International journal of bio-medical computing最新文献

In this article a technique is described to develop knowledge-based alarm systems for ventilator therapy, using mathematical modeling and machine learning. With a mathematical model airway pressure, expiratory gas flow and CO₂ concentration at the endotracheal tube are simulated for patients, undergoing volume-controlled ventilation with constant ventilator settings, during normal functioning of the breathing circuit and during breathing circuit mishaps (leaks and obstructions). Simulations were performed for 94 physiologically different ‘patients’, by varying airway resistance and lung thorax compliance values in the model. Each simulated breath was described by a set of derived signal features and a label that constituted during which event (normal function or mishap) the breath was recorded. With an inductive machine learning algorithm rules, linking signal feature values to breathing circuit events, were created from data of 54 of the simulated patients. The resulting set of rules was able to classify 99% of events in the data of the remaining 40 patients correctly. Of signals, measured at a ventilated lung simulator, 100% of events were classified correctly.

We report on a prospective, prolective observational study, supplying information on how physicians and other health care professionals retrieve medical knowledge on-line within the Heidelberg University Hospital information system. Within this hospital information system, on-line access to medical knowledge has been realised by installing a medical knowledge server in the range of about 24 GB and by providing access to it by health care professional workstations in wards, physicians' rooms, etc. During the study, we observed about 96 accesses per working day. The main group of health care professionals retrieving medical knowledge were physicians and medical students. Primary reasons for its utilisation were identified as support for the users' scientific work (50%), own clinical cases (19%), general medical problems (14%) and current clinical problems (13%). Health care professionals had accesses to medical knowledge bases such as MEDLINE (79%). drug bases (‘Rote Liste’. 6%). and to electronic text books and knowledge base systems as well. Sixty-five percent of accesses to medical knowledge were judged to be successful. In our opinion, medical knowledge retrieval can serve as a first step towards knowledge processing in medicine. We point out the consequences for the management of hospital information systems in order to provide the prerequisites for such a type of knowledge retrieval.

We were interested in studying a demographic indicator, the Malthusian parameter which had not been investigated earlier in the case of the Finnish population. We computed the Malthusian parameter with a known renewal equation, which is, as usual, approximated on discrete data by using normal distribution, on the Finnish population in the 20th century. The data was collected from the abundant official statistical sources which are known to be accurate and reliable in Finland. In addition to this parameter we computed the gross and net reproduction rates, the total fertility index, and the mean and variance age of females at child-bearing. The Malthusian parameter seems to be a rather good means of characterizing the development of the population. If the parameter is positive for long enough, the population tends to grow. If it is negative, as has been the case in Finland since 1969, the population starts to diminish sooner or later. On the other hand, it cannot take all factors into account. For instance, because of still increasing lifetime and also because of a relatively large quantity of females at the reproductive age the population is not yet decreasing in Finland. In any case, the Malthusian parameter forecasts the future trend of the decreasing population.

In biomedical research data are often collected serially over time. Hence, the main outcome is represented by response curves. A suitable approach to analyse such data is given by summary measures describing the main features of the response curves. An important issue is the precision of the estimated summary measures, which can be represented by confidence intervals. However, since summary measures frequently cannot be obtained via linear relationships, the calculation of confidence intervals involves some special considerations. In this paper attention is focused on unimodal response curves. Important summary measures for this type of response curves are the curve maximum (C_max), the time to curve maximum (t_max), and the area under the curve (AUC). These summary measures can be calculated from the parameters of nonlinear regression models fitted to the data. Since the summary measures are nonlinear functions of the regression coefficients the multivariate delta method is used to derive formulas for the standard errors and confidence intervals of the summary measures. The method is illustrated by application to pharmacodynamic data.

A new expert system for the analysis of post-cardiosurgical patients in Intensive Care Units is described, and a preliminary validation performed. The inference engine employs a hybrid reasoning method which integrates quantitative and qualitative simulation techniques in an original manner. The long-term knowledge consists of a causal network which reproduces the main relationships between physiological quantities involved in the course after cardiac surgery. Emphasis has been given to respiratory and metabolic, as well as cardiovascular quantities both in the systemic and pulmonary circulations. Preliminary system validation has been performed on a set of 40 cardiosurgical patients, previously classified either at normal-risk (17 patients) or at high-risk (23 patients) by means of statistical classification techniques. In most cases, predictions of the expert system substantially agree with those provided by the more traditional statistical method. The system, however, is also able to furnish detailed explanations on the possible physiological causes responsible for the patient status. In particular, simulation results indicate that a reduction in the cardiac index (19 cases) and an increase in the oxygen utilization coefficient (19 cases) are the most critical alterations in the high-risk patients. The system imputes the reduced cardiac index to a rise in total systemic resistance (15 high-risk patients), a decrease in cardiac strength (2 high-risk patients) or an insufficient filling volume of the systemic circulation (4 high-risk patients). Furthermore, in 6 high-risk patients the depressed cardiac outflow occurs with a reduction in the arterial oxygen content, mainly imputable to an insufficiency of blood hemoglobin content. Finally, two examples of the complete expert system explanatory capabilities are shown with reference to a pair of high-risk patients and discussed.

In this paper we consider the security of medical databases. We give an overview of the security problems and the possible available mechanisms for the prevention of security compromises. Many of the security problems are common to all databases. However, the problem of data inference from statistical queries is particularly pertinent to medical databases and consequently we treat this problem in more detail. The paper concludes with a proposal for a Security Subsystem in a database management system.