The recent shift toward the Health Level Seven Fast Healthcare Interoperability Resources (HL7 FHIR) standard opens a new frontier for clinical AI, demanding LLM agents to navigate complex, resource-based data models instead of conventional structured health data. However, existing benchmarks have lagged behind this transition, lacking the realism needed to evaluate recent LLMs on interoperable clinical data. To bridge this gap, we introduce FHIR-AgentBench--a benchmark that grounds 2,931 real-world clinical questions in the HL7 FHIR standard. Using this benchmark, we systematically evaluate agentic frameworks, comparing different data retrieval strategies (direct FHIR API calls vs. specialized tools), interaction patterns (single-turn vs. multi-turn), and reasoning strategies (natural language vs. code generation). Our experiments highlight the practical challenges of retrieving data from intricate FHIR resources and the difficulty of reasoning over them--both of which critically affect question answering performance.

Realizing personalized medicine at scale calls for methods that distill insights from longitudinal patient journeys, which can be viewed as a sequence of medical events. Foundation models pretrained on large-scale medical event data represent a promising direction for scaling real-world evidence generation and generalizing to diverse downstream tasks. Using Epic Cosmos, a dataset with medical events from de-identified longitudinal health records for 16.3 billion encounters over 300 million unique patient records from 310 health systems, we introduce the Curiosity models, a family of decoder-only transformer models pretrained on 118 million patients representing 115 billion discrete medical events (151 billion tokens). We present the largest scaling-law study of medical event data, establishing a methodology for pretraining and revealing power-law scaling relationships for compute, tokens, and model size. Consequently, we pretrained a series of compute-optimal models with up to 1 billion parameters. Conditioned on a patient's real-world history, Curiosity autoregressively predicts the next medical event to simulate patient health timelines. We studied 78 real-world tasks, including diagnosis prediction, disease prognosis, and healthcare operations. Remarkably for a foundation model with generic pretraining and simulation-based inference, Curiosity generally outperformed or matched task-specific supervised models on these tasks, without requiring task-specific fine-tuning or few-shot examples. Curiosity's predictive power consistently improves as the model and pretraining scale. Our results show that Curiosity, a generative medical event foundation model, can effectively capture complex clinical dynamics, providing an extensible and generalizable framework to support clinical decision-making, streamline healthcare operations, and improve patient outcomes.

(Figure 2).

(Figure 2).

Accurate diagnosis with medical large language models is hindered by knowledge gaps and hallucinations. Retrieval and tool-augmented methods help, but their impact is limited by weak use of external knowledge and poor feedback-reasoning traceability. To address these challenges, We introduce Deep-DxSearch, an agentic RAG system trained end-to-end with reinforcement learning (RL) that enables steer tracebale retrieval-augmented reasoning for medical diagnosis. In Deep-DxSearch, we first construct a large-scale medical retrieval corpus comprising patient records and reliable medical knowledge sources to support retrieval-aware reasoning across diagnostic scenarios. More crutially, we frame the LLM as the core agent and the retrieval corpus as its environment, using tailored rewards on format, retrieval, reasoning structure, and diagnostic accuracy, thereby evolving the agentic RAG policy from large-scale data through RL. Experiments demonstrate that our end-to-end agentic RL training framework consistently outperforms prompt-engineering and training-free RAG approaches across multiple data centers. After training, Deep-DxSearch achieves substantial gains in diagnostic accuracy, surpassing strong diagnostic baselines such as GPT-4o, DeepSeek-R1, and other medical-specific frameworks for both common and rare disease diagnosis under in-distribution and out-of-distribution settings. Moreover, ablation studies on reward design and retrieval corpus components confirm their critical roles, underscoring the uniqueness and effectiveness of our approach compared with traditional implementations. Finally, case studies and interpretability analyses highlight improvements in Deep-DxSearch's diagnostic policy, providing deeper insight into its performance gains and supporting clinicians in delivering more reliable and precise preliminary diagnoses. See https://github.com/MAGIC-AI4Med/Deep-DxSearch.

--Access to real-world medical data is often restricted due to privacy regulations, posing a significant barrier to the advancement of healthcare research. Synthetic data offers a promising alternative; however, generating realistic, clinically valid, and privacy-conscious records remains a major challenge. Recent advancements in Large Language Models (LLMs) offer new opportunities for structured data generation; however, existing approaches frequently lack systematic prompting strategies and comprehensive, multi-dimensional evaluation frameworks. In this paper, we present SynLLM, a modular framework for generating high-quality synthetic medical tabular data using 20 state-of-the-art open-source LLMs, including LLaMA, Mistral, and GPT variants, guided by structured prompts. We propose four distinct prompt types, ranging from example-driven to rule-based constraints, that encode schema, metadata, and domain knowledge to control generation without model fine-tuning. Our framework features a comprehensive evaluation pipeline that rigorously assesses generated data across statistical fidelity, clinical consistency, and privacy preservation. We evaluate SynLLM across three public medical datasets, including Diabetes, Cirrhosis, and Stroke, using 20 open-source LLMs. Our results show that prompt engineering significantly impacts data quality and privacy risk, with rule-based prompts achieving the best privacy-quality balance. SynLLM establishes that, when guided by well-designed prompts and evaluated with robust, multi-metric criteria, LLMs can generate synthetic medical data that is both clinically plausible and privacy-aware, paving the way for safer and more effective data sharing in healthcare research. Access to real-world medical data is frequently restricted due to privacy regulations, ethical constraints, and institutional barriers, posing a significant challenge for the development of AI-driven healthcare solutions. While data protection laws such as the Health Insurance Portability and Accountability Act (HIP AA) [11] and the General Data Protection Regulation (GDPR) [37] are essential for safeguarding patient confidentiality, they often hinder the availability of data for clinical model development and research.

