[ANMCO Position paper: From acute to chronic disease: the needs of complex cardiac patients]

Managing a patient suffering from a chronic disease requires a multidisciplinary team that can take care of them beyond the simple coordination of various specialties. In this context, a central role in the treatment of chronic heart disease is the continuity of care that should promote organic integration among different hospital departments, hospital and community. This position paper of the Italian Association of Hospital Cardiologists (ANMCO) aims at defining the general principles to inspire care for complex cardiac patients at different phases of the disease. A multidisciplinary integrated holistic approach uses analytical tools able to understand the elements that characterize complexity and therefore suggest appropriate management strategies: (i) care pathways aimed at optimizing treatments; (ii) care pathways in intensive care and ward in a multidisciplinary perspective; (iii) integration of social and health needs; (iv) nursing role in the context of continuity of outpatient, community and home care; (v) promotion of educational interventions.

Bioimpedance vector analysis predicts hospital length of stay in acute heart failure

OBJECTIVE

Congestion in acute heart failure (AHF) affects survival curves and hospital length of stay (LOS). The evaluation of congestion, however, is not totally objective. The aim of this study was to verify the accuracy of bioelectrical impedance vector analysis (BIVA) in predicting the LOS in AHF patients.

METHODS

This is a retrospective study. A total of 706 patients (367 male; mean age: 78 ± 10 y) who had been admitted to hospital with an AHF event were enrolled. All underwent anthropometric and clinical evaluation, baseline transthoracic echocardiography, and biochemical and BIVA evaluations.

RESULTS

The comparison among the clinical characteristics of congestion, LOS, and hyperhydration status revealed that the higher the hydration status, the longer the LOS (from 7.36 d [interquartile range: 7.34-7.39 d] in normohydrated patients to 9.04 d [interquartile range: 8.85- 9.19 d] in severe hyperhydrated patients; P < 0.05). At univariate analysis, brain natriuretic peptide, blood urea nitrogen, New York Heart Association class, hemoglobin, hydration index, and peripheral edema all had a statistically significant influence on LOS. At multivariate analysis, only brain natriuretic peptide (P < 0.0001), blood urea nitrogen (P = 0.011), and hydration index (P < 0.0001) were significantly associated to LOS.

CONCLUSIONS

Congestion evaluated by BIVA is an independent predictor of length of total hospital stay in HF patients with acute decompensation. The quick and reliable detection of congestion permits the administration of target therapy for AHF, thus reducing LOS and treatment costs.

What constitutes the ‘Minimal Care’ interventions of the nurse, physiotherapist, dietician and psychologist in Cardiovascular Rehabilitation and secondary prevention: A position paper from the Italian Association for Cardiovascular Prevention, Rehabilitation and Epidemiology

Background

In cardiovascular prevention and rehabilitation, care activities are carried out by different professionals in coordination, each with their own specific competence. This GICR–IACPR position paper has analysed the interventions performed by the nurse, physiotherapist, dietician and psychologist in order to identify what constitutes minimal care, and it lists the activities that are fundamental and indispensable for each team member to perform in clinical practice.

Results

In analysing each type of intervention, the following dimensions were considered: the level of clinical care complexity, determined both by the disease and by environmental factors; the ‘area’ complexity, i.e. the specific level of competence required of the professional in each professional section; organisational factors, i.e. whether the care is performed in an inpatient or outpatient setting; duration of the rehabilitation intervention. The specific contents of minimal care have been identified for each professional area together with the specific goals, the assessment tools and the main essential interventions. For the assessments, only a few validated tools have been indicated, leaving the choice of which instrument to use to the individual professional based on experience and usual practice.

Conclusion

For the interventions, attention has been focused on conditions of major complexity requiring special care, taking into account the different care settings, the clinical conditions secondary to the disease event, and the distinct tasks of each area according to the operator's specific role. The final report performed by each professional has also been included.

[Audit of medical records]

OBJECTIVE

TO assess the quality of medical records in a university teaching hospital in Africa.

