Few-Shot and Prompt Training for Text Classification in German Doctor's Letters.

To classify sentences in cardiovascular German doctor's letters into eleven section categories, we used pattern-exploiting training, a prompt-based method for text classification in few-shot learning scenarios (20, 50 and 100 instances per class) using language models with various pre-training approaches evaluated on CARDIO:DE, a freely available German clinical routine corpus. Prompting improves results by 5-28% accuracy compared to traditional methods, reducing manual annotation efforts and computational costs in a clinical setting.

A distributable German clinical corpus containing cardiovascular clinical routine doctor's letters.

We present CARDIO:DE, the first freely available and distributable large German clinical corpus from the cardiovascular domain. CARDIO:DE encompasses 500 clinical routine German doctor's letters from Heidelberg University Hospital, which were manually annotated. Our prospective study design complies well with current data protection regulations and allows us to keep the original structure of clinical documents consistent. In order to ease access to our corpus, we manually de-identified all letters. To enable various information extraction tasks the temporal information in the documents was preserved. We added two high-quality manual annotation layers to CARDIO:DE, (1) medication information and (2) CDA-compliant section classes. To the best of our knowledge, CARDIO:DE is the first freely available and distributable German clinical corpus in the cardiovascular domain. In summary, our corpus offers unique opportunities for collaborative and reproducible research on natural language processing models for German clinical texts.

Automatic extraction of 12 cardiovascular concepts from German discharge letters using pre-trained language models.

OBJECTIVE: A vast amount of medical data is still stored in unstructured text documents. We present an automated method of information extraction from German unstructured clinical routine data from the cardiology domain enabling their usage in state-of-the-art data-driven deep learning projects. METHODS: We evaluated pre-trained language models to extract a set of 12 cardiovascular concepts in German discharge letters. We compared three bidirectional encoder representations from transformers pre-trained on different corpora and fine-tuned them on the task of cardiovascular concept extraction using 204 discharge letters manually annotated by cardiologists at the University Hospital Heidelberg. We compared our results with traditional machine learning methods based on a long short-term memory network and a conditional random field. RESULTS: Our best performing model, based on publicly available German pre-trained bidirectional encoder representations from the transformer model, achieved a token-wise micro-average F1-score of 86% and outperformed the baseline by at least 6%. Moreover, this approach achieved the best trade-off between precision (positive predictive value) and recall (sensitivity). CONCLUSION: Our results show the applicability of state-of-the-art deep learning methods using pre-trained language models for the task of cardiovascular concept extraction using limited training data. This minimizes annotation efforts, which are currently the bottleneck of any application of data-driven deep learning projects in the clinical domain for German and many other European languages.

Comprehensive plasma and tissue profiling reveals systemic metabolic alterations in cardiac hypertrophy and failure.

AIMS: Heart failure is characterized by structural and metabolic cardiac remodelling. The aim of the present study is to expand our understanding of the complex metabolic alterations in the transition from pathological hypertrophy to heart failure and exploit the results from a translational perspective. METHODS AND RESULTS: Mice were subjected to transverse aortic constriction (TAC) or sham surgery and sacrificed 2 weeks, 4 weeks, or 6 weeks after the procedure. Samples from plasma, liver, skeletal muscle, and heart were collected and analysed using metabolomics. Cardiac samples were also analysed by transcriptional profiling. Progressive alterations of key cardiac metabolic pathways and gene expression patterns indicated impaired mitochondrial function and a metabolic switch during transition to heart failure. Similar to the heart, liver, and skeletal muscle revealed significant metabolic alterations such as depletion of essential fatty acids and glycerolipids in late stages of heart failure. Circulating metabolites, particularly fatty acids, reflected cardiac metabolic defects, and deteriorating heart function. For example, inverse correlation was found between plasma and the heart levels of triacylglycerol (C18:1, C18:2, C18:3), and sphingomyelin (d18:1, C23:0) already at an early stage of heart failure. Interestingly, combining metabolic and transcriptional data from cardiac tissue revealed that decreased carnitine shuttling and transportation preceded mitochondrial dysfunction. We, thus, studied the therapeutic potential of OCTN2 (Organic Cation/Carnitine Transporter 2), an important factor for carnitine transportation. Cardiac overexpression of OCTN2 using an adeno-associated viral vector significantly improved ejection fraction and reduced interstitial fibrosis in mice subjected to TAC. CONCLUSION: Comprehensive plasma and tissue profiling reveals systemic metabolic alterations in heart failure, which can be used for identification of novel biomarkers and potential therapeutic targets.