Search

Large Language Models (LLMs) show potential for medical applications but often lack specialized clinical knowledge. Retrieval Augmented Generation (RAG) allows customization with domain-specific information, making it suitable for healthcare. This study evaluates the accuracy, consistency, and safety of RAG models in determining fitness for surgery and providing preoperative instructions. We developed LLM-RAG models using 35 local and 23 international preoperative guidelines and tested them against human-generated responses. A total of 3,682 responses were evaluated. Clinical documents were processed using Llamaindex, and 10 LLMs, including GPT3.5, GPT4, and Claude-3, were assessed. Fourteen clinical scenarios were analyzed, focusing on seven aspects of preoperative instructions. Established guidelines and expert judgment were used to determine correct responses, with human-generated answers serving as comparisons. The LLM-RAG models generated responses within 20 seconds, significantly faster than clinicians (10 minutes). The GPT4 LLM-RAG model achieved the highest accuracy (96.4% vs. 86.6%, p=0.016), with no hallucinations and producing correct instructions comparable to clinicians. Results were consistent across both local and international guidelines. This study demonstrates the potential of LLM-RAG models for preoperative healthcare tasks, highlighting their efficiency, scalability, and reliability., Comment: arXiv admin note: substantial text overlap with arXiv:2402.01733

New privacy concerns arise with chatbots on group messaging platforms. Chatbots may access information beyond their intended functionalities, such as messages unintended for chatbots or sender's identities. Chatbot operators may exploit such information to infer personal information and link users across groups, potentially leading to personal data breaches, pervasive tracking, and targeted advertising. Our analysis of conversation datasets shows that (1) chatbots often access far more messages than needed, and (2) when a user joins a new group with chatbots, there is a 3.4% chance that at least one of the chatbots can recognize and associate the user with their previous interactions in other groups. Although state-of-the-art group messaging protocols provide robust end-to-end security and some platforms have implemented policies to limit chatbot access, no platforms successfully combine these features. This paper introduces SnoopGuard, a secure group messaging protocol that ensures user privacy against chatbots while maintaining strong end-to-end security. Our method offers selective message access, preventing chatbots from accessing unrelated messages, and ensures sender anonymity within the group. SnoopGuard achieves $O(\log n + m)$ message-sending complexity for a group of $n$ users and $m$ chatbots, compared to $O(\log(n + m))$ in state-of-the-art protocols, with acceptable overhead for enhanced privacy. Our prototype implementation shows that sending a message in a group of 50 users and 10 chatbots takes about 30 milliseconds when integrated with Message Layer Security (MLS)., Comment: 18 pages, 5 figures

Let $K$ be a simplicial complex, and let $\Delta_i^{up}(K)$ be the $i$-th up normalized Laplacian of $K$. Horak and Jost showed that the largest eigenvalue of $\Delta_i^{up}(K)$ is at most $i+2$, and characterized the equality case by the orientable or non-orientable circuits. In this paper, by using the balancedness of signed graphs, we show that $\Delta_i^{up}(K)$ has an eigenvalue $i+2$ if and only if $K$ has an $(i+1)$-path connected component $K'$ such that the $i$-th signed incidence graph $B_i(K')$ is balanced, which implies Horak and Jost's characterization. We also characterize the multiplicity of $i+2$ as an eigenvalue of $\Delta_i^{up}(K)$, which generalizes the corresponding result in graph case. Finally we gave some classes of infinitely many simplicial complexes $K$ with $\Delta_i^{up}(K)$ having an eigenvalue $i+2$ by using wedge, Cartesian product and duplication of motifs., Comment: arXiv admin note: substantial text overlap with arXiv:2405.19078

We demonstrate for the first time that the nonlinear saturation of neoclassical tearing modes (NTMs) can be found directly using a variational principle based on Taylor relaxation, without needing to simulate the intermediate, resistivity-dependent dynamics. As in previous investigations of classical tearing mode saturation (Loizu et al. 2020; Loizu & Bonfiglio 2023), we make use of SPEC (Hudson et al. 2012), an equilibrium solver based on the variational principle of the Multi-Region relaxed MHD, featuring stepped pressure profiles and arbitrary magnetic topology. We work in slab geometry and employ a simple bootstrap current model $J_\textrm{bs} = C \nabla p$ to study the bootstrap-driven tearing modes, scanning over the asymptotic matching parameter $\Delta'$ and the bootstrap current strength. Saturated island widths produced by SPEC agree well with the predictions of an initial value resistive MHD code (Huang & Bhattacharjee 2016) while being orders of magnitude faster to calculate. Additionally, we observe good agreement with a simple analytical Modified Rutherford Equation, without requiring any fitting coefficients. The match is obtained for both linearly unstable classical tearing modes in the presence of bootstrap current, and neoclassical tearing modes, which are linearly stable but nonlinear-unstable due to the effects of the bootstrap current, Comment: Submitted to PPCF