MATERIAL AND METHODS

We conducted a retrospective study at the Souro Sanou University Teaching Hospital of Bobo Dioulasso in Burkina Faso, by randomly selecting 480 medical records from 4 clinical departments (internal medicine, obstetrics & gynaecology, paediatrics and surgery). Items recorded were based mainly on those used by the French agency for the evaluation of health services (now the HAS). Ten physicians were also interviewed about medical file ergonomics file. Descriptive statistics were compiled from the data collected.

RESULTS

Only 368 of the 480 records could be found. Two of the four departments had an adequate record room. Assessment of the overall quality of the files noted that: i) 95 to 100% of the records were in good physical condition; ii) the handwriting in the files was legible in 94 to 100% of the cases; iii) the identity of the staff members making file entries could be determined in 73 to 92% of the cases. A detailed examination of the content of the files revealed that: i) the patient's social and demographic characteristics (name, sex, age, residence, occupation, marital status and religion) were available in 26 to 99% of the cases; ii) the mode of admission was noted in 52 to 88%; iii) the reason for admission was stated in 83 to 100%; iv) the main diagnosis was reported in 68 to 100%; v) surgery notes were found for 93 to 100% of patients who underwent surgery; vi) the disposition on discharge was not found in 31% of the records; vii) the circumstances of death were not recorded for 77% of the patients who died.

CONCLUSION

The quality of medical records at Souro University Teaching Hospital must be improved, through improving staff awareness and regular audits.

How often we need to measure brain natriuretic peptide (BNP) blood levels in patients admitted to the hospital for acute severe heart failure? Role of serial measurements to improve short-term prognostic stratification

BACKGROUND

Brain natriuretic peptide (BNP) is increasingly used in the management of patients with heart failure (HF). It is still unclear how to use serial BNP measurement in HF.

AIM

To evaluate the usefulness of three consecutive measurements of BNP in patients (pts) hospitalized for acute HF.

METHODS

Clinical evaluation, BNP levels and echocardiography were assessed in 150 pts (67% males, age: 69+/-12 years; left ventricular ejection fraction: 34+/-14%) admitted for severe HF (NYHA class III-IV: 146/150). BNP measurements were obtained: at admission (basal, T0), at discharge (T1) and at first ambulatory control (T2), after optimization of medical therapy in those with discharge BNP level >250 pg/mL. End-points were death and hospital readmission during 6-month follow-up.

RESULTS

According to BNP levels 3 groups of patients were identified: Group 1 (62 pts, 41%), in whom discharge (T1) BNP was high and persisted elevated at T2 despite aggressive medical therapy; at 6-month follow-up 72% died or were hospitalized for HF. Group 2 (36 pts, 24%), in whom discharge (T1) BNP was high but decreased after medical therapy (T2); death and HF-readmission were observed in 8 pts (26%). Group 3 (52 pts, 35%), in whom discharge (T1) BNP levels were <250 pg/mL and persisted below this value at T2; death and HF-hospital readmission were observed in 6 pts (12%). Event rate differences among groups were statistically significant (p<0.001). At Cox-analysis discharge BNP cutoff of 250 pg/mL was the only parameter predictive of a worse outcome.

CONCLUSION

These data suggest that 3 BNP measurements, at admission, at discharge and few weeks later can allow to identify HF pts whom, despite a further potentiation of medical therapy, will present a worsening or even will die during short-term follow-up.

Fall in readmission rate for heart failure after implementation of B-type natriuretic peptide testing for discharge decision: A retrospective study

BACKGROUND

B-type natriuretic peptide is the most powerful predictor of long term prognosis in patients hospitalised with heart failure. On an outsetting basis, a decrease in B-type natriuretic peptide levels is associated to a decrease in event rate for outpatients managed using the neuro-hormone levels as the target in heart failure therapy. We have retrospectively checked whether the addition of pre-discharge B-type natriuretic peptide levels to a clinical-instrumental decisional score for discharge decision in patients admitted for heart failure reduced readmission rate for heart failure and related cost.

