Background Traditional Chinese Medicine (TCM) rheumatology presents unique challenges for AI-assisted clinical decision support, as the diagnostic process relies heavily on tacit knowledge and individualized reasoning. While Large Language Models (LLMs) have shown promise in medical applications, they remain limited by hallucination risks and inability to replicate expert TCM reasoning. Retrieval-Augmented Generation (RAG) offers a potential solution, yet its application to complex TCM dialectical reasoning remains underexplored. Methods We developed TCM-CoT-RAG, a hybrid framework combining RAG with Chain-of-Thought (CoT) prompting, grounded in 1,700 expert-curated clinical cases (1,600 for RAG retrieval; 100 for evaluation, including 50 for blinded expert review by three senior TCM rheumatologists). Deployed on Alibaba Cloud, the five system leverages state-of-the-art LLMs (DeepSeek-V3, Qwen3-235B) under a human-in-the-loop paradigm. We designed a dual-tier evaluation: (1) Objective extraction tasks (Task 1–2) quantified using F1-scores; (2) Generative tasks (Task 3–5) assessed using BERTScore. Two senior TCM rheumatologists (≥15 years clinical experience) blindly assessed model outputs, and a senior chief expert quantified consistency between model predictions and ground truth (GT). Comprehensive ablation studies (S1-S4, S-Skip) isolated the contributions of each CoT module. Results TCM-CoT-RAG substantially improved diagnostic accuracy across five LLMs. DeepSeek-V3 with full-chain CoT-RAG achieved Entity F1 of 44.89% (+16.45% over baseline) and Formula F1 of 32.13% (+8.74% over baseline), with BERTScore of 0.81 indicating strong semantic alignment with expert reasoning. Ablation confirmed that the complete CoT pipeline was essential—removing any reasoning module caused performance collapse below the zero-shot baseline. Two independent experts validated clinical utility (Cohen’s κ > 0.7). DeepSeek-V3 achieved the highest ground-truth consistency at 81.6%, and consistency metrics were quantified by the third expert holding the most senior professional title. Conclusion This proof-of-concept framework demonstrates the potential of RAG-enhanced CoT reasoning to improve diagnostic consistency in TCM, objectifying the Symptom-Diagnosis-Prescription pipeline. It is important to note that this system is designed as an AI-assisted clinical decision-support tool. All recommendations require validation by qualified TCM practitioners before clinical application.
Abstract Software requirement documents—natural-language specifications that define a system’s entities, rules, processes, and interfaces—remain the core knowledge artifact in enterprise software development. Yet they remain inaccessible to automated tooling: downstream tasks like test generation, code scaffolding, compliance checking, and AI-assisted development cannot directly process unstructured prose. We present DKSE (Domain Knowledge Structuring Engine), a tool that automatically converts requirement documents into machine-readable structured ontologies organized around six core asset types: entities, relations, rules, processes, APIs, and dictionaries. DKSE uses an LLM-guided extraction pipeline that accepts multi-format inputs (DOCX, PDF, HTML), outputs YAML-encoded ontologies with full provenance tracing back to source sections, and includes built-in quality assurance tooling for validation, version diffing, and probe generation. In a case study across four banking sub-domains, we ran DKSE on six requirement documents totaling roughly 800,000 Chinese characters. It extracted 3,439 structured assets: 215 entities, 1,227 rules, 739 relations, 182 processes, 482 dictionaries, and 594 APIs. Expert review confirmed full functional-module coverage, with 96% of a stratified sample rated fully accurate and zero hallucinated assets. We validate DKSE’s practical value through three downstream use cases: automated benchmark generation (1,214 machine-graded probes), domain-specific LLM training corpus construction, and knowledge graph ingestion for retrieval-augmented generation. DKSE is built in Rust (~8,000 lines of code) and shipped as a CLI tool with an accompanying web interface. We position this work as a proof-of-concept within a single industry (Chinese banking), not a general-purpose validation. Quantitative evaluation across additional domains, languages, and against baseline extraction methods is left for future work.
Transaction processing systems underpin modern commerce, finance, critical infrastructure, and emerging Self-Sovereign Digital Identity (SSDI) protocols, yet their security has never been studied holistically across the full evolutionary arc of these systems. Over five decades, transaction processing has progressed through four distinct generations, from centralized databases, to distributed databases, to blockchain and distributed ledger technologies (DLTs), and most recently to multi-context systems that span cyber-physical components under real-time constraints. Each generation has introduced new transaction types and, with them, new classes of vulnerabilities; successful exploits now cause billions of dollars in annual losses. Despite this, security research remains fragmented by domain, and the foundational ACID transaction model has not been revisited to reflect the demands of contemporary systems.
