Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?

Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigated Named Entity Recognition (NER) and Relation Extraction (RE) using 1,588 clinical notes from four sources (UT Physicians, MTSamples, MIMIC-III, and i2b2). We developed an annotated corpus covering 4 clinical entities and 16 modifiers, and compared instruction-tuned LLaMA-2 and LLaMA-3 against BiomedBERT in terms of performance, generalizability, computational resources, and throughput to BiomedBERT. Results: LLaMA models outperformed BiomedBERT across datasets. With sufficient training data, LLaMA showed modest improvements (1% on NER, 1.5-3.7% on RE); improvements were larger with limited training data. On unseen i2b2 data, LLaMA-3-70B outperformed BiomedBERT by 7% (F1) on NER and 4% on RE. However, LLaMA models required more computing resources and ran up to 28 times slower. We implemented "Kiwi," a clinical IE package featuring both models, available at https://kiwi.clinicalnlp.org/. Conclusion: This study is among the first to develop and evaluate a comprehensive clinical IE system using open-source LLMs. Results indicate that LLaMA models outperform BiomedBERT for clinical NER and RE but with higher computational costs and lower throughputs. These findings highlight that choosing between LLMs and traditional deep learning methods for clinical IE applications should remain task-specific, taking into account both performance metrics and practical considerations such as available computing resources and the intended use case scenarios.

Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations

In acupuncture therapy, the accurate location of acupoints is essential for its effectiveness. The advanced language understanding capabilities of large language models (LLMs) like Generative Pre-trained Transformers (GPT) present a significant opportunity for extracting relations related to acupoint locations from textual knowledge sources. This study aims to compare the performance of GPT with traditional deep learning models (Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers for Biomedical Text Mining (BioBERT)) in extracting acupoint-related location relations and assess the impact of pretraining and fine-tuning on GPT's performance. We utilized the World Health Organization Standard Acupuncture Point Locations in the Western Pacific Region (WHO Standard) as our corpus, which consists of descriptions of 361 acupoints. Five types of relations ('direction_of,' 'distance_of,' 'part_of,' 'near_acupoint,' and 'located_near') (n= 3,174) between acupoints were annotated. Five models were compared: BioBERT, LSTM, pre-trained GPT-3.5, fine-tuned GPT-3.5, as well as pre-trained GPT-4. Performance metrics included micro-average exact match precision, recall, and F1 scores. Our results demonstrate that fine-tuned GPT-3.5 consistently outperformed other models in F1 scores across all relation types. Overall, it achieved the highest micro-average F1 score of 0.92. This study underscores the effectiveness of LLMs like GPT in extracting relations related to acupoint locations, with implications for accurately modeling acupuncture knowledge and promoting standard implementation in acupuncture training and practice. The findings also contribute to advancing informatics applications in traditional and complementary medicine, showcasing the potential of LLMs in natural language processing.

Me LLaMA: Foundation Large Language Models for Medical Applications

Recent large language models (LLMs) like ChatGPT and LLaMA have shown great promise in many AI applications. However, their performance on medical tasks is suboptimal and can be further improved by training on large domain-specific datasets. This study introduces Me LLaMA, a medical LLM family including foundation models - Me LLaMA 13/70B and their chat-enhanced versions - Me LLaMA 13/70B-chat, developed through the continual pre-training and instruction tuning of LLaMA2 using large medical data. Our domain-specific data suite for training and evaluation, includes a large-scale continual pre-training dataset with 129B tokens, an instruction tuning dataset with 214k samples, and a medical evaluation benchmark (MIBE) across six tasks with 14 datasets. Our extensive evaluation using MIBE shows that Me LLaMA models surpass existing open-source medical LLMs in zero-shot and few-shot learning and outperform commercial giants like ChatGPT on 6 out of 8 datasets and GPT-4 in 3 out of 8 datasets. In addition, we empirically investigated the catastrophic forgetting problem, and our results show that Me LLaMA models outperform other medical LLMs. Me LLaMA is one of the first and largest open-source foundational LLMs designed for the medical domain, using both biomedical and clinical data. It exhibits superior performance across both general and medical tasks compared to other medical LLMs, rendering it an attractive choice for medical AI applications. All resources are available at: https://github.com/BIDS-Xu-Lab/Me-LLaMA.

Large language models in biomedical natural language processing: benchmarks, baselines, and recommendations

Biomedical literature is growing rapidly, making it challenging to curate and extract knowledge manually. Biomedical natural language processing (BioNLP) techniques that can automatically extract information from biomedical literature help alleviate this burden. Recently, large Language Models (LLMs), such as GPT-3 and GPT-4, have gained significant attention for their impressive performance. However, their effectiveness in BioNLP tasks and impact on method development and downstream users remain understudied. This pilot study (1) establishes the baseline performance of GPT-3 and GPT-4 at both zero-shot and one-shot settings in eight BioNLP datasets across four applications: named entity recognition, relation extraction, multi-label document classification, and semantic similarity and reasoning, (2) examines the errors produced by the LLMs and categorized the errors into three types: missingness, inconsistencies, and unwanted artificial content, and (3) provides suggestions for using LLMs in BioNLP applications. We make the datasets, baselines, and results publicly available to the community via https://github.com/qingyu-qc/gpt_bionlp_benchmark.

Zero-shot Clinical Entity Recognition using ChatGPT

In this study, we investigated the potential of ChatGPT, a large language model developed by OpenAI, for the clinical named entity recognition task defined in the 2010 i2b2 challenge, in a zero-shot setting with two different prompt strategies. We compared its performance with GPT-3 in a similar zero-shot setting, as well as a fine-tuned BioClinicalBERT model using a set of synthetic clinical notes from MTSamples. Our findings revealed that ChatGPT outperformed GPT-3 in the zero-shot setting, with F1 scores of 0.418 (vs.0.250) and 0.620 (vs. 0.480) for exact- and relaxed-matching, respectively. Moreover, prompts affected ChatGPT's performance greatly, with relaxed-matching F1 scores of 0.628 vs.0.541 for two different prompt strategies. Although ChatGPT's performance was still lower than that of the supervised BioClinicalBERT model (i.e., relaxed-matching F1 scores of 0.628 vs. 0.870), our study demonstrates the great potential of ChatGPT for clinical NER tasks in a zero-shot setting, which is much more appealing as it does not require any annotation.