METHODS

We studied two series of consecutive patients admitted to the Heart Failure Unit due to acute heart failure as a main diagnosis. One-hundred and forty-nine patients discharged on the basis of the sole clinical acumen were compared to one hundred and sixty-six subjects discharged adding B-type natriuretic peptide levels to the decisional score.

RESULTS

During a six-month follow-up period, there were 52 readmissions (35%) among the clinical group (n=149) compared with 38 (23%) readmissions in the B-type natriuretic peptide group (n=166) (chi(2)=5.5; P=0.02). Survival did not differ between groups (87%). Changes in B-type natriuretic peptide values were correlated to clinical events: a B-type natriuretic peptide value on discharge of < or =250 pg/ml or a reduction of > or =30% in B-type natriuretic peptide values predicted a 23% event rate (death, plus readmission for heart failure), whereas a far higher percentage (71%) were observed in the remaining patients (chi(2)=32.7; P=0.001). Likewise, the overall costs of care were lower (-7%) in the B-type natriuretic peptide group: 2.781+/-923 vs 2.978+/-1.057 euros per patient respectively.

CONCLUSIONS

our study suggest that the addition of pre-discharge B-type natriuretic peptide levels to a clinical-instrumental decisional score for discharge decision in patients admitted for heart failure may contribute to reduce the number of readmissions and related cost.

Prognostic role of B-type natriuretic peptide in patients with diabetes and acute decompensated heart failure

BACKGROUND

Several studies have reported the prognostic value of natriuretic peptides, but their predictive value in patients with diabetes mellitus is unknown. The aim of the study was to test the hypothesis that measurement of brain natriuretic peptide (BNP) levels in ambulatory patients with congestive heart failure (CHF) and diabetes can predict the occurrence of cardiovascular events at 6-month follow-up.

METHODS

We enrolled 145 consecutive patient with diabetes [age 72 +/- 9 years, hypertension (21%), ischaemic heart disease (52%), atrial fibrillation (22%), preserved left ventricular function (29%)] seen in the outpatient heart failure clinic after an acute episode of cardiac failure.

RESULTS

The median (25th/75th interquartile range) BNP concentrations at discharge were 186 (75-348) pg/ml. At 6-month clinical follow-up 10/145 (7%) subjects had died and 31/145 (21%) had been readmitted because of cardiac decompensation. BNP values of 200 and 500 pg/ml were found to have the best compromise between sensitivity (88 and 46%, respectively) and specificity (71 and 89%, respectively) for predicting events at 6 months. Multivariate Cox regression analysis identified only two parameters as predictors of events: serum creatinine [hazard ratio (HR) = 3.3; P = 0.02], and BNP plasma level BNP cut-off values (HR = 3.8; P = 0.03 for 201-499 pg/ml and HR = 7.7; P = 0.001 for > or = 500 pg/ml).

CONCLUSION

These results suggest that BNP and serum creatinine are strong predictors of clinical events in patients with diabetes and CHF. In these patients, clinical outcome might be stratified by plasma BNP levels.

[Heart failure in Eastern Veneto: prevalence, hospitalization rate, adherence to guidelines and social costs]

