While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge. Retrieval-augmented generation (RAG) is a promising solution and has been widely adopted. However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes. To systematically evaluate such systems, we propose the Medical Information Retrieval-Augmented Generation Evaluation (MIRAGE), a first-of-its-kind benchmark including 7,663 questions from five medical QA datasets. Using MIRAGE, we conducted large-scale experiments with over 1.8 trillion prompt tokens on 41 combinations of different corpora, retrievers, and backbone LLMs through the MedRAG toolkit introduced in this work. Overall, MedRAG improves the accuracy of six different LLMs by up to 18% over chain-of-thought prompting, elevating the performance of GPT-3.5 and Mixtral to GPT-4-level. Our results show that the combination of various medical corpora and retrievers achieves the best performance. In addition, we discovered a log-linear scaling property and the “lost-in-the-middle” effects in medical RAG. We believe our comprehensive evaluations can serve as practical guidelines for implementing RAG systems for medicine.

Clinical trials provide essential guidance for practicing Evidence-Based Medicine, though often accompanying with unendurable costs and risks. To optimize the design of clinical trials, we introduce a novel Clinical Trial Result Prediction (CTRP) task. In the CTRP framework, a model takes a PICO-formatted clinical trial proposal with its background as input and predicts the result, i.e. how the Intervention group compares with the Comparison group in terms of the measured Outcome in the studied Population. While structured clinical evidence is prohibitively expensive for manual collection, we exploit large-scale unstructured sentences from medical literature that implicitly contain PICOs and results as evidence. Specifically, we pre-train a model to predict the disentangled results from such implicit evidence and fine-tune the model with limited data on the downstream datasets. Experiments on the benchmark Evidence Integration dataset show that the proposed model outperforms the baselines by large margins, e.g., with a 10.7% relative gain over BioBERT in macro-F1. Moreover, the performance improvement is also validated on another dataset composed of clinical trials related to COVID-19.

We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts. PubMedQA has 1k expert-annotated, 61.2k unlabeled and 211.3k artificially generated QA instances. Each PubMedQA instance is composed of (1) a question which is either an existing research article title or derived from one, (2) a context which is the corresponding abstract without its conclusion, (3) a long answer, which is the conclusion of the abstract and, presumably, answers the research question, and (4) a yes/no/maybe answer which summarizes the conclusion. PubMedQA is the first QA dataset where reasoning over biomedical research texts, especially their quantitative contents, is required to answer the questions. Our best performing model, multi-phase fine-tuning of BioBERT with long answer bag-of-word statistics as additional supervision, achieves 68.1% accuracy, compared to single human performance of 78.0% accuracy and majority-baseline of 55.2% accuracy, leaving much room for improvement. PubMedQA is publicly available at https://pubmedqa.github.io.

Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance. In this paper, we conduct probing experiments to determine what additional information is carried intrinsically by the in-domain trained contextualized embeddings. For this we use the pre-trained LMs as fixed feature extractors and restrict the downstream task models to not have additional sequence modeling layers. We compare BERT (Devlin et al. 2018), ELMo (Peters et al., 2018), BioBERT (Lee et al., 2019) and BioELMo, a biomedical version of ELMo trained on 10M PubMed abstracts. Surprisingly, while fine-tuned BioBERT is better than BioELMo in biomedical NER and NLI tasks, as a fixed feature extractor BioELMo outperforms BioBERT in our probing tasks. We use visualization and nearest neighbor analysis to show that better encoding of entity-type and relational information leads to this superiority.

Automatic identification and expansion of ambiguous abbreviations are essential for biomedical natural language processing applications, such as information retrieval and question answering systems. In this paper, we present DEep Contextualized Biomedical Abbreviation Expansion (DECBAE) model. DECBAE automatically collects substantial and relatively clean annotated contexts for 950 ambiguous abbreviations from PubMed abstracts using a simple heuristic. Then it utilizes BioELMo to extract the contextualized features of words, and feed those features to abbreviation-specific bidirectional LSTMs, where the hidden states of the ambiguous abbreviations are used to assign the exact definitions. Our DECBAE model outperforms other baselines by large margins, achieving average accuracy of 0.961 and macro-F1 of 0.917 on the dataset. It also surpasses human performance for expanding a sample abbreviation, and remains robust in imbalanced, low-resources and clinical settings.

Many problems in NLP require aggregating information from multiple mentions of the same entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks. We present a recurrent layer which is instead biased towards coreferent dependencies. The layer uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster. Incorporating this layer into a state-of-the-art reading comprehension model improves performance on three datasets – Wikihop, LAMBADA and the bAbi AI tasks – with large gains when training data is scarce.

There are millions of articles in PubMed database. To facilitate information retrieval, curators in the National Library of Medicine (NLM) assign a set of Medical Subject Headings (MeSH) to each article. MeSH is a hierarchically-organized vocabulary, containing about 28K different concepts, covering the fields from clinical medicine to information sciences. Several automatic MeSH indexing models have been developed to improve the time-consuming and financially expensive manual annotation, including the NLM official tool – Medical Text Indexer, and the winner of BioASQ Task5a challenge – DeepMeSH. However, these models are complex and not interpretable. We propose a novel end-to-end model, AttentionMeSH, which utilizes deep learning and attention mechanism to index MeSH terms to biomedical text. The attention mechanism enables the model to associate textual evidence with annotations, thus providing interpretability at the word level. The model also uses a novel masking mechanism to enhance accuracy and speed. In the final week of BioASQ Chanllenge Task6a, we ranked 2nd by average MiF using an on-construction model. After the contest, we achieve close to state-of-the-art MiF performance of ∼ 0.684 using our final model. Human evaluations show AttentionMeSH also provides high level of interpretability, retrieving about 90% of all expert-labeled relevant words given an MeSH-article pair at 20 output.