Plasmoid instability accelerates reconnection in collisional plasmas by transforming a laminar reconnection layer into numerous plasmoids connected by secondary current sheets in two dimensions (2D) and by fostering self-generated turbulent reconnection in three dimensions (3D). In large-scale astrophysical and space systems, plasmoid instability likely initiates in the collisional regime but may transition into the collisionless regime as the fragmentation of the current sheet progresses toward kinetic scales. Hall MHD models are widely regarded as a simplified yet effective representation of the transition from collisional to collisionless reconnection. However, plasmoid instability in 2D Hall MHD simulations often leads to a single-X-line reconnection configuration, which significantly differs from fully kinetic particle-in-cell simulation results. This study shows that single-X-line reconnection is less likely to occur in 3D compared to 2D. Moreover, depending on the Lundquist number and the ratio between the system size and the kinetic scale, Hall MHD can also realize 3D self-generated turbulent reconnection. We analyze the features of the self-generated turbulent state, including the energy power spectra and the scale dependence of turbulent eddy anisotropy.

Importance: We introduce a novel Retrieval Augmented Generation (RAG)-Large Language Model (LLM) framework as a Clinical Decision Support Systems (CDSS) to support safe medication prescription. Objective: To evaluate the efficacy of LLM-based CDSS in correctly identifying medication errors in different patient case vignettes from diverse medical and surgical sub-disciplines, against a human expert panel derived ground truth. We compared performance for under 2 different CDSS practical healthcare integration modalities: LLM-based CDSS alone (fully autonomous mode) vs junior pharmacist + LLM-based CDSS (co-pilot, assistive mode). Design, Setting, and Participants: Utilizing a RAG model with state-of-the-art medically-related LLMs (GPT-4, Gemini Pro 1.0 and Med-PaLM 2), this study used 61 prescribing error scenarios embedded into 23 complex clinical vignettes across 12 different medical and surgical specialties. A multidisciplinary expert panel assessed these cases for Drug-Related Problems (DRPs) using the PCNE classification and graded severity / potential for harm using revised NCC MERP medication error index. We compared. Results RAG-LLM performed better compared to LLM alone. When employed in a co-pilot mode, accuracy, recall, and F1 scores were optimized, indicating effectiveness in identifying moderate to severe DRPs. The accuracy of DRP detection with RAG-LLM improved in several categories but at the expense of lower precision. Conclusions This study established that a RAG-LLM based CDSS significantly boosts the accuracy of medication error identification when used alongside junior pharmacists (co-pilot), with notable improvements in detecting severe DRPs. This study also illuminates the comparative performance of current state-of-the-art LLMs in RAG-based CDSS systems.

Purpose: Large Language Models (LLMs) hold significant promise for medical applications. Retrieval Augmented Generation (RAG) emerges as a promising approach for customizing domain knowledge in LLMs. This case study presents the development and evaluation of an LLM-RAG pipeline tailored for healthcare, focusing specifically on preoperative medicine. Methods: We developed an LLM-RAG model using 35 preoperative guidelines and tested it against human-generated responses, with a total of 1260 responses evaluated. The RAG process involved converting clinical documents into text using Python-based frameworks like LangChain and Llamaindex, and processing these texts into chunks for embedding and retrieval. Vector storage techniques and selected embedding models to optimize data retrieval, using Pinecone for vector storage with a dimensionality of 1536 and cosine similarity for loss metrics. Human-generated answers, provided by junior doctors, were used as a comparison. Results: The LLM-RAG model generated answers within an average of 15-20 seconds, significantly faster than the 10 minutes typically required by humans. Among the basic LLMs, GPT4.0 exhibited the best accuracy of 80.1%. This accuracy was further increased to 91.4% when the model was enhanced with RAG. Compared to the human-generated instructions, which had an accuracy of 86.3%, the performance of the GPT4.0 RAG model demonstrated non-inferiority (p=0.610). Conclusions: In this case study, we demonstrated a LLM-RAG model for healthcare implementation. The pipeline shows the advantages of grounded knowledge, upgradability, and scalability as important aspects of healthcare LLM deployment., Comment: NA

