The entry of large language models (LLMs) into research and commercial spaces has led to a trend of ever-larger models, with initial promises of generalisability, followed by a widespread desire to downsize and create specialised models without the need for complete fine-tuning, using Parameter Efficient Fine-tuning (PEFT) methods. We present an investigation into the suitability of different PEFT methods to clinical decision-making tasks, across a range of model sizes, including extremely small models with as few as $25$ million parameters. Our analysis shows that the performance of most PEFT approaches varies significantly from one task to another, with the exception of LoRA, which maintains relatively high performance across all model sizes and tasks, typically approaching or matching full fine-tuned performance. The effectiveness of PEFT methods in the clinical domain is evident, particularly for specialised models which can operate on low-cost, in-house computing infrastructure. The advantages of these models, in terms of speed and reduced training costs, dramatically outweighs any performance gain from large foundation LLMs. Furthermore, we highlight how domain-specific pre-training interacts with PEFT methods and model size, and discuss how these factors interplay to provide the best efficiency-performance trade-off. Full code available at: tbd.

Large Language Models (LLMs), particularly those similar to ChatGPT, have significantly influenced the field of Natural Language Processing (NLP). While these models excel in general language tasks, their performance in domain-specific downstream tasks such as biomedical and clinical Named Entity Recognition (NER), Relation Extraction (RE), and Medical Natural Language Inference (NLI) is still evolving. In this context, our study investigates the potential of instruction tuning for biomedical language processing, applying this technique to two general LLMs of substantial scale. We present a comprehensive, instruction-based model trained on a dataset that consists of approximately $200,000$ instruction-focused samples. This dataset represents a carefully curated compilation of existing data, meticulously adapted and reformatted to align with the specific requirements of our instruction-based tasks. This initiative represents an important step in utilising such models to achieve results on par with specialised encoder-only models like BioBERT and BioClinicalBERT for various classical biomedical NLP tasks. Our work includes an analysis of the dataset's composition and its impact on model performance, providing insights into the intricacies of instruction tuning. By sharing our codes, models, and the distinctively assembled instruction-based dataset, we seek to encourage ongoing research and development in this area.

Large language models (LLMs) have made significant progress in various domains, including healthcare. However, the specialized nature of clinical language understanding tasks presents unique challenges and limitations that warrant further investigation. In this study, we conduct a comprehensive evaluation of state-of-the-art LLMs, namely GPT-3.5, GPT-4, and Bard, within the realm of clinical language understanding tasks. These tasks span a diverse range, including named entity recognition, relation extraction, natural language inference, semantic textual similarity, document classification, and question-answering. We also introduce a novel prompting strategy, self-questioning prompting (SQP), tailored to enhance LLMs' performance by eliciting informative questions and answers pertinent to the clinical scenarios at hand. Our evaluation underscores the significance of task-specific learning strategies and prompting techniques for improving LLMs' effectiveness in healthcare-related tasks. Additionally, our in-depth error analysis on the challenging relation extraction task offers valuable insights into error distribution and potential avenues for improvement using SQP. Our study sheds light on the practical implications of employing LLMs in the specialized domain of healthcare, serving as a foundation for future research and the development of potential applications in healthcare settings.

We noticed that ChatGPT struggled to extract co-reference entities like "her medications" or "her symptoms", which should be annotated in accordance with the 2010 i2b2 annotation guidelines, for coreference identification purposes. After we removed those co-reference entities in the gold standard and re-evaluated the performance of both ChatGPT and GPT-3, we observed modest increases in performance, with ChatGPT achieving an F1 score of 0.628 using Prompt-2 and GPT-3 attaining an F1 score of 0.500 in the relaxed-match criteria. Moreover, we observed a significant degree of randomness in ChatGPT's output. Even when presented with the same prompt and the same input text, it sometimes generated responses with considerable differences in format and content. This phenomenon was particularly prevalent when the input note was lengthy, despite our efforts to minimize input sequence length by limiting it to the HPI section. We anticipate this issue will be addressed when GPT-4 allows much longer text. Although it is not clear whether clinical corpora (and what types of clinical corpora) are used in training ChatGPT, ChatGPT has demonstrated its understanding of the medical text to a certain degree. We believe fine-tuning ChatGPT with domain-specific corpora, assuming OpenAI will provide such an API, will further improve its performance on clinical NLP tasks such as NER in the zero-shot fashion.

