i) Q/sub a0/ is replaced by a triangular flow, reconstructed from cardiac output, and is characterised by its base T/sub ej/ (systolic ejection time) and peak flow 2SV/T/sub ej/ (SV=stroke volume) at T/sub ej//3; (ii) PP/sub a0/ is estimated from a tonometric radial pressure measurement and a generalised aorta-radial pressure transfer function (TFF/sub g/). Application of the NIPPM on data from a group of hypertensive patients and young normotensive volunteers shows that (i) PP/sub a0/ is higher in the hypertensives for a same PP/sub r/ad; (ii) TAC is reduced from 2.11+/-0.51 ml/mmHg in the young volunteers to 1.13+/-0.51 ml/mmHg in the hypertensives.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"35 33","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113934270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"24 hour variability of ventricular premature beats coupling interval in patients with ischemic heart disease","authors":"M. Sosnowski, M. Tendera","doi":"10.1109/CIC.1997.648128","DOIUrl":"https://doi.org/10.1109/CIC.1997.648128","url":null,"abstract":"The study was designed to analyse the diurnal variations of coupling interval of ventricular premature beats (VPBs) in 12 patients with ischemic heart disease and frequent VPBs. 24 hour ECG recordings and analyses were performed using commercially available system and software. Data were compared in six epochs of 4 hour period each. In total 72 epochs were analysed. The coupling interval of VPBS varied throughout 24 hours and reflected those of RR interval. Greater differences were found in 5% values of PVBs-CI ranged from 435/spl plusmn/46 ms at 10 AM to 484/spl plusmn/61 ms at 10 PM (p<0.001). Standard deviation of PVBs-CI ranged from 73.8/spl plusmn/47.7 ms at 6 AM to 52.3/spl plusmn/22.8 at 2 PM (ns). Longer PVBS-CI, as well as greater standard deviation of CI were found in patients with low ejection fraction, non-sustained VT or in those, who subsequently died. It is concluded that evaluation of variability of coupling interval of PVBS from 24 hour ECG recodings may be a novel tool for quantifying ventricular arrhythmia.","PeriodicalId":228649,"journal":{"name":"Computers in Cardiology 1997","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131783032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}