Nurses' Attitude Towards Various Hand Hygiene Products. Soap vs Antiseptics.

BACKGROUND: According to the latest recommendations of WHO, in most situations requiring hands treatment, alcohol-based skin antiseptics should be used. This study is aimed to determine the awareness and preferences of nurses in the city of Moscow regarding the choice of methods regarding hand hygiene treatment and the factors influencing this choice. STUDY DESIGN: Using the specially designed questionnaire, 184 nurses working in Moscow hospitals were interviewed to find out the attitude of nurses to various methods of hand hygiene. METHODS: The questionnaire was developed on the basis of WHO Recommendations and Russian Recommendations. The survey was conducted from May 2017 to July 2017. To confirm the statistical significance of the identified associations a chi-square test was used. To find the 95% confidence interval to the relative values the Clopper-Pearson method was used. RESULTS: Only 3 (1.63%) of respondents indicated that they use antiseptic as the most frequently used hand hygiene product, 27 (14.67%) use liquid soap more often, 153 (83.15%) indicated that they use soap and antiseptic with equal frequency. In none of the standard situations we examined the use of antiseptic was the most frequent choice. Only in three cases antiseptic was chosen more often than soap - before and after manipulations with wounds and catheters (36.96%) or before performing invasive procedures (36.41%) and after contact with biological material (29.35%). At the same time nurses with more than 15 years of experience have preferred antiseptic. CONCLUSIONS: Based on the study it can be assumed that despite the implementation of the Russian guidelines on hand hygiene developed according to WHO recommendations, nurses prefer the traditional method of washing hands with soap. This suggests that in the current conditions additional measures are needed to train nurses and to monitor their work.

[Formation of diagnostic rules by using neural networks]. / Formirovanie diagnosticheskikh pravil s ispol'zovaniem neironnykh setei.

Neural networks were trained on unrepresentative patient data sets proposed by skilled clinicians. In all cases, the trained neural networks correctly classified all presented cases. There were 2 intervals introduced for encoding estimates. The number of both signs and neurons in the trained neural networks was minimized. The trained neural networks adequately represent a set of logical formulas that are easy to perceive. These formulas are similar to syndrome complexes, they can be tabulated and presented as diagnostic tables the physicians usually use. The proposed decisions are accompanied by the estimates of their affinity, which allows their validity to be controlled. The clinical studies performed showed that the proposed decisions were in good agreement with medical conclusions in most cases (over 88%).