Specialised pre-trained language models are becoming more frequent in NLP since they can potentially outperform models trained on generic texts. BioBERT (Sanh et al., 2019) and BioClinicalBERT (Alsentzer et al., 2019) are two examples of such models that have shown promise in medical NLP tasks. Many of these models are overparametrised and resource-intensive, but thanks to techniques like Knowledge Distillation (KD), it is possible to create smaller versions that perform almost as well as their larger counterparts. In this work, we specifically focus on development of compact language models for processing clinical texts (i.e. We developed a number of efficient lightweight clinical transformers using knowledge distillation and continual learning, with the number of parameters ranging from 15 million to 65 million. These models performed comparably to larger models such as BioBERT and ClinicalBioBERT and significantly outperformed other compact models trained on general or biomedical data. Our extensive evaluation was done across several standard datasets and covered a wide range of clinical text-mining tasks, including Natural Language Inference, Relation Extraction, Named Entity Recognition, and Sequence Classification. To our knowledge, this is the first comprehensive study specifically focused on creating efficient and compact transformers for clinical NLP tasks. The models and code used in this study can be found on our Huggingface profile at https: //huggingface.co/nlpie and Github page at https://github.com/ Large language models pre-trained on generic texts serve as the foundation upon which most stateof-the-art NLP models are built. There is ample evidence that, for certain domains and downstream tasks, models that are pre-trained on specialised data outperform baselines that have only relied on generic texts (Sanh et al., 2019; Alsentzer et al., 2019; Beltagy et al., 2019; Nguyen et al., 2020; Chalkidis et al., 2020).

Both electronic health records and personal health records are typically organized by data type, with medical problems, medications, procedures, and laboratory results chronologically sorted in separate areas of the chart. As a result, it can be difficult to find all of the relevant information for answering a clinical question about a given medical problem. A promising alternative is to instead organize by problems, with related medications, procedures, and other pertinent information all grouped together. A recent effort by Buchanan (2017) manually defined, through expert consensus, 11 medical problems and the relevant labs and medications for each. We show how to use machine learning on electronic health records to instead automatically construct these problem-based groupings of relevant medications, procedures, and laboratory tests. We formulate the learning task as one of knowledge base completion, and annotate a dataset that expands the set of problems from 11 to 32. We develop a model architecture that exploits both pre-trained concept embeddings and usage data relating the concepts contained in a longitudinal dataset from a large health system. We evaluate our algorithms' ability to suggest relevant medications, procedures, and lab tests, and find that the approach provides feasible suggestions even for problems that are hidden during training. The dataset, along with code to reproduce our results, is available at https://github.com/asappresearch/kbc-pomr.

Artificial intelligence is often hailed as a great catalyst of medical innovation, a way to find cures to diseases that have confounded doctors and make health care more efficient, personalized, and accessible. But what if it turns out to be poison? Jonathan Zittrain, a Harvard Law School professor, posed that question during a conference in Boston Tuesday that examined the use of AI to accelerate the delivery of precision medicine to the masses. "I think of machine learning kind of as asbestos," he said. "It turns out that it's all over the place, even though at no point did you explicitly install it, and it has possibly some latent bad effects that you might regret later, after it's already too hard to get it all out."

It's impossible to read about the future of healthcare without encountering two pixelated vowels that, together, represent the hopes and fears of an industry seeking more intelligent solutions. Though the field of artificial intelligence (AI) has been around since 1956, it has made precious few contributions to medical practice. Only recently has the hype of machine-based learning begun to merge with reality. Confusion surrounding AI--its applications in healthcare and even its definition--remains widespread in popular media. Today, AI is shorthand for any task a computer can perform just as well as, if not better than, humans.

Mining relationships between treatment(s) and medical problem(s) is vital in the biomedical domain. This helps in various applications, such as decision support system, safety surveillance, and new treatment discovery. We propose a deep learning approach that utilizes both word level and sentence-level representations to extract the relationships between treatment and problem. While deep learning techniques demand a large amount of data for training, we make use of a rule-based system particularly for relationship classes with fewer samples. Our final relations are derived by jointly combining the results from deep learning and rule-based models. Our system achieved a promising performance on the relationship classes of I2b2 2010 relation extraction task.

This report summarises views expressed in the second of three BCS Thought Leadership Debates run in association with the UK Office of Science and Technology as part of the Cognitive Systems Programme of the UK Foresight Programme, which explores areas for advanced research. The event was on 25 November 2004 at the Institute of Directors in London. Two expert speakers stimulated debate with short talks and then the 30 participants discussed the topic in small groups over dinner. The participants were mainly senior computer scientists and neuroscientists from UK universities, with others from specialist companies and research organisations. After dinner each table reported back to the entire gathering.