Yiliang Zhou

Yishu Wei, Xindi Wang, Hanley Ong et al.

Despite significant progress in applying large language models (LLMs) to the medical domain, several limitations still prevent them from practical applications. Among these are the constraints on model size and the lack of cohort-specific labeled datasets. In this work, we investigated the potential of improving a lightweight LLM, such as Llama 3.1-8B, through fine-tuning with datasets using synthetic labels. Two tasks are jointly trained by combining their respective instruction datasets. When the quality of the task-specific synthetic labels is relatively high (e.g., generated by GPT4- o), Llama 3.1-8B achieves satisfactory performance on the open-ended disease detection task, with a micro F1 score of 0.91. Conversely, when the quality of the task-relevant synthetic labels is relatively low (e.g., from the MIMIC-CXR dataset), fine-tuned Llama 3.1-8B is able to surpass its noisy teacher labels (micro F1 score of 0.67 v.s. 0.63) when calibrated against curated labels, indicating the strong inherent underlying capability of the model. These findings demonstrate the potential of fine-tuning LLMs with synthetic labels, offering a promising direction for future research on LLM specialization in the medical domain.

Yiliang Zhou, Hanley Ong, Patrick Kennedy et al.

The study examines the application of GPT-4V, a multi-modal large language model equipped with visual recognition, in detecting radiological findings from a set of 100 chest radiographs and suggests that GPT-4V is currently not ready for real-world diagnostic usage in interpreting chest radiographs.

Jingze Zhang, Jiahe Qian, Yiliang Zhou et al.

Fact-checking for health-related content is challenging due to the limited availability of annotated training data. In this study, we propose a synthetic data generation pipeline that leverages large language models (LLMs) to augment training data for health-related fact checking. In this pipeline, we summarize source documents, decompose the summaries into atomic facts, and use an LLM to construct sentence-fact entailment tables. From the entailment relations in the table, we further generate synthetic text-claim pairs with binary veracity labels. These synthetic data are then combined with the original data to fine-tune a BERT-based fact-checking model. Evaluation on two public datasets, PubHealth and SciFact, shows that our pipeline improved F1 scores by up to 0.019 and 0.049, respectively, compared to models trained only on the original data. These results highlight the effectiveness of LLM-driven synthetic data augmentation in enhancing the performance of health-related fact-checkers.

Yiliang Zhou, Abigail M. Newbury, Gongbo Zhang et al.

The fundamental process of evidence extraction and synthesis in evidence-based medicine involves extracting PICO (Population, Intervention, Comparison, and Outcome) elements from biomedical literature. However, Outcomes, being the most complex elements, are often neglected or oversimplified in existing benchmarks. To address this issue, we present EvidenceOutcomes, a novel, large, annotated corpus of clinically meaningful outcomes extracted from biomedical literature. We first developed a robust annotation guideline for extracting clinically meaningful outcomes from text through iteration and discussion with clinicians and Natural Language Processing experts. Then, three independent annotators annotated the Results and Conclusions sections of a randomly selected sample of 500 PubMed abstracts and 140 PubMed abstracts from the existing EBM-NLP corpus. This resulted in EvidenceOutcomes with high-quality annotations of an inter-rater agreement of 0.76. Additionally, our fine-tuned PubMedBERT model, applied to these 500 PubMed abstracts, achieved an F1-score of 0.69 at the entity level and 0.76 at the token level on the subset of 140 PubMed abstracts from the EBM-NLP corpus. EvidenceOutcomes can serve as a shared benchmark to develop and test future machine learning algorithms to extract clinically meaningful outcomes from biomedical abstracts.

Qiao Jin, Fangyuan Chen, Yiliang Zhou et al.

Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI models into clinical workflows.