Applicability of a clinical decision support system for screening the risk of laryngotracheal aspiration in hospitalized adults: a methodological study

Background: Screening the risk of laryngotracheal aspiration in hospitalized adults is a complex, multivariable, multicausal, and interdisciplinary task. This study aimed to develop and evaluate the applicability of a clinical decision support system, based on the Bayesian Network, intended to assist the interdisciplinary hospital team. Methods A Bayesian network was built from a systematic literature review, which allowed identifying and categorizing of the main variables needed to identify the risk of laryngotracheal aspiration. These variables were grouped into the current diagnosis of the patient, history associated with swallowing disorders, aspects associated with swallowing, and simple epidemiological characteristics. An application was developed and then evaluated by 9 specialists from an interdisciplinary hospital team. The aspects evaluated were the internal and external quality of the application. Results The system was developed for Android mobile devices. It was evaluated by specialists (n = 9) from the interdisciplinary hospital team (physicians, nurses, nutritionists, and speech pathologists) regarding the quality of the software product. They considered that the system was functional (86.1%), reliable (83.3%), usable (84.4%), efficient (92.6), capable of being modified (maintainability) (90.4), and portable (88.9%). Conclusions From the development of the interdisciplinary screening system, this was considered of interest and with the feasibility of its use by the specialists. Study registration: This study required validation with specialists in the fields of medicine, nursing, nutrition, and speech pathology. Thus, it was necessary to be evaluated and approved by the Ethics Committee in Research with Human Beings of the Federal University of Health Sciences of Porto Alegre – UFCSPA (# 44920121.0.0000.5345).