Heart failure is a prominent problem of public health, requiring innovating methods of health services organization. Nevertheless, data are still not available on prevalence, hospitalization rate, adherence to Guidelines and social costs in the general Italian population. The necessity to identifying patients with heart failure derives from the efficacy of new therapeutic interventions in reducing morbidity and mortality. In this study we aimed to identify, in a subset of the Eastern Veneto population, patients with heart failure through a pharmacologic-epidemiologic survey. The study was divided in 5 phases: (1) identification of patients on furosemide in the year 2000 in the ASL 10 of Eastern Veneto general population, through an analysis of a specific pharmaceutic service database; (2) definition of the actual prevalence of heart failure in a casual sample of these patients, through data base belonging to general practitioners, cardiologists, or others. Diagnosis was based on the following criteria: (a) previous diagnosis of heart failure; (b) previous hospitalization for heart failure; (c) clinical evidence, with echocardiographic control in unclear cases; (3) survey of hospitalizations; (4) evaluation of adhesion to guidelines, through both databases and questionnaires; (5) analysis of the social costs of the disease, with a retrospective "bottom up" approach. From a total population of 198,000 subjects, we identified 4502 patients on furosemide. In a casual sample of 10,661 subjects we defined a prevalence of heart failure in Eastern Veneto of 1.1%, that increased to 7.1% in octagenarians. The prescription of life saving drugs was satisfactory, while rather poor was the indication to echocardiography and to cardiologic consultation. Hospitalization rate for DRG 127 was low: 2.1/1000 inhabitants/year in the general population and 12.5 /1000 inhabitants/year in patients >70 years of age. Yearly mortality was 10.3%. Social costs were elevated (15.394 Euros/patient/year), due to a relevant sanitary component (hospital 53%, drugs 28%) and particularly a to an indirect cost component. In conclusion, the assumption of furosemide lends itself as a good marker for identifying patients with heart failure. Patient identification is simple, cheap and cost-efficient, and can be easily reproduced in other regional areas.

B-type natriuretic peptide predicts postdischarge prognosis in elderly patients admitted due to cardiogenic pulmonary edema

To examine the prognostic role of predischarge B-type natriuretic peptide (BNP) levels in elderly patients admitted to the hospital due to cardiogenic pulmonary edema, 203 patients consecutively admitted to the Heart Failure Unit of the Cardiology Department were retrospectively evaluated. The primary clinical end point selected was a combination of: 1) deaths; plus 2) readmissions to the hospital for heart failure in the 6 months after discharge. Thirty-one deaths (15.3%) and 44 readmissions for heart failure (21.7%) were recorded. Cox multivariate regression analysis confirmed that BNP cutoff values (identified on receiver-operated curve analysis) are the most accurate predictor of events. Hazard ratios (HRs) increased from the lowest, for BNP < or = 200 pg/mL (HR=1), through BNP 201-499 pg/mL (HR=2.3200; p=0.0174), to the highest, for BNP > or = 500 pg/mL (HR=3.6233; p=0.0009). This study demonstrates that BNP is useful in predischarge risk stratification of elderly patients with cardiogenic pulmonary edema.

The BNP assay does not identify mild left ventricular diastolic dysfunction in asymptomatic diabetic patients

AIMS

We examined the usefulness of BNP for screening for left ventricular (LV) diastolic dysfunction in a sample of type 2 diabetic patients, without structural heart disorder, who have never presented symptoms or signs of heart failure (HF).

METHODS AND RESULTS

Seventy-six consecutive patients admitted to the Outpatient Diabetes Clinic were studied. Blood samples were analyzed using the Triage BNP fluorescence immunoassay (Biosite Diagnostics, La Jolla, CA, USA). Echocardiography examinations were performed, with no knowledge of the BNP value. A total of 39 patients out of 76 (51%) were diagnosed with LV diastolic dysfunction and 23 (30%) with LV hypertrophy. Of the patients with LV diastolic dysfunction, impaired relaxation and pseudonormal pattern accounted for 97 and 3% of the cases, respectively. BNP levels among subjects with LV diastolic dysfunction (26+/-22 pg/ml, n=39) were not significantly different from patients with normal LV function (24+/-23 pg/ml, n=37 pg/ml; Mann-Whitney U-test, Z=-0.4, n.s.).

CONCLUSIONS

Our data confirm alarmingly high prevalence of LV diastolic dysfunction in asymptomatic individuals with diabetes. Identification of patients with preclinical diabetic cardiomyopathy should be a research and clinical priority. BNP levels cannot be used to detect mild LV diastolic dysfunction in this subset of patients, which requires Doppler echocardiography to be detected.

