No description available.

Bakgrund Det finns flera svårigheter vid en överförflyttning från intensivvårdsavdelning till en vårdavdelning. En av dessa är hur all den vård som utförts på intensivvårdsavdelningen ska sammanfattas till en relevant, överblickbar omvårdnadsepikris. Syfte och frågeställning Syftet med denna studie är att undersöka om sjuksköterskor som vårdar traumapatienter anser att omvårdnadsepikrisen innehåller den information som krävs för att omvårdnadens mål ska kunna uppnås. Utöver detta syftar studien till att undersöka vilken information  sjuksköterskorna anser att omvårdnadsepikrisen ska innehålla. Vidare undersöks huruvida åsikterna skiljer sig åt mellan de båda grupperna och vad de tror om införandet av en standardiserad omvårdnadsepikrismall för traumapatienter. Metod Uppsatsen har designen av en kvantitativ studie med ett stratifierat strategiskt urval. Sammanlagt 48 sjuksköterskor har deltagit i studien. Tjugotvå stycken från ett regionsjukhus och 26 stycken från ett länssjukhus. Enkäten bestod av nio frågor där sjuksköterskorna fick bland annat skatta hur pass hur ofta de skrev viss information och vilka av VIPS- sökord de ansåg mest relevanta för omvårdnadsepikrisen. Resultat Det finns skillnader i hur omvårdnadsepikrisen uppfattas av de olika urvalsgrupperna. Regionssjukhusgruppen ansåg att de fick med all relevant information när de sammanställde omvårdnadsepikrisen medan länssjukhusgruppen ansåg att informationen var bristfällig. Vidare visade studien att de båda urvalsgrupperna skattade likvärdigt på flertalet sökord. Slutsats Båda urvalsgrupperna var i stort överrens om vilka VIPS- sökord omvårdnadsepikrisen bör innehålla. Information som ofta saknades var rekommenderade åtgärder. / Background There are numerous difficulties associated with transferring a patient from an intensive care unit to a regular ward. One of these difficulties regards the patient discharge summaries (PDS). It is difficult to summarize a relevant PDS for patients that have been treated at an intensive care unit. Objective This study’s objective is to describe what information registered nurses (RN) that care for, or receives trauma patients’ sees as relevant to include in the PDS for trauma patients. Method The study was made with a quantitative method, using a stratified strategic sample. Forty-eight RNs participated, divided into two study groups (group 1 & 2). 22 RNs were sampled from a regional hospital and 26 RNs were sampled from a county hospital. The RNs assessed how frequent they documented specific information. They also assessed how important they felt specific keywords from the VIPS- documentation tool were to compile a relevant PDS. The two groups’ assessments were then compared. Results Differences were found in how the two groups perceived the amount of information in the PDS. Group 1 felt that they wrote enough information in the patient discharge summary. Group 2 felt that the information in the PDS was insufficient. The study also showed that the two groups assesses similarly on most of the VIPS- keywords Conclusion Both groups mostly agreed on what the PDS should contain. Both groups felt that information about recommended measures was missing.

The discharge summary is an important document, summarizing a patient’s medical information during their hospital stay. It is crucial for communication between clinicians and primary care physicians. Creating a discharge sum- mary is a necessary task. However, it is time-consuming for physicians. Using technology to automatically generate discharge summaries can be helpful for physicians and assist them in concentrating more on the patients than writing clinical summarization notes and discharge summaries. This master’s thesis aims to contribute to the research of building a transformer-based model for an automated discharge summary with a pre-trained DistilBART language model. This study plans to answer this main research question: How e↵ective is the pre-trained DistilBART language model in predicting an automated discharge summary for multiple clinical texts? The research strategy used in this study is experimental. the dataset is MIMIC- III. To evaluate the e↵ectiveness of the model, ROUGE scores are selected. The result of this model is compared with the result of the baseline BART model, which is implemented on the same dataset in the other recent research. This study regards multiple document summarization as the process of combining multiple inputs into a single input, which is then summarized. The findings indicate an improvement in ROUGE-2 and ROUGE-Lsum in the DistilBART model in comparison with the baseline BART model. However, one important limitation was computational resource constraint. The study also provides eth- ical considerations and some recommendations for future works.