RESUMO
The monitoring of ionic dialysance in hemodialysis allows early detection of arterio-venous fistula stenosis. One limitation to the practical use of ionic dialysance is that the analysis is very time consuming on a majority of normal cases.The purpose of the study is to evaluate the utility of an expert system reproducing a human analysis and allowing continuous monitoring of the ionic dialysance by helping the physician to focus his or her expertise on the abnormal cases.The method is based on a Bayesian model that analyzes the blood flow rate, the ionic dialysance, and the venous and arterial pressures measured on the extra corporeal circuit.The clinical evaluation was performed on 90 dialysis patients at the hospital dialysis center of Saint Brieux in France with a history of at least four consecutive months of validated recording. The retrospective automated analysis was evaluated in comparison to vascular access problems identified from invasive investigation or treatment. The sensitivity of the automated analysis is 92% with a specificity of 75%.As a conclusion we suggest that this expert system could be used in a continuous vascular access monitoring procedure consisting in a weekly review of the patient population at the dialysis center. The patients with the highest risk score need a further investigation of their historical data and their medical history in order to decide whether or not to perform an invasive intervention.
Assuntos
Derivação Arteriovenosa Cirúrgica/efeitos adversos , Sistemas Inteligentes , Soluções para Hemodiálise/uso terapêutico , Rins Artificiais , Diálise Renal/instrumentação , Algoritmos , Pressão Arterial , Automação Laboratorial , Teorema de Bayes , Velocidade do Fluxo Sanguíneo , Desenho de Equipamento , Reações Falso-Negativas , Reações Falso-Positivas , França , Soluções para Hemodiálise/química , Humanos , Concentração Osmolar , Valor Preditivo dos Testes , Reprodutibilidade dos Testes , Estudos Retrospectivos , Fatores de Risco , Fatores de Tempo , Resultado do Tratamento , Pressão VenosaRESUMO
Pharmaceutic studies require to analyze thousands of ECGs in order to evaluate the side effects of a new drug. In this paper we present a new support system based on the use of probabilistic models for automatic ECG segmentation. We used a bayesian HMM clustering algorithm to partition the training base, and we improved the method by using a multi-channel segmentation. We present a statistical analysis of the results where we compare different automatic methods to the segmentation of the cardiologist as a gold standard.
Assuntos
Algoritmos , Arritmias Cardíacas/diagnóstico , Arritmias Cardíacas/fisiopatologia , Diagnóstico por Computador/métodos , Eletrocardiografia/métodos , Frequência Cardíaca , Reconhecimento Automatizado de Padrão/métodos , Inteligência Artificial , Simulação por Computador , Humanos , Cadeias de Markov , Modelos Cardiovasculares , Modelos Estatísticos , SoftwareRESUMO
Commercial gait analysis systems rely on wearable sensors. The goal of this study is to develop a low cost marker less human motion capture tool. Our method is based on the estimation of 3d movements using video streams and the projection of a 3d human body model. Dynamic parameters only depend on human body movement constraints. No trained gait model is used which makes this approach generic. The 3d model is characterized by the angular positions of its articulations. The kinematic chain structure allows to factor the state vector representing the configuration of the model. We use a dynamic bayesian network and a modified particle filtering algorithm to estimate the most likely state configuration given an observation sequence. The modified algorithm takes advantage of the factorization of the state vector for efficiently weighting and resampling the particles.
