The study aims to follow up on the analysis of Pressure injuries (PIs) prevalence conducted between 2007 and 2014 and after the new methodological requirements for PIs surveillance establishment at the national level. A retrospective, nationwide cross-sectional analysis of data regarding the STROBE checklist was collected by the National Health Information System (NHIS). The International Classification of Diseases (ICD-10) diagnoses L89.0-L89.9 for PIs were used in the period 2010-2019. A total of 264 442 records of patients with diagnoses of L89.0-L89.9 were identified from 2010 to 2019 (26 444 patients per year on average). The numbers are increasing every year, and there is a 40% increase between 2010 and 2019. When comparing recorded PIs, the percentage of PIs occurrence in category I decreased, and the number of PIs in category IV increased in the second analysed period. Still, in absolute numbers, there is an increase across all categories. The age of patients with recorded PIs also rose slightly in the second analysed period. We have proven the PIs prevalence increase in an ageing population.

• Klíčová slova
• epidemiology, national registry, pressure injuries, pressure ulcers, prevalence,
• MeSH
• dekubity * MeSH
• incidence MeSH
• lidé MeSH
• následné studie MeSH
• prevalence * MeSH
• průřezové studie MeSH
• registrace MeSH
• retrospektivní studie MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• Geografické názvy
• Česká republika epidemiologie   MeSH

Increasingly available open medical and health datasets encourage data-driven research with a promise of improving patient care through knowledge discovery and algorithm development. Among efficient approaches to such high-dimensional problems are a number of machine learning methods, which are applied in this paper to pressure ulcer prediction in modular critical care data. An inherent property of many health-related datasets is a high number of irregularly sampled time-variant and scarcely populated features, often exceeding the number of observations. Although machine learning methods are known to work well under such circumstances, many choices regarding model and data processing exist. In particular, this paper address both theoretical and practical aspects related to the application of six classification models to pressure ulcers, while utilizing one of the largest available Medical Information Mart for Intensive Care (MIMIC-IV) databases. Random forest, with an accuracy of 96%, is the best-performing approach among the considered machine learning algorithms.

• Klíčová slova
• MIMIC database, MIMIC-IV, artificial neural network, machine learning, open data, pressure injury, pressure ulcer, random forest,
• Publikační typ
• časopisecké články MeSH

BACKGROUND: The critically ill patients suffering from coronavirus disease (COVID-19) and admitted to the intensive care units (ICUs) are susceptible to a wide array of complications that can be life-threatening or impose them to long-term complications. The COVID-19 oral mucocutaneous complications require multidisciplinary management and research for their pathophysiological course and epidemiological significance; therefore, the objective of this study was to evaluate the prevalence and characteristics of the critically ill COVID-19 patients with oral complications. METHODS: We described the clinical and microbiological characteristics of the critically ill COVID-19 patients in our ICU department (Banska Bystrica, Slovakia). In addition, we reviewed the current body of evidence in Ovid MEDLINE®, Embase, Cochrane Library, and Google Scholar for the oral mucocutaneous complications of ICU patients with COVID-19. RESULTS: Three out of nine critically ill patients (33.3%) in our ICU department presented with oral complications including haemorrhagic ulcers and necrotic ulcers affecting the lips and tongue. The microbiological assessment revealed the presence of opportunistic pathogens, confirming the possibility of co-infection. On reviewing the current literature, two hundred ten critically ill patients were reported to have oral complications due to their stay in the ICU setting. Perioral pressure ulcers were the most common complication, followed by oral candidiasis, herpetic and haemorrhagic ulcers, and acute onset macroglossia. The prolonged prone positioning and mechanical ventilation devices were the primary risk factors for those oral complications, in addition to the immunosuppressive drugs. CONCLUSIONS: The multidisciplinary approach is strongly advocated for monitoring and management of COVID-19 patients, thus implying that dermatology and oral healthcare specialists and nurses should be integrated within the ICU teams.

• Klíčová slova
• COVID-19, candidiasis, critical care, macroglossia, oral manifestations, pressure ulcer, prone position,
• Publikační typ
• časopisecké články MeSH
• přehledy MeSH