B-Type Natriuretic Peptide Can Predict the Medium-Term Risk in Patients With Acute Heart Failure and Preserved Systolic Function

BACKGROUND

Half of patients with heart failure (HF) have preserved left ventricular ejection fraction (LVEF). Neurohormonal activation characterizes the disease and measurement of plasma B-type natriuretic peptide (BNP) indicates the severity of left ventricular dysfunction. The purpose of this study was to test the hypothesis that measurement of BNP levels in ambulatory patients with HF and preserved LVEF can predict the occurrence of cardiovascular events in the next 6 months.

METHODS AND RESULTS

We enrolled 233 consecutive patients admitted to the Outpatient Heart Failure Clinic (OHFC), on stabilization after an episode of acute HF, with a LVEF > 50%. Standard echocardiography was performed and left ventricular systolic/diastolic function was assessed. Plasma BNP levels were measured on admission to OHFC. Patients were followed for 6 months; the main endpoint combined cardiovascular death or readmission for HF. Among the 233 patients discharged, 48 endpoints occurred (death: n = 15; readmission: n = 33). Receiver operated curve analysis shows that BNP levels are strong predictors of subsequent events (area under the curve = 0.84; CI = 0.78-0.88). Multivariate Cox regression showed that the cutoff values identified by receiver operated curve analysis (200-500 pg/mL) of the neurohormone are the most accurate predictors of events: HR = 2.2 (P < .04) and HR = 5.8 (P < .001), respectively, for 201-499 pg/mL and > or = 500 pg/mL ranges.

CONCLUSION

BNP level is a strong predictor for cardiovascular mortality and early readmission in patients with diastolic HF. The results suggest that BNP levels might be used successfully to guide the intensity of follow-up after a decompensation, because increased BNP levels were associated with a progressively bad prognosis.

The NT-proBNP assay identifies very elderly nursing home residents suffering from pre-clinical heart failure

BACKGROUND

Little is known about the prevalence of heart failure among very old people, although hospitalisation rates for chronic heart failure are very high. Recently, brain natriuretic peptides have emerged as important diagnostic and prognostic serum markers for congestive heart failure.

AIMS

The main purpose of our study was to determine whether there is a cut-off for NT-proBNP for detecting the echocardiographic features of left ventricular systolic and/or diastolic dysfunction and clinical heart failure among old people living in nursing homes. Secondarily, we investigated the medium-term prognostic power of the neurohormone levels.

METHODS

We screened 101 old people (80% females, aged 84+/-9 years) from two nursing homes. We prospectively evaluated whether we could effectively stratify patients using a combination of (1) restrictive clinical criteria, (2) NT-proBNP measurements (Elecsys System, Roche Diagnostics) and (3) echocardiography for all patients.

RESULTS

Forty-two percent of the subjects had left ventricular dysfunction: 11% systolic, 23% diastolic and 8% both systolic and diastolic. The mean NT-proBNP concentration was 2806+/-7028 pg/ml in the 42 patients with left ventricular systolic and/or diastolic dysfunction, compared with 365+/-456 pg/ml in the 59 patients with normal left ventricular function (p<0.01, Z=-4.8 Mann-Whitney U test). The neurohormone proved to be a good predictor of events within 6 months [area under the receiver-operated curve (ROC)=0.79].

CONCLUSIONS

Blood NT-proBNP concentrations can play an important role in stratifying old people into left ventricular dysfunction risk groups. The neurohormone is an independent marker for death or admission for heart failure in the medium term.

Epilepsy and traditional medicine in Bobo-Dioulasso (Burkina Faso)

OBJECTIVES

To contribute to a better knowledge of how epilepsy is perceived by traditional healers in Burkina Faso; what means they use to treat it, and how they think about modern treatment.

MATERIAL AND METHODS

Individual interviews with 65 traditional healers chosen at random from members of the Reelwende Association.

