Xiaochen Zheng

Yinghao Zhu, Junyi Gao, Zixiang Wang et al.

Large Language Models (LLMs) are increasingly deployed in medicine. However, their utility in non-generative clinical prediction, often presumed inferior to specialized models, remains under-evaluated, leading to ongoing debate within the field and potential for misuse, misunderstanding, or over-reliance due to a lack of systematic benchmarking. Our ClinicRealm study addresses this by benchmarking 15 GPT-style LLMs, 5 BERT-style models, and 11 traditional methods on unstructured clinical notes and structured Electronic Health Records (EHR), while also assessing their reasoning, reliability, and fairness. Key findings reveal a significant shift: for clinical note predictions, leading LLMs (e.g., DeepSeek-V3.1-Think, GPT-5) in zero-shot settings now decisively outperform finetuned BERT models. On structured EHRs, while specialized models excel with ample data, advanced LLMs (e.g., GPT-5, DeepSeek-V3.1-Think) show potent zero-shot capabilities, often surpassing conventional models in data-scarce settings. Notably, leading open-source LLMs can match or exceed proprietary counterparts. These results provide compelling evidence that modern LLMs are competitive tools for non-generative clinical prediction, particularly with unstructured text and offering data-efficient structured data options, thus necessitating a re-evaluation of model selection strategies. This research should serve as an important insight for medical informaticists, AI developers, and clinical researchers, potentially prompting a reassessment of current assumptions and inspiring new approaches to LLM application in predictive healthcare.

Xiaochen Zheng, Zhiwen Jiang, Melanie Guerard et al.

Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic targets. This process is inherently iterative and expert-driven, posing challenges in scalability and reproducibility. We present TSAssistant, a multi-agent framework designed to support TSA report drafting through a modular, section-based, and human-in-the-loop paradigm. The framework decomposes report generation into a coordinated pipeline of specialised subagents, each targeting a single TSA section. Specialised subagents retrieve structured and unstructured data as well as literature evidence from curated biomedical sources through standardised tool interfaces, producing individually citable, evidence-grounded sections. Agent behaviour is governed by a hierarchical instruction architecture comprising system prompts, domain-specific skill modules, and runtime user instructions. A key feature is an interactive refinement loop in which users may manually edit sections, append new information, upload additional sources, or re-invoke agents to revise specific sections, with the system maintaining conversational memory across iterations. TSAssistant is designed to reduce the mechanical burden of evidence synthesis and report drafting, supporting a hybrid model in which agentic AI augments evidence synthesis while toxicologists retain final decision authority.

Yinghao Zhu, Ziyi He, Haoran Hu et al.

The rapid advancement of Large Language Models (LLMs) has stimulated interest in multi-agent collaboration for addressing complex medical tasks. However, the practical advantages of multi-agent collaboration approaches remain insufficiently understood. Existing evaluations often lack generalizability, failing to cover diverse tasks reflective of real-world clinical practice, and frequently omit rigorous comparisons against both single-LLM-based and established conventional methods. To address this critical gap, we introduce MedAgentBoard, a comprehensive benchmark for the systematic evaluation of multi-agent collaboration, single-LLM, and conventional approaches. MedAgentBoard encompasses four diverse medical task categories: (1) medical (visual) question answering, (2) lay summary generation, (3) structured Electronic Health Record (EHR) predictive modeling, and (4) clinical workflow automation, across text, medical images, and structured EHR data. Our extensive experiments reveal a nuanced landscape: while multi-agent collaboration demonstrates benefits in specific scenarios, such as enhancing task completeness in clinical workflow automation, it does not consistently outperform advanced single LLMs (e.g., in textual medical QA) or, critically, specialized conventional methods that generally maintain better performance in tasks like medical VQA and EHR-based prediction. MedAgentBoard offers a vital resource and actionable insights, emphasizing the necessity of a task-specific, evidence-based approach to selecting and developing AI solutions in medicine. It underscores that the inherent complexity and overhead of multi-agent collaboration must be carefully weighed against tangible performance gains. All code, datasets, detailed prompts, and experimental results are open-sourced at https://medagentboard.netlify.app/.

Xiaochen Zheng

Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on supervised learning and thus require vast amounts of training data. Due to their scarcity and minuscule size, annotating animals in aerial imagery is a highly tedious process. In this project, we present a methodology to reduce the amount of required training data by resorting to self-supervised pretraining. In detail, we examine a combination of recent contrastive learning methodologies like Momentum Contrast (MoCo) and Cross-Level Instance-Group Discrimination (CLD) to condition our model on the aerial images without the requirement for labels. We show that a combination of MoCo, CLD, and geometric augmentations outperforms conventional models pretrained on ImageNet by a large margin. Meanwhile, strategies for smoothing label or prediction distribution in supervised learning have been proven useful in preventing the model from overfitting. We combine the self-supervised contrastive models with image mixup strategies and find that it is useful for learning more robust visual representations. Crucially, our methods still yield favorable results even if we reduce the number of training animals to just 10%, at which point our best model scores double the recall of the baseline at similar precision. This effectively allows reducing the number of required annotations to a fraction while still being able to train high-accuracy models in such highly challenging settings.