A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives.

While large language models (LLMs) are endowed with broad knowledge, their task-specific performance is often suboptimal. Fine-tuning LLMs with task-specific data from diverse nodes is necessary, but this data is typically safeguarded and not shared publicly due to privacy concerns. A common solution involves downstream nodes downloading the LLM locally and fine-tuning it with their proprietary data. However, owners often regard pre-trained LLMs as valuable assets and are reluctant to share them. Additionally, the significant computational resources required by LLMs make local fine-tuning impractical for many nodes. To mitigate these problems, this paper proposes CrossLM, a data-free collaborative fine-tuning framework for large and small language models. CrossLM enables resource-constrained nodes to train smaller language models (SLMs) using their private task-specific data. These SLMs are subsequently leveraged to promote the task-specific natural language generation and understanding capabilities of the LLMs. Simultaneously, the SLMs of nodes also benefit from enhancement by the fine-tuned LLMs. In this way, CrossLM avoids sharing private data and proprietary LLMs, and also reduces the resource requirements of nodes. Through extensive experiments across a range of benchmark tasks and popular language models, we demonstrate that CrossLM significantly boosts the task-specific performance of both LLMs and SLMs while preserving the generalization capabilities of LLMs.

How Can <i>IJDS</i> Authors, Reviewers, and Editors Use (and Misuse) Generative AI?

Use of neurosurgical data for clinical research and machine learning (ML) model development is often limited by data availability, sample sizes, and regulatory constraints. Synthetic data offer a potential solution to challenges associated with accessing, sharing, and using real-world data (RWD). The aim of this study was to evaluate the capability of generating synthetic neurosurgical data with a generative adversarial network and large language model (LLM) to augment RWD, perform secondary analyses in place of RWD, and train an ML model to predict postoperative outcomes. Synthetic data were generated with a conditional tabular generative adversarial network (CTGAN) and the LLM GPT-4o based on a real-world neurosurgical dataset of 140 older adults who underwent neurosurgical interventions. Each model was used to generate datasets at equivalent (n = 140) and amplified (n = 1000) sample sizes. Data fidelity was evaluated by comparing univariate and bivariate statistics to the RWD. Privacy evaluation involved measuring the uniqueness of generated synthetic records. Utility was assessed by: 1) reproducing and extending clinical analyses on predictors of Karnofsky Performance Status (KPS) deterioration at discharge and a prolonged postoperative intensive care unit (ICU) stay, and 2) training a binary ML classifier on amplified synthetic datasets to predict KPS deterioration on RWD. Both the CTGAN and GPT-4o generated complete, high-fidelity synthetic tabular datasets. GPT-4o matched or exceeded CTGAN across all measured fidelity, utility, and privacy metrics. All significant clinical predictors of KPS deterioration and prolonged ICU stay were retained in the GPT-4o-generated synthetic data, with some differences observed in effect sizes. Preoperative KPS was not preserved as a significant predictor in the CTGAN-generated data. The ML classifier trained on GPT-4o data outperformed the model trained on CTGAN data, achieving a higher F1 score (0.725 vs 0.688) for predicting KPS deterioration. This study demonstrated a promising ability to produce high-fidelity synthetic neurosurgical data using generative models. Synthetic neurosurgical data present a potential solution to critical limitations in data availability for neurosurgical research. Further investigation is necessary to enhance synthetic data utility for secondary analyses and ML model training, and to evaluate synthetic data generation methods across other datasets, including clinical trial data.