RESULTS

All traditional practitioners were of male gender. Most of them were above 50 years of age, and 75% had more than 10 years' experience. Epilepsy was considered to be contagious by 44% of the traditional practitioners, and hereditary according to 40% of them. Roughly, 15% of the healers think that the problem is localized in the head of a person and 7.8% think that they have worms in their head. Thirty-one per cent of them diagnose epilepsy if there is a combination of 'convulsions, sudden fall, dribbling and amnesia'. Another 15% require a combination of 'convulsions, amnesia and dribbling', the remaining 54% make the diagnosis based on one symptom or various combinations of two symptoms of 'grand mal' (generalized tonic clonic) seizures and most claim they have a treatment for it. For a quarter of them, therapeutic-means include concoctions of herbs or roots, baths and infusions. During the fit, 31% of the traditional practitioners think that nothing should be performed. According to 75% of them, traditional and modern treatments are complementary.

CONCLUSION

Notwithstanding important differences in culture and religions (Muslim, Christian and Original), there is great similarity between the knowledge and beliefs about epilepsy reported from other parts of Africa and those presented by our study-group, suggesting an ancient origin of the concepts. Further study is needed to find out how other facets of epilepsy (e.g. complex partial seizures, absences) are perceived and how these are being treated. Ways need to be found to raise awareness about epilepsy without interfering with religious and cultural beliefs.

Authentication of Galician (N.W. Spain) quality brand potatoes using metal analysis. Classical pattern recognition techniques versus a new vector quantization-based classification procedure

The objective of this work was to develop a classification system in order to confirm the authenticity of Galician potatoes with a Certified Brand of Origin and Quality (CBOQ) and to differentiate them from other potatoes that did not have this quality brand. Elemental analysis (K, Na, Rb, Li, Zn, Fe, Mn, Cu, Mg and Ca) of potatoes was performed by atomic spectroscopy in 307 samples belonging to two categories, CBOQ and Non-CBOQ potatoes. The 307 x 10 data set was evaluated employing multivariate chemometric techniques, such as cluster analysis and principal component analysis in order to perform a preliminary study of the data structure. Different classification systems for the two categories on the basis of the chemical data were obtained applying several commonly supervised pattern recognition procedures [such as linear discriminant analysis, K-nearest neighbours (KNN), soft independent modelling of class analogy and multilayer feed-forward neural networks]. In spite of the fact that some of these classification methods produced satisfactory results, the particular data distribution in the 10-dimensional space led to the proposal of a new vector quantization-based classification procedure (VQBCP). The results achieved with this new approach (percentages of recognition and prediction abilities > 97%) were better than those attained by KNN and can be compared advantageously with those provided by LDA (linear discriminant analysis), SIMCA (soft independent modelling of class analogy) and MLF-ANN (multilayer feed-forward neural networks). The new VQBCP demonstrated good performance by carrying out adequate classifications in a data set in which the classes are subgrouped. The metal profiles of potatoes provided sufficient information to enable classification criteria to be developed for classifying samples on the basis of their origin and brand.

Detection of abnormality in the electrocardiogram without prior knowledge by using the quantisation error of a self-organising map, tested on the European ischaemia database

Most systems for the automatic detection of abnormalities in the ECG require prior knowledge of normal and abnormal ECG morphology from pre-existing databases. An automated system for abnormality detection has been developed based on learning normal ECG morphology directly from the patient. The quantisation error from a self-organising map 'learns' the form of the patient's ECG and detects any change in its morphology. The system does not require prior knowledge of normal and abnormal morphologies. It was tested on 76 records from the European Society of Cardiology database and detected 90.5% of those first abnormalities declared by the database to be ischaemic. The system also responded to abnormalities arising from ECG axis changes and slow baseline drifts and revealed that ischaemic episodes are often followed by long-term changes in ECG morphology.

