An official website of the United States government
Estimating Clinical Benefit of a Novel Passive Othopedic Implant by Relating Objective Measures to Clinical Data
More Like this
-
Recent advances in Large Language Models (LLMs) have led to remarkable progresses in medical consultation.However, existing medical LLMs overlook the essential role of Electronic Health Records (EHR) and focus primarily on diagnosis recommendation, limiting their clinical applicability. We propose DiaLLM, the first medical LLM that integrates heterogeneous EHR data into clinically grounded dialogues, enabling clinical test recommendation, result interpretation, and diagnosis prediction to better align with real-world medical practice. To construct clinically grounded dialogues from EHR, we design a Clinical Test Reference (CTR) strategy that maps each clinical code to its corresponding description and classifies test results as “normal” or “abnormal”. Additionally, DiaLLM employs a reinforcement learning framework for evidence acquisition and automated diagnosis. To handle the large action space, we introduce a reject sampling strategy to reduce redundancy and improve exploration efficiency. Furthermore, a confirmation reward and a class-sensitive diagnosis reward are designed to guide accurate diagnosis prediction.Extensive experimental results demonstrate that DiaLLM outperforms baselines in clinical test recommendation and diagnosis prediction. Our code is available at Github.more » « less
-
null (Ed.)Fast and accurate interrogation of complex samples containing diseased cells or pathogens is important to make informed decisions on clinical and public health issues. Inertial microfluidics has been increasingly employed for such investigations to isolate target bioparticles from liquid samples with size and/or deformability-based manipulation. This phenomenon is especially useful for the clinic, owing to its rapid, label-free nature of target enrichment that enables further down- stream assays. Inertial microfluidics leverages the principle of inertial focusing, which relies on the balance of inertial and viscous forces on particles to align them into size-dependent laminar stream- lines. Several distinct microfluidic channel geometries (e.g., straight, curved, spiral, contraction-ex- pansion array) have been optimized to achieve inertial focusing for a variety of purposes, including particle purification and enrichment, solution exchange, and particle alignment for on-chip assays. In this review, we will discuss how inertial microfluidics technology has contributed to improving accuracy of various assays to provide clinically relevant information. This comprehensive review expands upon studies examining both endogenous and exogenous targets from real-world samples, highlights notable hybrid devices with dual functions, and comments on the evolving outlook of the field.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