Named entity recognition (NER) plays a vital role in extracting critical medical entities from health care records, facilitating applications such as clinical decision support and data mining. Developing robust NER models for low-resource languages, such as Estonian, remains a challenge due to the scarcity of annotated data and domain-specific pretrained models. Large language models (LLMs) have proven to be promising in understanding text from any language or domain. This study addresses the development of medical NER models for low-resource languages, specifically Estonian. We propose a novel approach by generating synthetic health care data and using LLMs to annotate them. These synthetic data are then used to train a high-performing NER model, which is applied to real-world medical texts, preserving patient data privacy. Our approach to overcoming the shortage of annotated Estonian health care texts involves a three-step pipeline: (1) synthetic health care data are generated using a locally trained GPT-2 model on Estonian medical records, (2) the synthetic data are annotated with LLMs, specifically GPT-3.5-Turbo and GPT-4, and (3) the annotated synthetic data are then used to fine-tune an NER model, which is later tested on real-world medical data. This paper compares the performance of different prompts; assesses the impact of GPT-3.5-Turbo, GPT-4, and a local LLM; and explores the relationship between the amount of annotated synthetic data and model performance. The proposed methodology demonstrates significant potential in extracting named entities from real-world medical texts. Our top-performing setup achieved an F1-score of 0.69 for drug extraction and 0.38 for procedure extraction. These results indicate a strong performance in recognizing certain entity types while highlighting the complexity of extracting procedures. This paper demonstrates a successful approach to leveraging LLMs for training NER models using synthetic data, effectively preserving patient privacy. By avoiding reliance on human-annotated data, our method shows promise in developing models for low-resource languages, such as Estonian. Future work will focus on refining the synthetic data generation and expanding the method's applicability to other domains and languages.

Large language models’ exceptional all-purpose abilities have made human-computer conversations normal, but for particular industries and verticals, they fall short of enhancing the expertise of knowledge and the timeliness of information. In order to give current information, and provide improved search capabilities, large language models need to increasingly incorporate specialist resources and databases. In this research, a model for intelligent assisted decision-making was proposed that the model incorporates knowledge from domain-specific databases and real-time data and uses large language models to offer expert tax guidance. The research proposed to overcome the limits of general-purpose language models and deliver specialized advise for tax-related inquiries by complementing large language models with domain-specific information.The results we achieve demonstrate that by offering tax advice tailored to a given situation, and the model we proposed goes beyond the validity of general large language language models. Our contribution is that not only exploring the combination of tax area and large language model, but also proposing a new effective model for government tax department to use in real life. This study highlights the potential of big language models for use in real-world professional domains and advances the field of domain-specific human-computer interaction.

Background: Large language models (LLMs) excel on standardized oncology exams; however, their broader clinical utility remains unclear. LLMs are easy to use through “prompting.” For example, a doctor or patient can provide a clinical note and ask about the probability of an adverse event (AE). Current AE prediction relies on machine learning using tabular data, which requires substantial engineering to adapt to specific tasks and settings, making them costly and less generalizable. We compared prompting LLMs against tabular ML models to predict AEs during systemic cancer therapy. Materials an. Methods: Patients with aerodigestive cancers at Princess Margaret Cancer Centre who received their first systemic therapy from 2008 to 2015 formed the development set, and from 2016 to 2018 formed the test set. We evaluated different prompting strategies with open-source LLMs using the de-identified consult and most recent pre-treatment note from each patient to predict the risk of clinical, symptom, and laboratory AEs. An ensemble of ML models was trained on tabular electronic health record data for comparison. We measured performance with the area under the receiver-operating characteristic curve (AUC). Using an established schema, an oncologist reviewed the text-based justifications from 20 random LLM predictions. Results The cohort included 6,381 patients. Notes had a median token length of 1,737 (range 137-7,795). The LLM Qwen 2.5 14B achieved the best AUC across 14 of 19 AEs in the development set. The larger 14B model outperformed the 7B model on all targets (p = 4e-5). Among prompting strategies, no benefit was observed with the oncologist versus AI model persona (p = 0.21), chain-of-thought reasoning (p = 0.23), or concatenating tabular data to notes (p = 0.42). In the test cohort, LLMs and tabular ML showed equivalent performance for some AEs, such as death within 30 days (LLM AUC: 0.73 [95% CI 0.66, 0.80], versus [v.] ML: 0.74 [0.67, 0.81], p = 0.89) and hyperbilirubinemia (0.79 [0.72, 0.86] v. 0.78 [0.70, 0.85], p = 0.77). For other AEs, performance was numerically similar, such as death in one year (0.72 [0.70, 0.74] v. 0.76 [0.73, 0.78], p = 0.02) and anemia (0.78 [0.75, 0.80] v. 0.82 [0.8, 0.84], p = 0.01). LLMs performed worse for symptom-related AEs, such as pain (0.48 [0.44, 0.53] v. 0.69 [0.65, 0.74], p = 1e-11) and tiredness (0.49 [0.45, 0.52] v. 0.69 [0.65, 0.72], p = 2e-14). The oncologist deemed LLM justifications satisfactory across all dimensions for at least 90% of predictions, except that 20% had factual consistency errors. Conclusion: Prompting LLMs performed similarly to engineered tabular ML models for predicting several AEs, despite using only raw text from notes. Better performance with larger models suggests the gap between LLMs and ML models may continue to narrow. This work lays the foundation for using LLMs as general-purpose clinical decision-support tools for cancer care. Citation Format: Wayne Isaac T. Uy, Galileo Arturo Gonzalez Conchas, Jiang Chen He, Muammar Kabir, Baijiang Yuan, Geoffrey Liu, Sharon Narine, Melanie Powis, Benjamin Grant, Mattea Welch, Tran Truong, Robert Grant. Prompting Large Language Models to Predict Adverse Events during Cancer Treatment [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr B012.