Characterization of Galician (N.W. Spain) quality brand potatoes: a comparison study of several pattern recognition techniques

Authenticity is an important food quality criterion and rapid methods to guarantee it are widely demanded by food producers, processors, consumers and regulatory bodies. The objective of this work was to develop a classification system in order to confirm the authenticity of Galician potatoes with a Certified Brand of Origin and Quality (CBOQ) 'Denominación Específica: Patata de Galicia' and to differentiate them from other potatoes that did not have this CBOQ. Ten selected metals were determined by atomic spectroscopy in 102 potato samples which were divided into two categories: CBOQ and non-CBOQ potatoes. Multivariate chemometric techniques, such as cluster analysis and principal component analysis, were applied to perform a preliminary study of the data structure. Four supervised pattern recognition procedures [including linear discriminant analysis (LDA), K-nearest neighbours (KNN), soft independent modelling of class analogy (SIMCA) and multilayer feed-forward neural networks (MLF-ANN)] were used to classify samples into the two categories considered on the basis of the chemical data. Results for LDA, KNN and MLF-ANN are acceptable for the non-CBOQ class, whereas SIMCA showed better recognition and prediction abilities for the CBOQ class. A more sophisticated neural network approach performed by the combination of the self-organizing with adaptive neighbourhood network (SOAN) and MLF network was employed to optimize the classification. Using this combined method, excellent performance in terms of classification and prediction abilities was obtained for the two categories with a success rate ranging from 98 to 100%. The metal profiles provided sufficient information to enable classification rules to be developed for identifying potatoes according to their origin brand based on SOAN-MLF neural networks.

Fuzzy logic in a patient supervision system

A patient supervision system in progress for intensive and coronary care units, focused on patients with acute myocardial infarct is briefly described particularly regarding the role that fuzzy logic is playing in its design, and why this is so.

A new approach for TU complex characterization

In this paper, we present a new TU complex detection and characterization algorithm that consists of two stages; the first is a mathematical modeling of the electrocardiographic segment after QRS complex; the second uses classic threshold comparison techniques, over the signal and its first and second derivatives, to determine the significant points of each wave. Later, both T and U waves are morphologically classified. Amongst the principal innovations of this algorithm is the inclusion of U-wave characterization and a mathematical modeling stage, that avoids many of the problems of classic techniques when there is a low signal-to-noise ratio or when wave morphology is atypical. The results of the algorithm validation with the recently appeared QT database are also shown. For T waves these results are better when compared to other existing algorithms. U-wave results cannot be contrasted with other algorithms as, to our knowledge, none are available. Examples showing the causes of principal discrepancies between our algorithm and the QT database annotations are also given, and some ways of attempting to improve and benefit from the proposed algorithm are suggested.

A problem-solving method for 'unprotocolised' therapy administration task in medicine

This paper describes a problem-solving method for modelling the 'unprotocolised' treatment administration task in medicine. We argue that there are medical domains in which no well-established standard treatment protocols exist, and the physician has to decide on the therapy that is to be applied to each patient, in function of a set of therapeutic objectives to be fulfilled. For this reason, we propose the modelling of this type of task adapting the generic class of problem resolution methods for design task, labelled as Propose-Critique-Modify (PCM). In this paper, we are presenting a model of expertise which has been developed using the basic modelling components of the CommonKADS methodology.

SUTIL: intelligent ischemia monitoring system

SUTIL is an intelligent monitoring system for intensive and exhaustive follow up of patients in coronary care units. This system processes electrocardiographic and hemodynamic signals in real time, with the main objective of detecting ischemic episodes. In this paper, we describe the tasks included in SUTIL. In addition to basic tasks, those at higher levels will also be presented. Some of these latter tasks attempt to mimic, to some extent, the way in which the human expert operates.

Grammatic representation of beat sequences for fuzzy arrhythmia diagnosis

The final stage of a system for automatic monitoring of cardiac arrhythmias is the diagnosis of the rhythm or arrhythmia present in the patient during the monitoring process. In this paper we approach the detection process by means of the analysis of the electrocardiographic signal (ECG) on a surface lead produced by those arrhythmias which can be recognized by identifying specific beat sequences and taking into account contextual information, mainly rhythm information. We have developed a diagnosis process for arrhythmias which uses a fuzzy classification of beats according to their etiology or focus of origin. The process we describe permits a more adequate consideration by the user of the arrhythmias diagnosed by the system, mainly in those cases in which the information derived from ECG analysis is not determinant.