In this paper, by the representation theory of symmetric group, we give a decomposition of the Laplace operator (in matrix form) of a covering simplicial complex into the direct sum of some matrices, including the Laplace operator of the underlying simplicial complex. So, the spectrum of a covering simplicial complex can be expressed into a union of the spectrum of the underlying simplicial complex and the spectra of some other matrices, which implies a result of Horak and Jost. In particular, we show that the spectrum of a $2$-fold covering simplicial complex is the union the that of the underlying simplicial complex and that of an incidence-signed simplicial complex, which is an analog of Bilu and Linial's result on graphs. Finally we show that the dimension of the cohomology group of a covering simplicial complex is greater than or equal to that of the underlying simplicial complex.

Additive manufacturing (AM) technology is undergoing rapid development and emerging as an advanced technique that can fabricate complex near-net shaped and light-weight metallic parts with acceptable strength and fatigue performance. A number of studies have indicated that the strength or other mechanical properties of AM metals are comparable or even superior to that of conventionally manufactured metals, but the fatigue performance is still a thorny problem that may hinder the replacement of currently used metallic components by AM counterparts when the cyclic loading and thus fatigue failure dominates. This article reviews the state-of-art published data on the fatigue properties of AM metals, principally including $S$--$N$ data and fatigue crack growth data. The AM techniques utilized to generate samples in this review include powder bed fusion (e.g., EBM, SLM, DMLS) and directed energy deposition (e.g., LENS, WAAM). Further, the fatigue properties of AM metallic materials that involve titanium alloys, aluminum alloys, stainless steel, nickel-based alloys, magnesium alloys, and high entropy alloys, are systematically overviewed. In addition, summary figures or tables for the published data on fatigue properties are presented for the above metals, the AM techniques, and the influencing factors (manufacturing parameters, e.g., built orientation, processing parameter, and post-processing). The effects of build direction, particle, geometry, manufacturing parameters, post-processing, and heat-treatment on fatigue properties, when available, are provided and discussed. The fatigue performance and main factors affecting the fatigue behavior of AM metals are finally compared and critically analyzed, thus potentially providing valuable guidance for improving the fatigue performance of AM metals., Comment: 201 pages, 154 figures

In this paper we investigate Ramanujan hypergraphs by using hypergraph coverings. We first show that the spectrum of a $k$-fold covering $\bar{H}$ of a connected hypergraph $H$ contains the spectrum of $H$, and that it is the union of the spectrum of $H$ and the spectrum of an incidence-signed hypergraph with $H$ as underlying hypergraph if $k=2$, which generalizes Bilu-Linial result on graph coverings. We give a lower bound for the second largest eigenvalue of a $d$-regular hypergraph by universal cover, which generalizes Alon-Boppana bound on $d$-regular graphs and Feng-Li bound on $(d,r)$-regular hypergraphs. By using interlacing family of polynomials, we prove that every $(d,r)$-regular hypergraph has a right-sided Ramanujan $2$-covering, and has a left-sided Ramanujan $2$-covering if the roots of the matching polynomial of its incident graph satisfy some condition. By Ramanujan $2$-coverings, we prove the existence of some families of infinite many left-sided or right-sided $(d,r)$-regular Ramanujan hypergraphs under certain conditions on $d$ and $r$.

Origami-inspired robots with multiple advantages, such as being lightweight, requiring less assembly, and exhibiting exceptional deformability, have received substantial and sustained attention. However, the existing origami-inspired robots are usually of limited functionalities and developing feature-rich robots is very challenging. Here, we report an origami-wheeled robot (OriWheelBot) with variable width and outstanding sand walking versatility. The OriWheelBot's ability to adjust wheel width over obstacles is achieved by origami wheels made of Miura origami. An improved version, called iOriWheelBot, is also developed to automatically judge the width of the obstacles. Three actions, namely direct pass, variable width pass, and direct return, will be carried out depending on the width of the channel between the obstacles. We have identified two motion mechanisms, i.e., sand-digging and sand-pushing, with the latter being more conducive to walking on the sand. We have systematically examined numerous sand walking characteristics, including carrying loads, climbing a slope, walking on a slope, and navigating sand pits, small rocks, and sand traps. The OriWheelBot can change its width by 40%, has a loading-carrying ratio of 66.7% on flat sand and can climb a 17-degree sand incline. The OriWheelBot can be useful for planetary subsurface exploration and disaster area rescue., Comment: 23 papes, 7 figures