Recent advancements in Generative Adversarial Networks and large language models (LLMs) have significantly advanced the synthesis and augmentation of medical data. These and other deep learning-based methods offer promising potential for generating high-quality, realistic datasets crucial for improving machine learning applications in health care, particularly in contexts where data privacy and availability are limiting factors. However, challenges remain in accurately capturing the complex associations inherent in medical datasets. This study evaluates the effectiveness of various Synthetic Data Generation (SDG) methods in replicating the correlation structures inherent in real medical datasets. In addition, it examines their performance in downstream tasks using Random Forests (RFs) as the benchmark model. To provide a comprehensive analysis, alternative models such as eXtreme Gradient Boosting and Gated Additive Tree Ensembles are also considered. We compare the following SDG approaches: Synthetic Populations in R (synthpop), copula, copulagan, Conditional Tabular Generative Adversarial Network (ctgan), tabular variational autoencoder (tvae), and tabula for LLMs. We evaluated synthetic data generation methods using both real-world and simulated datasets. Simulated data consist of 10 Gaussian variables and one binary target variable with varying correlation structures, generated via Cholesky decomposition. Real-world datasets include the body performance dataset with 13,393 samples for fitness classification, the Wisconsin Breast Cancer dataset with 569 samples for tumor diagnosis, and the diabetes dataset with 768 samples for diabetes prediction. Data quality is evaluated by comparing correlation matrices, the propensity score mean-squared error (pMSE) for general utility, and F1-scores for downstream tasks as a specific utility metric, using training on synthetic data and testing on real data. Our simulation study, supplemented with real-world data analyses, shows that the statistical methods copula and synthpop consistently outperform deep learning approaches across various sample sizes and correlation complexities, with synthpop being the most effective. Deep learning methods, including large LLMs, show mixed performance, particularly with smaller datasets or limited training epochs. LLMs often struggle to replicate numerical dependencies effectively. In contrast, methods like tvae with 10,000 epochs perform comparably well. On the body performance dataset, copulagan achieves the best performance in terms of pMSE. The results also highlight that model utility depends more on the relative correlations between features and the target variable than on the absolute magnitude of correlation matrix differences. Statistical methods, particularly synthpop, demonstrate superior robustness and utility preservation for synthetic tabular data compared with deep learning approaches. Copula methods show potential but face limitations with integer variables. Deep Learning methods underperform in this context. Overall, these findings underscore the dominance of statistical methods for synthetic data generation for tabular data, while highlighting the niche potential of deep learning approaches for highly complex datasets, provided adequate resources and tuning.

