Changes of swallowing function after tracheostomy: a videofluoroscopy study.

BACKGROUND: Patients after tracheostomy often present swallowing dysfunctions but little is known about the mechanism underlying dysphagia and its reversibility. The aims of this study were: 1) to characterize swallowing dysfunctions in patients with dysphagia and tracheostomy; 2) to evaluate the reversibility of these changes; 3) to evaluate the possible influence of the underlying disease. METHODS: Prospective, observational, single-center study enrolling patients with tracheostomy admitted to a rehabilitation center over a period of 36 months. All patients who were found to be dysphagic underwent a swallowing study with videofluoroscopy (VF) at the beginning of hospital stay and a second VF study was repeated after approximately 4 weeks. RESULTS: A total of 557 patients with tracheostomy were admitted to the rehabilitation center during the considered period. 187 patients fulfilled the enrolling criteria and were studied with VF soon after admission. They had been tracheostomized for respiratory failure secondary to cerebrovascular accident (N.=106) or to acute-on chronic respiratory failure (N.=81). Incomplete backward epiglottis folding, pharyngeal retention, penetration and aspiration were the most frequent swallowing dysfunctions, observed with a frequency of 48%, 32%, 33% and 28%, respectively. Eighty-one patients underwent a second VF study, where these four swallowing phases again turned out to be the most compromised, with a frequency of 41%, 19%, 27% and 17%, respectively. The improvement was less evident in patients with chronic respiratory disease. CONCLUSION: The swallowing function is impaired in patients with dysphagia and tracheostomy, but most swallowing abnormalities appear to be partially reversible. Patients with chronic respiratory disease exhibit a worse swallowing function.

From data to the decision: A software architecture to integrate predictive modelling in clinical settings.

The application of statistics and mathematics over large amounts of data is providing healthcare systems with new tools for screening and managing multiple diseases. Nonetheless, these tools have many technical and clinical limitations as they are based on datasets with concrete characteristics. This proposition paper describes a novel architecture focused on providing a validation framework for discrimination and prediction models in the screening of Type 2 diabetes. For that, the architecture has been designed to gather different data sources under a common data structure and, furthermore, to be controlled by a centralized component (Orchestrator) in charge of directing the interaction flows among data sources, models and graphical user interfaces. This innovative approach aims to overcome the data-dependency of the models by providing a validation framework for the models as they are used within clinical settings.