Importance: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models’ performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets. Objectives: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance. Materials and Methods: We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT. Results: Using baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed. Discussion: The study’s findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings. Conclusion: While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.

Existing general clinical natural language processing (NLP) systems such as MetaMap and Clinical Text Analysis and Knowledge Extraction System have been successfully applied to information extraction from clinical text. However, end users often have to customize existing systems for their individual tasks, which can require substantial NLP skills. Here we present CLAMP (Clinical Language Annotation, Modeling, and Processing), a newly developed clinical NLP toolkit that provides not only state-of-the-art NLP components, but also a user-friendly graphic user interface that can help users quickly build customized NLP pipelines for their individual applications. Our evaluation shows that the CLAMP default pipeline achieved good performance on named entity recognition and concept encoding. We also demonstrate the efficiency of the CLAMP graphic user interface in building customized, high-performance NLP pipelines with 2 use cases, extracting smoking status and lab test values. CLAMP is publicly available for research use, and we believe it is a unique asset for the clinical NLP community.

Generative artificial intelligence (AI) and large language models (LLMs), exemplified by ChatGPT, are promising for revolutionizing data and information management in healthcare and medicine. However, there is scant literature guiding their integration for non-AI professionals. This study conducts a scoping literature review to address the critical need for guidance on integrating generative AI and LLMs into healthcare and medical practices. It elucidates the distinct mechanisms underpinning these technologies, such as Reinforcement Learning from Human Feedback (RLFH), including few-shot learning and chain-of-thought reasoning, which differentiates them from traditional, rule-based AI systems. It requires an inclusive, collaborative co-design process that engages all pertinent stakeholders, including clinicians and consumers, to achieve these benefits. Although global research is examining both opportunities and challenges, including ethical and legal dimensions, LLMs offer promising advancements in healthcare by enhancing data management, information retrieval, and decision-making processes. Continued innovation in data acquisition, model fine-tuning, prompt strategy development, evaluation, and system implementation is imperative for realizing the full potential of these technologies. Organizations should proactively engage with these technologies to improve healthcare quality, safety, and efficiency, adhering to ethical and legal guidelines for responsible application.

The discovery of novel anticancer drugs is critical for the pharmaceutical research and development, and patient treatment. Repurposing existing drugs that may have unanticipated effects as potential candidates is one way to meet this important goal. Systematic investigation of efficient anticancer drugs could provide valuable insights into trends in the discovery of anticancer drugs, which may contribute to the systematic discovery of new anticancer drugs. In this study, we collected and analyzed 150 anticancer drugs approved by the US Food and Drug Administration (FDA). Based on drug mechanism of action, these agents are divided into two groups: 61 cytotoxic-based drugs and 89 target-based drugs. We found that in the recent years, the proportion of targeted agents tended to be increasing, and the targeted drugs tended to be delivered as signal drugs. For 89 target-based drugs, we collected 102 effect-mediating drug targets in the human genome and found that most targets located on the plasma membrane and most of them belonged to the enzyme, especially tyrosine kinase. From above 150 drugs, we built a drug-cancer network, which contained 183 nodes (150 drugs and 33 cancer types) and 248 drug-cancer associations. The network indicated that the cytotoxic drugs tended to be used to treat more cancer types than targeted drugs. From 89 targeted drugs, we built a cancer-drug-target network, which contained 214 nodes (23 cancer types, 89 drugs, and 102 targets) and 313 edges (118 drug-cancer associations and 195 drug-target associations). Starting from the network, we discovered 133 novel drug-cancer associations among 52 drugs and 16 cancer types by applying the common target-based approach. Most novel drug-cancer associations (116, 87%) are supported by at least one clinical trial study. In this study, we provided a comprehensive data source, including anticancer drugs and their targets and performed a detailed analysis in term of historical tendency and networks. Its application to identify novel drug-cancer associations demonstrated that the data collected in this study is promising to serve as a fundamental for anticancer drug repurposing and development.

The rapid growth of biomedical literature poses challenges for manual knowledge curation and synthesis. Biomedical Natural Language Processing (BioNLP) automates the process. While Large Language Models (LLMs) have shown promise in general domains, their effectiveness in BioNLP tasks remains unclear due to limited benchmarks and practical guidelines. We perform a systematic evaluation of four LLMs—GPT and LLaMA representatives—on 12 BioNLP benchmarks across six applications. We compare their zero-shot, few-shot, and fine-tuning performance with the traditional fine-tuning of BERT or BART models. We examine inconsistencies, missing information, hallucinations, and perform cost analysis. Here, we show that traditional fine-tuning outperforms zero- or few-shot LLMs in most tasks. However, closed-source LLMs like GPT-4 excel in reasoning-related tasks such as medical question answering. Open-source LLMs still require fine-tuning to close performance gaps. We find issues like missing information and hallucinations in LLM outputs. These results offer practical insights for applying LLMs in BioNLP.

Objectives Drug repurposing, which finds new indications for existing drugs, has received great attention recently. The goal of our work is to assess the feasibility of using electronic health records (EHRs) and automated informatics methods to efficiently validate a recent drug repurposing association of metformin with reduced cancer mortality. Methods By linking two large EHRs from Vanderbilt University Medical Center and Mayo Clinic to their tumor registries, we constructed a cohort including 32 415 adults with a cancer diagnosis at Vanderbilt and 79 258 cancer patients at Mayo from 1995 to 2010. Using automated informatics methods, we further identified type 2 diabetes patients within the cancer cohort and determined their drug exposure information, as well as other covariates such as smoking status. We then estimated HRs for all-cause mortality and their associated 95% CIs using stratified Cox proportional hazard models. HRs were estimated according to metformin exposure, adjusted for age at diagnosis, sex, race, body mass index, tobacco use, insulin use, cancer type, and non-cancer Charlson comorbidity index. Results Among all Vanderbilt cancer patients, metformin was associated with a 22% decrease in overall mortality compared to other oral hypoglycemic medications (HR 0.78; 95% CI 0.69 to 0.88) and with a 39% decrease compared to type 2 diabetes patients on insulin only (HR 0.61; 95% CI 0.50 to 0.73). Diabetic patients on metformin also had a 23% improved survival compared with non-diabetic patients (HR 0.77; 95% CI 0.71 to 0.85). These associations were replicated using the Mayo Clinic EHR data. Many site-specific cancers including breast, colorectal, lung, and prostate demonstrated reduced mortality with metformin use in at least one EHR. Conclusions EHR data suggested that the use of metformin was associated with decreased mortality after a cancer diagnosis compared with diabetic and non-diabetic cancer patients not on metformin, indicating its potential as a chemotherapeutic regimen. This study serves as a model for robust and inexpensive validation studies for drug repurposing signals using EHR data.