Cross-chain technology is the key to solving the “data silo” problem in medical blockchain systems. However, it is difficult for existing cross-chain consensus mechanisms to meet the high standards of data security and consensus efficiency in medical scenarios. Therefore, this paper proposes a medical cross-chain Delegated proof of stake consensus(DPoS) scheme that integrates reputation and contribution evaluation. First, a dynamic reputation evaluation model was constructed, and the historical behaviour and communication quality of nodes were incorporated into the evaluation system, thereby mitigating the risk of centralization caused by the excessive reliance on the number of coins held in the DPoS consensus. Second, a hybrid random block generation mechanism combining the multiparty coin-tossing protocol and the secure shuffling algorithm was proposed. By collaboratively generating a verifiable global random seed and uniformly and randomly shuffling the candidate node sequence, the predictability of the block generation order was eliminated. Finally, a two-layer incentive architecture based on the Shapley value was proposed. Fine-grained contribution assessment mechanisms were established at both the candidate node layer and the voting node layer, making the reward distribution more equitable, enhancing the enthusiasm of nodes for voting and improving the consensus efficiency. Theoretical analysis and experimental results show that compared with the DPoS scheme, the proposed scheme improves the throughput by approximately 30% and reduces the average latency by approximately 50%. Compared with existing similar schemes, this scheme also has significant advantages in terms of reputation calculation overhead and malicious node elimination and can provide efficient and reliable consensus support for cross-chain scenarios in the medical field.
Efficient extraction and integration of pharmacokinetic (PK) data from scientific literature is critical for informed decision-making in drug development. Prior knowledge of PK parameters, particularly from similar compounds, supports first-in-human dosing, parameter estimation, and compound screening, ultimately helping to reduce attrition in clinical trials. While recent natural language processing (NLP) efforts have focused on extracting PK data from unstructured text, these approaches often overlook more comprehensive PK information and essential contextual metadata, which are usually reported in tables. Despite the prevalence and value of these tables, no previous work has systematically addressed the automated extraction of PK data from them. This thesis presents a novel NLP pipeline for identifying, extracting, and structuring PK data from scientific tables. The work addresses a key gap by targeting tables as a rich and underutilised source of PK information. The thesis is structured around four main components. First, a classification system combining supervised learning and prompt-based approaches is developed to retrieve PK-relevant tables from full-text biomedical articles. Second, heuristic and neural named entity recognition approaches are designed to extract PK parameters and associated metadata from table cells, including dose, species, study population, route of administration, units, and other contextual qualifiers. Third, an entity linking pipeline, including rule-based and zero-shot methods, is developed to normalise extracted data to a standardised PK ontology. Finally, the full pipeline is utilised to construct a large-scale PK database from PubMed Open Access articles. The database is evaluated through systematic sampling and manual quality assessment, and proof-of-concept analyses demonstrate how the extracted data can be used to characterise literature-wide reporting trends and explore comparative pharmacological questions. The results of this thesis demonstrate that automated PK table mining is both feasible and scalable, significantly accelerating the curation of high-quality datasets for pharmacometrics modelling. This work presents new open-source annotated corpora, domain-specific NLP methodologies, and practical tools for structuring PK literature, thereby opening the door to scalable, data-driven approaches in early drug development.
Ana-Maria Istrate, Fausto Milletarì, Fabrizio Castrotorres, Jakub M. Tomczak · 7 authors
Abstract Reasoning models are typically trained against verification mechanisms in formally specified systems such as code or symbolic math. In open domains like biology, however, we lack exact rules to enable large-scale formal verification and instead often rely on lab experiments to test predictions. Such experiments are slow, costly, and cannot scale with computation. In this work, we show that world models of biology or other prior knowledge can serve as approximate oracles for soft verification , allowing reasoning systems to be trained without additional experimental data. We present two paradigms of training models with approximate verifiers: RLEMF : reinforcement learning with experimental model feedback and RLPK : reinforcement learning from prior knowledge. Using these paradigms, we introduce rbio1 , a reasoning model for biology post-trained from a pretrained LLM with reinforcement learning, using learned biological models for verification during training. We demonstrate that soft verification can distill biological world models into rbio1 , enabling it to achieve state-of-the-art performance on perturbation prediction in the PerturbQA benchmark. We further show that composing multiple AI-verifiers improves performance and that models trained with soft biological rewards transfer zero-shot to cross-domain tasks such as disease-state prediction. We present rbio1 as a proof of concept that predictions from biological models can train powerful reasoning systems using simulations rather than experimental data, offering a new paradigm for model training.
Marielle S. