Furthermore, we find that support sets drastically improve the performance for pregnancy- and gynecology-related diagnoses up to 32. 9% points compared to the baseline.
However, all models struggled significantly in tasks requiring the identification of missing information, highlighting a critical area for improvement in clinical data interpretation.
As large language models (LLMs) like OpenAI's GPT series continue to make strides, we witness the emergence of artificial intelligence applications in an ever-expanding range of fields.
no code implementations • 14 Mar 2023 • Keno K. Bressem, Jens-Michalis Papaioannou, Paul Grundmann, Florian Borchert, Lisa C. Adams, Leonhard Liu, Felix Busch, Lina Xu, Jan P. Loyen, Stefan M. Niehues, Moritz Augustin, Lennart Grosser, Marcus R. Makowski, Hugo JWL. Aerts, Alexander Löser
This paper presents medBERTde, a pre-trained German BERT model specifically designed for the German medical domain.
The use of deep neural models for diagnosis prediction from clinical text has shown promising results.
Clinical phenotyping enables the automatic extraction of clinical conditions from patient records, which can be beneficial to doctors and clinics worldwide.
We thus introduce an extendable testing framework that evaluates the behavior of clinical outcome models regarding changes of the input.
We apply KIMERA to BERT-base to evaluate the extent of the domain transfer and also improve on the already strong results of BioBERT in the clinical domain.
Retrieving answer passages from long documents is a complex task requiring semantic understanding of both discourse and document context.
Outcome prediction from clinical text can prevent doctors from overlooking possible risks and help hospitals to plan capacities.
Ranked #1 on Medical Diagnosis on Clinical Admission Notes from MIMIC-III (using extra training data)
At the same time, they are difficult to incorporate into the large, black-box models that achieve state-of-the-art results in a multitude of NLP tasks.
Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-task training to encode the position of clinical entities and aspects alongside the document discourse.
Our generalization of the tree doubling algorithm gives a parameterized 3-approximation, where the parameter is the number of asymmetric edges in a given minimum spanning arborescence.
Data Structures and Algorithms
In order to better understand BERT and other Transformer-based models, we present a layer-wise analysis of BERT's hidden states.
From our extensive evaluation of 20 architectures, we report a highest score of 71. 6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR LSTM model with bloom filter embeddings and bidirectional segmentation.
Toxic comment classification has become an active research field with many recently proposed approaches.
We present a new methodology for high-quality labeling in the fashion domain with crowd workers instead of experts.
We present a novel architecture, In-Database Entity Linking (IDEL), in which we integrate the analytics-optimized RDBMS MonetDB with neural text mining abilities.
We report results on benchmarking Open Information Extraction (OIE) systems using RelVis, a toolkit for benchmarking Open Information Extraction systems.