Fuzzy K-nearest neighbor classifiers for ventricular arrhythmia detection

We report a study of the efficiency of 4 classifiers (the K-nearest-neighbor and single-nearest-prototype algorithms, each as parametrized by both Fuzzy C-Means and Fuzzy Covariance clustering) in the detection of ventricular arrhythmias in ECG traces characterized by 4 features derived from 7 spectral parameters. Principal components analysis was used in conjunction with a cardiologist's deterministic classification of 90 ECG traces to fix the number of trace classes to 5 (ventricular fibrillation/flutter, sinus rhythm, ventricular rhythms with aberrant complexes and 2 classes of artefact). Forty of the 90 traces were then defined as a test set; 5 different learning sets (numbering 25, 30, 35, 40 and 45 traces) were randomly selected from the remaining 50 traces; each learning set was used to parametrize both the classification algorithms using both fuzzy clustering algorithms and the parametrized classification algorithms were then applied to the test set. Optimal K for K-nearest-neighbor algorithms and optimal cluster volumes for Fuzzy Covariance algorithms were sought by trial and error to minimize classification differences with respect to the cardiologist's classification. Fuzzy Covariance clustering afforded significantly better perception of cluster structure than the Fuzzy C-Means algorithm, and the classifiers performed correspondingly with an overall empirical error ratio of just 0.10 for the K-nearest-neighbor algorithm parametrized by Fuzzy Covariance.

Multimicroprocessor system for online monitoring in a CCU

A real-time monitoring system for physiological signals, developed for patients in coronary care units (CCUs), is described. This system monitors the signals that have the greatest clinical value in a CCU environment (ECG and cardiovascular pressures), taking charge of detecting dangerous situations and of extracting information significant to the correct monitoring of the patient. The information it extracts, mainly from the ECG, is presented to the user in an ergonomic way using written reports and graphs which collect and compile the information, facilitating its interpretation. Some utilities have been developed to allow the user to modify certain monitoring conditions as well as to correct results derived from them, thereby improving the reliability of the monitoring process. The system uses a multimicroprocessor architecture (imposed by the need to perform a large number of tasks in real time) with a block based on the VME bus, charged with acquiring and processing the monitored signals, and an IBM-compatible PC/XT which is used as a system user interface and a massive storage device in which the information resulting from the monitoring of signals is stored.

Fuzzy beat labeling for intelligent arrhythmia monitoring

The performance in automatic diagnosis of cardiac rhythm based on the analysis of the electrocardiographic signal (ECG) is strongly conditioned by the correct classification of each beat detected. In this work we present a fuzzy classifier of beats that applies empiric criteria and that permits it to ignore the frequent lack of clarity in the information coming from previous stages within ECG processing. The classification of each beat is performed applying diffuse conditional statements which represent the knowledge of the cardiologist expert and that use a set of descriptions of the temporal and morphological attributes of the analyzed beat. The process of classification is completed with information derived from the consideration of "families," which group beats that have QRSs of similar morphology, and with information brought in by the user himself in the monitoring process. The modularity of the classifier that has been developed facilitates the incorporation of new descriptions and classification criteria in order to increase its reliability. The design process proposed has a structure that is transferable to other analysis and event classification processes.

Algorithmic sequential decision-making in the frequency domain for life threatening ventricular arrhythmias and imitative artefacts: a diagnostic system

A preliminary study to approach the problem of reliably detecting life threatening ventricular arrhythmias in real time is described. An algorithm (DIAGNOSIS) has been developed in order to classify ECG signal records on the basis of the computation of four simple parameters calculated from a representation in the frequency domain. This algorithm uses a set of rules constituting an operative classification scheme based on the comparison of the parameters with a set of pre-established thresholds. This allows us to differentiate four general categories: ventricular fibrillation-flutter, ventricular rhythms, imitative artefacts and predominant sinus rhythm.