Real-time prediction of acute cardiovascular events using hardware-implemented Bayesian networks.

This paper presents a decision support system that aims to estimate a patient׳s general condition and detect situations which pose an immediate danger to the patient׳s health or life. The use of this system might be especially important in places such as accident and emergency departments or admission wards, where a small medical team has to take care of many patients in various general conditions. Particular stress is laid on cardiovascular and pulmonary conditions, including those leading to sudden cardiac arrest. The proposed system is a stand-alone microprocessor-based device that works in conjunction with a standard vital signs monitor, which provides input signals such as temperature, blood pressure, pulseoxymetry, ECG, and ICG. The signals are preprocessed and analysed by a set of artificial intelligence algorithms, the core of which is based on Bayesian networks. The paper focuses on the construction and evaluation of the Bayesian network, both its structure and numerical specification.

Age-dependency of classic and new parameters of diastolic function.

UNLABELLED: Age-dependency has been demonstrated for classic diastolic parameters but is less documented for novel markers. We compared wide spectrum of diastolic measurements in healthy subjects younger and older than 50 and 70 years. METHOD: In 80 subjects (17 to 91 year, 38 male, mean age 53 +/- 16) we assessed in transthoracic echocardiography mitral inflow, pulmonary vein flow, propagation velocity, and tissue Doppler parameters. The data were compared between the groups: A < 50, B 50-70, and C > 70 years and their correlation with age was analyzed. RESULT: In the older groups a longer duration of isovolumic relaxation, higher velocity of mitral inflow atrial phase, and lower early to atrial mitral inflow velocity ratio (E/A) were observed. In pulmonary veins ratio of peak systolic to diastolic velocity (S/D) was higher and atrial reversal flow faster. Among the new parameters in older groups a lower propagation velocity of early wave (Ep) (30 +/- 8 in C, 44 +/- 10 in B vs 49+/-9 cm/s in A;P< 0.05) and peak early diastolic velocity of mitral annulus (E' 9.5 +/- 1.8 in C and 11.2 +/- 2.9 in B vs 15.8 +/- 4.1 cm/s in A,P< 0.05) were recorded. CONCLUSIONS: Besides the evolution of mitral inflow toward the delayed relaxation profile in elderly, a decrease of propagation and tissue Doppler velocities were documented. The strongest positive correlation with age was observed for atrial velocity of mitral inflow (A, r = 0.63) and inverse correlation for E/A ratio (r =-0.6) and early diastolic velocity of mitral annulus (r =-0.69).

Pulmonary edema prognostic score predicts in-hospital mortality risk in patients with acute cardiogenic pulmonary edema.

BACKGROUND: Congestive heart failure is a common cardiac disorder associated with a high mortality. There are a limited number of prognostic scales predicting in-hospital outcomes after an acute episode of congestive heart failure. OBJECTIVES: The goal of this investigation was to develop a simple prognostic score predicting in-hospital outcome in patients with acute cardiogenic pulmonary edema. METHODS: We retrospectively studied 276 consecutive patients hospitalized with acute pulmonary edema from the years 1998 to 2000. RESULTS: During the initial hospitalization, 58 patients (21%) died and 218 patients (79%) were discharged. Statistical analyses revealed that the most significant predictors of inhospital mortality were acute myocardial infarction, heart rate greater than 115/beats/min, systolic blood pressure of 130 mm Hg or less, and white blood cell count greater than 11,500/mm3 on presentation. The presence of each factor was scored as 1 point, and the absence was scored as 0 points. The Pulmonary Edema Prognostic Score (PEPS) was defined as a sum of all points. Patients with a PEPS of 0 had good short-term prognosis with a 2% in-hospital mortality rate, whereas mortality in patients with a PEPS of 4 was 64%. CONCLUSIONS: The PEPS is a simple tool that can be easily calculated using common clinical diagnostic tests (electrocardiogram, blood pressure, heart rate, and white cell count) to determine in-hospital mortality risk in patients with an acute episode of cardiogenic pulmonary edema.

Clinical presentation and pharmacological therapy in patients with cardiogenic pulmonary oedema.

BACKGROUND: Cardiogenic pulmonary oedema is a typical clinical presentation of acute heart failure and is associated with a poor outcome. Therapeutic strategies in patients with this condition have not yet been uniformly developed and are based on expert consensus rather than results of randomised studies. The underlying aetiology seems to be one of the most important factors influencing therapy. AIM: To evaluate treatment of patients with acute cardiogenic pulmonary oedema. METHODS: The analysed group consisted of 276 consecutive patients who were treated due to acute cardiogenic pulmonary oedema in two cardiac centres in the city of Lódz between 1998 and 2000. Clinical characteristics, aetiology and therapy were retrospectively analysed based on medical records. RESULTS: Fifty nine (21%) patients died in hospital whereas the remaining 218 subjects were discharged. Etiologic Results. Fifty nine (21%) patients died in hospital whereas the remaining 218 subjects were discharged. Etiologic factors included a marked elevation of blood pressure (BP) (29%), acute myocardial infarction (MI) (25%), unstable angina (16%), decompensation of valvular disorder (9%), respiratory tract infection (8%) and paroxysmal atrial fibrillation (4%). The highest in-hospital mortality (35%) was associated with acute MI, and the lowest (6%) - with BP elevation. The most frequently used agents during in-hospital stay were diuretics (89%), followed by antibiotics (84%) and acetylsalicylic acid (81%). Compared with survivors, patients who died during hospital stay were significantly more frequently treated with catecholamines (59% vs 7%, p<0.00001), corticosteroids (71% vs 15%, p<0.00001) and morphine (62% vs 41%, p<0.0015) whereas angiotensin converting enzyme inhibitors, intravenous nitroglycerine, beta-blockers and acetylsalicylic acid were less frequently used in deceased patients (34% vs 89%, p<0.00001; 52% vs 78%, p<0.00001; 14% vs 37%, p<0.001; and 64% vs 86%, p<0.0003, respectively). CONCLUSIONS: In spite of intensive pharmacotherapy, cardiogenic pulmonary oedema is still associated with a high in-hospital mortality. Therapy should be tailored according to aetiology. Differences in pharmacological treatment between survivors and deceased patients depict better prognosis in those who have on admission normal or elevated blood pressure which enables an early administration of vasodilators and beta-blockers.