No abstract

This study applied artificial intelligence to help nurses address problems and receive instructions through information technology. Nurses make diagnoses according to professional knowledge, clinical experience, and even instinct. Without comprehensive knowledge and thinking, diagnostic accuracy can be compromised and decisions may be delayed. We used a back-propagation neural network and other tools for data mining and statistical analysis. We further compared the prediction accuracy of the previous methods with an adaptive-network-based fuzzy inference system and the back-propagation neural network, identifying differences in the questions and in nurse satisfaction levels before and after using the nursing information system. This study investigated the use of artificial intelligence to generate nursing diagnoses. The percentage of agreement between diagnoses suggested by the information system and those made by nurses was as much as 87 percent. When patients are hospitalized, we can calculate the probability of various nursing diagnoses based on certain characteristics.

In recent years, the prevention, control, diagnosis and treatment of infectious diseases has become a global focus for public health. Traditional methods for pathogen testing have some major disadvantages including the need for highly skilled staff and expensive instrumentation, while procedural aspects are complex and sensitive to the environment. These shortcomings have greatly limited the application of traditional testing in on site pathogen detection. In this paper, we present a new point-of-care-testing (POCT) system based on magnetic nanoparticles that enable sample in-answer out (SIAO) automated real-time testing for pathogens. Various performance tests were conducted on the instrument. Nucleic acid extraction efficiencies of SIAO versus manual systems were 95.49% and 84.33%, respectively. Real-time PCR by two methods (TaqMan-based probe and SYBR green dye) in the SIAO system was achievable, with comparable results to the manual method. Nucleic acid testing with the SIAO system was repeatable and better than with manual testing. The SIAO system had good anti-pollution performance with easy avoidance of inter-assay cross contamination. Finally, use of the SIAO system for adenovirus detection produced similar results to LightCycler2.0 system assay findings. The amplification plots and Ct values suggested similar amplification plots shapes for adenovirus testing with the SIAO system and with real-time fluorescence PCR testing and commercial instrument post-manual nucleic acid extraction. Collectively, these findings indicate that testing with the SIAO system is virtually equivalent to that of manual extraction with commercial system testing.

No abstract

In 2009, the Department of Health, part of Taiwan's Executive Yuan, announced the advent of electronic medical records to reduce medical expenses and facilitate the international exchange of medical record information. An information technology platform for nursing records in medical institutions was then quickly established, which improved nursing information systems and electronic databases. The purpose of the present study was to explore the usability of the data mining techniques to enhance completeness and ensure consistency of nursing records in the database system.First, the study used a Chinese word-segmenting system on common and special terms often used by the nursing staff. We also used text-mining techniques to collect keywords and create a keyword lexicon. We then used an association rule and artificial neural network to measure the correlation and forecasting capability for keywords. Finally, nursing staff members were provided with an on-screen pop-up menu to use when establishing nursing records. Our study found that by using mining techniques we were able to create a powerful keyword lexicon and establish a forecasting model for nursing diagnoses, ensuring the consistency of nursing terminology and improving the nursing staff's work efficiency and productivity.