For sharing privacy-sensitive data, de-identification is commonly regarded as adequate for safeguarding privacy. Synthetic data is also being considered as a privacy-preserving alternative. Recent successes with numerical and tabular data generative models and the breakthroughs in large generative language models raise the question of whether synthetically generated clinical notes could be a viable alternative to real notes for research purposes. In this work, we demonstrated that (i) de-identification of real clinical notes does not protect records against a membership inference attack, (ii) proposed a novel approach to generate synthetic clinical notes using the current state-of-the-art large language models, (iii) evaluated the performance of the synthetically generated notes in a clinical domain task, and (iv) proposed a way to mount a membership inference attack where the target model is trained with synthetic data. We observed that when synthetically generated notes closely match the performance of real data, they also exhibit similar privacy concerns to the real data. Whether other approaches to synthetically generated clinical notes could offer better trade-offs and become a better alternative to sensitive real notes warrants further investigation.

Broca's aphasia is a type of aphasia characterized by non-fluent, effortful and agrammatic speech production with relatively good comprehension. Since traditional aphasia treatment methods are often time-consuming, labour-intensive, and do not reflect real-world conversations, applying natural language processing based approaches such as Large Language Models (LLMs) could potentially contribute to improving existing treatment approaches. To address this issue, we explore the use of sequence-to-sequence LLMs for completing Broca's aphasic sentences. We first generate synthetic Broca's aphasic data using a rule-based system designed to mirror the linguistic characteristics of Broca's aphasic speech. Using this synthetic data (without authentic aphasic samples), we then fine-tune four pre-trained LLMs on the task of completing agrammatic sentences. We evaluate our fine-tuned models on both synthetic and authentic Broca's aphasic data. We demonstrate LLMs' capability for reconstructing agrammatic sentences, with the models showing improved performance with longer input utterances. Our result highlights the LLMs' potential in advancing communication aids for individuals with Broca's aphasia and possibly other clinical populations.

The emergence of large language models (LLMs) and the increasing prevalence of electronic health records (EHRs) present significant opportunities for advancing health care research and practice. However, research that compares and applies LLMs to extract key epilepsy-related information from unstructured medical free text is under-explored. This study fills this gap by comparing and applying different open-source LLMs and methods to extract epilepsy information from unstructured clinic letters, thereby optimizing EHRs as a resource for the benefit of epilepsy research. We also highlight some limitations of LLMs. Employing a dataset of 280 annotated clinic letters from King's College Hospital, we explored the efficacy of open-source LLMs (Llama and Mistral series) for extracting key epilepsy-related information, including epilepsy type, seizure type, current anti-seizure medications (ASMs), and associated symptoms. The study used various extraction methods, including direct extraction, summarized extraction, and contextualized extraction, complemented by role-prompting and few-shot prompting techniques. Performance was evaluated against a gold standard dataset, and was also compared to advanced fine-tuned models and human annotations. Llama 2 13b (a 13-billion-parameter LLM developed by Meta) demonstrated superior extraction capabilities across tasks by consistently outperforming other LLMs (F1 = .80 in epilepsy-type extraction, F1 = .76 in seizure-type extraction, and F1 = .90 in current ASMs extraction). Here, F1 score is a balanced metric indicating the model's accuracy in correctly identifying relevant information without excessive false positives. The study highlights the direct extraction showing consistent high performance. Comparative analysis showed that LLMs outperformed current approaches like MedCAT (Medical Concept Annotation Tool) in extracting epilepsy-related information (.2 higher in F1). The results affirm the potential of LLMs in medical information extraction relating to epilepsy, offering insights into leveraging these models for detailed and accurate data extraction from unstructured texts. The study underscores the importance of method selection in optimizing extraction performance and suggests a promising avenue for enhancing medical research and patient care through advanced natural language processing technologies.

