Simon A. Lee

Zilin Jing, Vincent Jeanselme, Yuta Kobayashi et al.

Clinical events captured in Electronic Health Records (EHR) are irregularly sampled and may consist of a mixture of discrete events and numerical measurements, such as laboratory values or treatment dosages. The sequential nature of EHR, analogous to natural language, has motivated the use of next-token prediction to train prior EHR Foundation Models (FMs) over events. However, this training fails to capture the full structure of EHR. When a given event occurs must be captured, but the event value (abnormal lab) also modulates the likelihood of other clinical events. Most existing EHR FMs do not jointly model this likelihood and are unable to capture the full observation process, impacting downstream capabilities. We propose ORA, a marked time-to-event pretraining objective that jointly models event timing and associated measurements. Across multiple datasets, downstream tasks, and model backbones, this objective consistently yields more generalizable representations than next-token prediction and pretraining losses that ignore continuous measurements. Importantly, the proposed objective yields improvements beyond traditional classification evaluation, including better regression and time-to-event prediction. Beyond introducing a new family of FMs, our ablations suggest a broader takeaway: pretraining objectives that account for EHR structure are critical for expanding downstream capabilities and generalizability.

Simon A. Lee, Sujay Jain, Alex Chen et al.

In this work, we introduce the Multiple Embedding Model for EHR (MEME), an approach that serializes multimodal EHR tabular data into text using pseudo-notes, mimicking clinical text generation. This conversion not only preserves better representations of categorical data and learns contexts but also enables the effective employment of pretrained foundation models for rich feature representation. To address potential issues with context length, our framework encodes embeddings for each EHR modality separately. We demonstrate the effectiveness of MEME by applying it to several decision support tasks within the Emergency Department across multiple hospital systems. Our findings indicate that MEME outperforms traditional machine learning, EHR-specific foundation models, and general LLMs, highlighting its potential as a general and extendible EHR representation strategy.

Simon A. Lee, Timothy Lindsey

Large Language Models (LLMs) have become a pivotal research area, potentially making beneficial contributions in fields like healthcare where they can streamline automated billing and decision support. However, the frequent use of specialized coded languages like ICD-10, which are regularly updated and deviate from natural language formats, presents potential challenges for LLMs in creating accurate and meaningful latent representations. This raises concerns among healthcare professionals about potential inaccuracies or ``hallucinations" that could result in the direct impact of a patient. Therefore, this study evaluates whether large language models (LLMs) are aware of medical code ontologies and can accurately generate names from these codes. We assess the capabilities and limitations of both general and biomedical-specific generative models, such as GPT, LLaMA-2, and Meditron, focusing on their proficiency with domain-specific terminologies. While the results indicate that LLMs struggle with coded language, we offer insights on how to adapt these models to reason more effectively.

Simon A. Lee, Anthony Wu, Jeffrey N. Chiang

We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at producing semantically rich representations tailored for long context tasks. We validate this both by analyzing its pretrained weights and through empirical evaluation on a comprehensive suite of clinical NLP benchmarks.

Weizhi Zhang, Zechen Li, Hamid Palangi et al.

The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access. However, large-scale clinical deployment remains constrained by an open-ended evaluation bottleneck: physician annotation is reliable but costly and unscalable, while LLM-as-a-judge evaluators are scalable but subjective, inconsistent, and sometimes clinically misaligned. We introduce RubricsTree, a scalable evaluation framework with an expert-aligned hierarchical taxonomy of over 100 atomic, clinically-verifiable Boolean rubrics, evolving from the insights of 4,000 real user queries through an iterative human-in-the-loop curation protocol with an expertise panel led by an experienced physician. A context-aware adaptive router activates only the relevant auto-weighted rubric subset per query, providing the throughput needed for scalable evaluation with expert-aligned quality. Through a systematic meta-evaluation, we show that RubricsTree (i) substantially exceeds a strong large-scale evaluation baseline in expert alignment on challenging open-ended queries; (ii) reliably penalizes contextually degraded responses; and (iii) when used as structured instructions, text feedback, or training rewards for performance optimization, yields up to ~66% relative gains on HealthBench for Gemini, GPT, and Qwen model families. RubricsTree thus provides a scalable, auditable, and evolving evaluation infrastructure required for the continuous optimization of product-level personal healthcare AI.

Simon A. Lee, John Lee, Jeffrey N. Chiang

In this study, we introduce FEET, a standardized protocol designed to guide the development and benchmarking of foundation models. While numerous benchmark datasets exist for evaluating these models, we propose a structured evaluation protocol across three distinct scenarios to gain a comprehensive understanding of their practical performance. We define three primary use cases: frozen embeddings, few-shot embeddings, and fully fine-tuned embeddings. Each scenario is detailed and illustrated through two case studies: one in sentiment analysis and another in the medical domain, demonstrating how these evaluations provide a thorough assessment of foundation models' effectiveness in research applications. We recommend this protocol as a standard for future research aimed at advancing representation learning models.

Kyoka Ono, Simon A. Lee

Recent research has explored how Language Models (LMs) can be used for feature representation and prediction in tabular machine learning tasks. This involves employing text serialization and supervised fine-tuning (SFT) techniques. Despite the simplicity of these techniques, significant gaps remain in our understanding of the applicability and reliability of LMs in this context. Our study assesses how emerging LM technologies compare with traditional paradigms in tabular machine learning and evaluates the feasibility of adopting similar approaches with these advanced technologies. At the data level, we investigate various methods of data representation and curation of serialized tabular data, exploring their impact on prediction performance. At the classification level, we examine whether text serialization combined with LMs enhances performance on tabular datasets (e.g. class imbalance, distribution shift, biases, and high dimensionality), and assess whether this method represents a state-of-the-art (SOTA) approach for addressing tabular machine learning challenges. Our findings reveal current pre-trained models should not replace conventional approaches.