Design and validation of an intelligent patient monitoring and alarm system based on a fuzzy logic process model.

The process of patient care performed by an anaesthesiologist during high invasive surgery requires fundamental knowledge of the physiologic processes and a long standing experience in patient management to cope with the inter-individual variability of the patients. Biomedical engineering research improves the patient monitoring task by providing technical devices to measure a large number of a patient's vital parameters. These measurements improve the safety of the patient during the surgical procedure, because pathological states can be recognised earlier, but may also lead to an increased cognitive load of the physician. In order to reduce cognitive strain and to support intra-operative monitoring for the anaesthesiologist an intelligent patient monitoring and alarm system has been proposed and implemented which evaluates a patient's haemodynamic state on the basis of a current vital parameter constellation with a knowledge-based approach. In this paper general design aspects and evaluation of the intelligent patient monitoring and alarm system in the operating theatre are described. The validation of the inference engine of the intelligent patient monitoring and alarm system was performed in two steps. Firstly, the knowledge base was validated with real patient data which was acquired online in the operating theatre. Secondly, a research prototype of the whole system was implemented in the operating theatre. In the first step, the anaesthetists were asked to enter a state variable evaluation before a drug application or any other intervention on the patient into a recording system. These state variable evaluations were compared to those generated by the intelligent alarm system on the same vital parameter constellations. Altogether 641 state variable evaluations were entered by six different physicians. In total, the sensitivity of alarm recognition is 99.3%, the specificity is 66% and the predictability is 45%. The second step was performed using a research prototype of the system in anaesthesiological routine. The evaluation of 684 events yielded a sensitivity, specificity and predictability of the alarm recognition of more than 99%.

Fuzzy logic and control: principal approach and potential applications in medicine.

During the last few years intelligent machines appeared in nearly all technical areas, such as consumer electronics, robotics, and industrial control systems. There are for example washing machines that work very effectively, need comparably less power than in the past, and have short execution times because they adjust their washing cycles to each set of clothes and change their washing strategies as the clothes become clean. These intelligent systems are based on fuzzy control strategies, i.e., common sense rules are used to describe a system's behavior instead of complex mathematical models. We have applied this new technology to control problems as well as to reasoning problems in biomedical engineering where appropriate mathematical models could not be built due to the complexity of the problem. After a short introduction to the concepts of fuzzy logic two approaches in the field are described: a fuzzy control strategy for the pump rate adjustment of a novel total artificial heart and an intelligent alarm system based on fuzzy inference which supports the anesthetist in monitoring and evaluating the hemodynamic state of a patient undergoing cardiac surgery. These examples indicate the inherent reliability and stability of this technique in the field of complex dynamic systems. Such properties are highly significant especially in medical applications.

A knowledge-based approach to intelligent alarms in anesthesia.

The combination and aggregation of separate information sources to generate more ;intelligent' alarms using a knowledge-based approach is described. The approach gas developed as part of the knowledge-based anesthesia decision support system, AES-2, which monitors the patient's physiological state during anesthesia and eventually suggests therapeutic actions. Integration of the alarm system into a conventional information system is discussed. The state variable model used and the modeling of uncertainty are examined. The tools that support knowledge acquisition, design of knowledge-base prototypes. and test of the knowledge base of the AES-2 are described. A simulation example is given.

Size of jejunal Peyer's patches and migration of lymphocyte subsets in pigs after resection or transposition of the continuous ileal Peyer's patch.

In pigs there are two types of Peyer's patches in the small intestine: discrete patches in the jejunum (jejPP) and a continuous patch in the terminal ileum (ilPP). The ilPP was resectioned or transposed into the upper jejunum. After the operation the size of the remaining jejPP showed no compensatory growth in either group within 10 months. However, the number of CD8+ lymphocytes in the blood, spleen, mesenteric lymph nodes, tonsils, and Peyer's patches and the number of CD4+ cells in the spleen and tonsils was reduced in comparison to those of age-matched control pigs. Autologous blood lymphocytes were labelled with fluorescein isothiocyanate and retransfused. In control animals the mid-portion of the ilPP showed a lower entry of lymphocytes and the migration pattern of lymphocyte subsets was different in the animals with resectioned or transposed ilPP as compared to controls. Thus, the removal of the ilPP (about 60% of all small intestinal PP) did not result in the remaining patches adapting their size, but it did influence other lymphoid organs.