딥러닝을 이용한 욕창예방간호 임상적 의사결정지지 시스템의 개발 및 효과

Abstract

Pressure ulcers are localized damage to the skin or underlying tissue over the bony protrusion as a result of shear and pressure. It is one of the major health problems that needs to be steadily monitored and managed with sensitive nursing and care. In order to prevent pressure ulcers, it is essential to not only perform direct nursing practices, but also to develop interventions that are highly practical, accessible and straightforward for nurses to facilitate themselves to follow the prevention guidelines. The purpose of this study is to develop and to evaluate the impact of a Clinical Decision Support System (CDSS) using deep learning on the pressure ulcer prevention. The CDSS was built upon a two-stream model in a clinical decision support system, and was developed through verification and consultation on its content validity by a group of experts. The development of the CDSS was carried out through the steps of analysis, design, development, implementation and evaluation, according to the ADDIE model. We used non-equivalent control group non-synchronized design to evaluate the effectiveness of the developed program. The study subjects were nurses who worked in the intensive care unit, with 23 people in the experimental group and 26 people in the control group. The experimental group was asked to use the web-based CDSS for 4 weeks, while the control group was provided with a pocket book material. The research tools were to measure nurses’ visual differentiation of pressure ulcer, clinical decision-making, nursing performance, knowledge, and nursing attitude. We used SPSS IBM Statistics Program 25 software to perform χ2-test, Fisher's exact test, Shapiro-Wilk test, independent t-test, and Mann Whitney U test on the data collected from experiments. After the CDSS intervention, the experimental group showed significant statistic improvement over the control group in scores of visual differentiation ability on skin pressure ulcers (p<.001) and oral mucosa pressure ulcers (p=.044), pressure ulcer prevention nursing performance (p=.002), and nursing attitude toward skin pressure ulcer prevention (p<.001), which consequently supported the hypothesis. On the other hand, the hypothesis was rejected due to lack of significant difference in the scores of clinical decision-making ability, knowledge, and the attitude toward oral mucosa pressure ulcer prevention care. In conclusion, the web-based CDSS was shown to be effective in improving the visual differentiation ability, attitude, and performance of pressure ulcer prevention. Therefore, it is expected that the proposed CDSS can contribute to the improvement of nursing performance on the pressure ulcer prevention.