SummaryBackground: The lifetime prevalence of epistaxis is approximately 60%, and 6-10% of the affected persons need medical care. In rare cases, severe bleeding calls for the rapid initiation of effective treatment.

Acute self-poisoning is an increasing medical issue. Psychotropic drugs remain the most common means of suicide attempt. Although alcohol intoxication is very frequent, intake of illicit drugs as the cause of emergency admission is increasing.

No abstract

Purpose Detection of cochlear nerve deficiency (CND) is usually straightforward using magnetic resonance imaging (MRI). In patients in whom MRI cannot be performed or imaging provides equivocal findings, computed tomography (CT) of the temporal bone might offer indirect evidence of CND. Our study aimed to derive a cut-off value for the diameter of the cochlear nerve canal (CNC) and internal auditory canal (IAC) in temporal bone CT to predict CND. Materials and Methods This retrospective study included 70 children with sensorineural hearing loss (32 with CND and 38 control patients). The height, width, and cross-sectional area of the IAC and diameter of the CNCs were determined using temporal bone CT. Receiver operating characteristic (ROC) and Student’s t-tests were performed for each parameter. Results The mean diameter of the CNCs was significantly smaller in children with CND than in the control group (1.2 mm versus 2.4 mm, p < .001). The optimal threshold for CNC for separation of the two groups was 1.9 mm, resulting in a sensitivity of 98.7 % and specificity of 89.2 %. The IAC dimensions could not distinguish between children with CND and controls. Conclusion A CNC diameter of less than 1.9 mm is a reliable predictor of CND in children with sensorineural hearing loss. Key Points:  Citation Format

The documentation of a surgical procedure remains a time-consuming task that surgeons must incorporate into their daily routine. However, since a surgical report should be produced immediately after the operation with all impressions of the procedure in mind, a means of automation assistance should be provided. We, therefore, propose a method that generates surgical reports based on keywords stated during the procedure. Our report generation is based on a sequence-tosequence model that is trained on sentence pairs of two consecutive sentences in a surgical report. The known sentence is augmented with a keyword based on the following surgical action to be documented and is then passed into a language model to generate the next sentence. In this way, the complexity of predicting a vast number of possible surgical report phrasings is reduced to a next sentence prediction task. For the language model, an encoder-decoder structure was used with bidirectional 2-layer Long-Short Term Memory (LSTM) units for both components and an attention layer between input and output sentences. The training data consisted of 50 ear-,nose- and throat surgery (ENT) reports with 1500 sentences. The model training was performed in a k-fold cross-validation study with k = 10 and cross-entropy loss as the objective function. The generated reports were investigated using NIST, ROUGE, and METEOR metrics. Additionally, three medical experts identified the report content regarding plausibility and text errors. The trained models reached an accuracy of 0.82 for the next sentence predictions. The generated reports show consistent sentence structures and keyword correspondence for about 70 % of provided keyword sequences. The NIST, ROUGE, and METEOR metrics reached 0.65, 0.71, and 0.64, respectively. The model underperformed for not yet known keyword sequences and shows signs of overfitting when keyword sequences deviate from the baseline of the training set. Our approach for the keyword-augmented generation of surgical reports shows the potential of reducing the text generation complexity by providing a sequence of anchor words. However, the automated generation of surgical reports remains a difficult task due to individual report phrasings and the high variance in keyword sequences.