A study on ECG biometrics for authentication and sensitive data security, showing promise for robustness under physiological and temporal variations. This could be relevant to AI-powered healthcare applications, but is not directly related to AI agent security or technology.

A new LLM framework, CliniCIRCA, is proposed for constructing longitudinal mental health patient journeys from raw EHR narratives. It introduces a multi-stage approach for temporal event classification and summarization, achieving improved results compared to zero- and few-shot prompting.

Researchers developed a multimodal information system to improve access to medical knowledge from case reports, leveraging structured summaries, medical images, and biomedical named entities. This system can aid junior clinicians in retrieving relevant cases and diagnosing rare diseases.

Researchers proposed a new CT reconstruction framework, Dose-Aware Cold Diffusion (DACD), which models radiation dose as a continuous latent factor and improves generalization across dose levels. This development is relevant to AI agents in medical imaging, particularly in areas like healthcare and medical diagnosis.

The paper proposes TERN, a machine learning model for forecasting influenza epidemics. It uses a delta-rule fast-weight memory with decay and online adaptation to improve forecasting. Results show TERN outperforms existing models on benchmark datasets. This is relevant to AI agents as it demonstrates a new approach to forecasting in a specific domain, which may be of interest to researchers and developers working on AI applications in healthcare or epidemiology.

Researchers introduced information set emulation, a method to attach causal certificates to AI-derived EHR features, addressing the lack of admissibility for causal inference. This approach provides auditable evidence for proposed causal roles and resolves ambiguity in extracted features.