Unlocking new frontiers in leukemia diagnostics through large language Model–Driven report generation

Rationale: The majority of clinically relevant data is contained in unstructured text such as clinical notes. ILD notes are particularly prone to verbosity and imprecision, making structured data extraction a major bottleneck for clinical research and a costly endeavor when maintaining ILD registries and databases. In this study, we explore the utility and performance characteristics of current GPT LLMs for extracting structured binary data from unstructured clinical text. Methods: We used GPT-3.5-turbo, GPT-4, GPT-4o, GPT-4o-mini and GPT-o1-mini models using a protected health information (PHI) compliant API pipeline and Llama 3.3-70B, Llama 3.1-8B and Mistral-7b-0.3 running locally on GPUs. Patients who were initially seen in the Stanford ILD clinic between 2018 to 2022, with at least three follow-up visits were selected for this study. Prompt engineering was performed using notes randomly selected from 10 patients of this cohort. Various prompt types (simple, heuristic, and chain of thought) were tested and those with best performance were selected. 100 randomly selected clinic notes from the patient cohort that had not been previously used in the prompt engineering stage were then processed through the LLM pipeline. Three ILD physicians independently scored the same notes and prompts. The discordant answers were reviewed by two ILD physicians to come to a consensus answer, which was considered the ground truth for this study. In addition to answering questions, LLMs can also provide a measure of its confidence in the answer. We used the logprobs parameter to assess the LLM's confidence in its answer, and compared the accuracy for answers in which the LLM was confident versus not. Results: It took approximately 1-2 seconds to process each clinical note-prompt combination. The three ILD physicians’ mean accuracy was 96%, similar to that of GPT-4, GPT-4o, GPT-4o-mini and GPT-o1-mini (Table 1). GPT 3.5, Llama 3.3-70B, Llama 3.1-8B and Mistral-7b-0.3 ‘s accuracy was much lower, to the point of not being clinically useful. The LLMs were substantially less accurate for questions where the LLM's level of confidence was low (&amp;lt;80%). Conclusions: GPT LLMs demonstrate human level accuracy while being orders of magnitude faster for extracting structured binary data from unstructured ILD clinical data. Using the LLM's confidence in the answer can further identify records requiring human review, allowing for additional improvement in accuracy. Incorporating these GPT LLMs in ILD clinical research has the potential to dramatically accelerate data-driven insights, streamline research workflows, and elevate clinical research to a new level.

CARDBiomedBench: a benchmark for evaluating the performance of large language models in biomedical research.

With the rapid development of Large Language Model (LLM) technology, it has become an indispensable force in biomedical data analysis research. However, biomedical researchers currently have limited knowledge about LLM. Therefore, there is an urgent need for a summary of LLM applications in biomedical data analysis. Herein, we propose this review by summarizing the latest research work on LLM in biomedicine. In this review, LLM techniques are first outlined. We then discuss biomedical datasets and frameworks for biomedical data analysis, followed by a detailed analysis of LLM applications in genomics, proteomics, transcriptomics, radiomics, single-cell analysis, medical texts and drug discovery. Finally, the challenges of LLM in biomedical data analysis are discussed. In summary, this review is intended for researchers interested in LLM technology and aims to help them understand and apply LLM in biomedical data analysis research.

Large Language Models (LLMs) exhibit exceptional proficiency in comprehending human language. Despite their significant success across a wide array of tasks, understanding tabular data remains a challenging task. Especially, tabular data lacks an intrinsic order of the different features (table fields), whereas LLMs take only sequential inputs. Consequently, an artificial order is imposed, the impact of which on the performance of LLMs has not yet been thoroughly investigated. Surprisingly, as discovered in this work, this artificially induced order bias dramatically influences the performance of LLMs on tasks related to tabular data. Mitigating the order bias presents a significant challenge. To address this, we propose a simple and cost-effective method, Re-Ordering Tabular feATures fOR LLM (ROTATOR-LLM), to conduct test-time compute without fine-tuning the base LLM. Aiming at optimizing the feature order of tabular data and boosting LLMs' capability to better understand the data semantics, ROTATOR-LLM re-frames the ordering problem as a feature trajectory generation task. A dynamic programming based meta-controller is trained to auto-regressively generate an individualized feature trajectory for each data instance via accumulative value estimation of the serialized feature input through the LLM's final performance metrics. Model performance is maximized by iteratively selecting features across different steps. Experimental results on multiple datasets and LLMs show close to or over 20% performance boosts via features reordered by ROTATOR-LLM against the un-ordered counterpart. Meanwhile, it outperforms stateof- the-Art tabular LLM methods with significant margin.