The design of medical systems for remote, resource-limited environments faces persistent challenges due to poor interoperability, lack of offline support, and dependency on costly infrastructure. Many existing digital health solutions neglect these constraints, limiting their effectiveness for frontline health workers in underserved regions. This paper presents a portable, edge-enabled Electronic Health Record platform optimized for offline-first operation, secure patient data management, and modular diagnostic integration. Running on small-form factor embedded devices, it provides AES-256 encrypted local storage with optional cloud synchronization for interoperability. As a use case, we integrated a non-invasive anemia screening module leveraging fingernail pallor analysis. Trained on 250 patient cases (27\% anemia prevalence) with KDE-balanced data, the Random Forest model achieved a test RMSE of 1.969 g/dL and MAE of 1.490 g/dL. A severity-based model reached 79.2\% sensitivity. To optimize performance, a YOLOv8n-based nail bed detector was quantized to INT8, reducing inference latency from 46.96 ms to 21.50 ms while maintaining mAP@0.5 at 0.995. The system emphasizes low-cost deployment, modularity, and data privacy compliance (HIPAA/GDPR), addressing critical barriers to digital health adoption in disconnected settings. Our work demonstrates a scalable approach to enhance portable health information systems and support frontline healthcare in underserved regions.

Migraine is a common but complex neurological disorder that doubles the lifetime risk of cryptogenic stroke (CS). However, this relationship remains poorly characterized, and few clinical guidelines exist to reduce this associated risk. We therefore propose a data-driven approach to extract probabilistically-independent sources from electronic health record (EHR) data and create a 10-year risk-predictive model for CS in migraine patients. These sources represent external latent variables acting on the causal graph constructed from the EHR data and approximate root causes of CS in our population. A random forest model trained on patient expressions of these sources demonstrated good accuracy (ROC 0.771) and identified the top 10 most predictive sources of CS in migraine patients. These sources revealed that pharmacologic interventions were the most important factor in minimizing CS risk in our population and identified a factor related to allergic rhinitis as a potential causative source of CS in migraine patients.

Generating realistic synthetic electronic health records (EHRs) holds tremendous promise for accelerating healthcare research, facilitating AI model development and enhancing patient privacy. However, existing generative methods typically treat EHRs as flat sequences of discrete medical codes. This approach overlooks two critical aspects: the inherent hierarchical organization of clinical coding systems and the rich semantic context provided by code descriptions. Consequently, synthetic patient sequences often lack high clinical fidelity and have limited utility in downstream clinical tasks. In this paper, we propose the Hierarchy- and Semantics-Guided Transformer (HiSGT), a novel framework that leverages both hierarchical and semantic information for the generative process. HiSGT constructs a hierarchical graph to encode parent-child and sibling relationships among clinical codes and employs a graph neural network to derive hierarchy-aware embeddings. These are then fused with semantic embeddings extracted from a pre-trained clinical language model (e.g., ClinicalBERT), enabling the Transformer-based generator to more accurately model the nuanced clinical patterns inherent in real EHRs. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that HiSGT significantly improves the statistical alignment of synthetic data with real patient records, as well as supports robust downstream applications such as chronic disease classification. By addressing the limitations of conventional raw code-based generative models, HiSGT represents a significant step toward clinically high-fidelity synthetic data generation and a general paradigm suitable for interpretable medical code representation, offering valuable applications in data augmentation and privacy-preserving healthcare analytics.

Alzheimer's Disease (AD) early detection is critical for enabling timely intervention and improving patient outcomes. This paper presents a DMV framework using Llama3-70B and GPT-4o as embedding models to analyze clinical notes and predict a continuous risk score associated with early AD onset. Framing the task as a regression problem, we model the relationship between linguistic features in clinical notes (inputs) and a target variable (data value) that answers specific questions related to AD risk within certain topic categories. By leveraging a multi-faceted feature set that includes geolocation data, we capture additional environmental context potentially linked to AD. Our results demonstrate that the integration of the geolocation information significantly decreases the error of predicting early AD risk scores over prior models by 28.57% (Llama3-70B) and 33.47% (GPT4-o). Our findings suggest that this combined approach can enhance the predictive accuracy of AD risk assessment, supporting early diagnosis and intervention in clinical settings. Additionally, the framework's ability to incorporate geolocation data provides a more comprehensive risk assessment model that could help healthcare providers better understand and address environmental factors contributing to AD development.