1,720,999 research outputs found
Portable system for fast lung function test
No full textThe analysis of gas-concentration changes at mouth during normal breathing is nowadays a routine exam to infer the lung functionality and several commercial instruments are available to carry out this kind of measurements. Unfortunately, most of these measuring systems are very specific, designed to be used in the hospital and costly. This paper describes a complete and versatile system which is designed for in the field use and can be tailored to several different measurement situations. The proposed system employs commercial sensors coupled to a versatile conditioning and acquisition board, which is designed to be connected to a conventional Personal Computer. A skeleton of a software which carries out the routine tasks (acquisition, storing, calibrations, and visualization) has been designed and installed on the PC. The skeleton can be easily adapted to the different applications, thus enabling the fast development of new clinical methodics. As an example, in this paper, an application is described that performs an Oxygen/Carbon-Dioxide analysis on a multi-breath basis and estimates the result uncertainty. The skeleton contains routines to save both results and raw data according to the Digital Imaging and Communication in Medicine (DICOM) standard format, so that the analyzes can be easily shared among the different physicians involved in the patient's care
Evaluation of surgical risks by means of neural networks in the presence of uncertainties
No full textSurgical risks in elderly patients are often rather high and therefore a need exists for preoperative tests that are able to predict the postoperative risk of mortality. In most cases no test has been found to be completely able to predict postoperative severe complications although reasonable results can be obtained by employing a multi-test approach. A neural network can conveniently be employed to perform the required data-fusion thus producing an overall "risk index"; however the surgical outcome being of a binary type, the network output tends to be a step-like function that does not give much information on the risk level. In this paper a modified training approach that takes the parameter uncertainties into account and which trains the network avoiding the step-like behaviour is proposed. The results that can be obtained with this approach are eventually explained by applying it to the estimation of a surgical risk index for lung resection procedures in patients affected by lung cance
Uncertainty Analysis of Feature Extraction from Expired Gas Traces
Full text linkNoninvasive medical analyses are a convenient method to study several pathologies even though their indirect nature often requires a complex processing to determine the relevant health "indicators". The usefulness of such indicators depends on the employed model, but also on the uncertainty that is connected to the complex processing involved in the indicator determination. This paper deals with the problems related to the estimation of the uncertainty when the indicators are computed by means of a nontrivial processing on recorded traces of clinical parameters. The paper is focused on the analysis of expired gas traces, but the procedure can also be applied to many other cases where the processing involves manual or automatic selection of suitable "key points" on repetitive traces
Mixed Neural-Conventional Processing to Differentiate Airway Diseases by Means of Functional Noninvasive Tests
Full text linkThis paper describes a processing technique that can be used to combine information from different medical analyze to discriminate between different pathologies that have similar symptoms. The paper is focused on the differentiation between asthma, bronchitis, and emphysema, using only functional noninvasives tests, but the proposed technique can be easily applied to other similar situations where different tests have to be used to identify a pathology. The technique is based on mixed neural-and-conventional processing that not only suggests the pathology, but also estimates the reliability of this suggestion
Mixed neural-conventional processing to differentiate airway diseases by means of functional non-invasive tests
No full textThis paper describes a processing technique that can be used to combine the pieces of information coming from different medical analyses. Such a technique is based on a mixed neural-and-conventional processing that allows both an easy neural network training and a robust estimation to be obtained. The paper is focused on the differentiation of asthma, bronchitis and emphysema by using functional non-invasive tests only, but the proposed technique can be easily applied to several different situations
Angolo goniaco e divergenze intermascellari in pazienti disgnatici con aumento delle resistenze nasali
No full text- …
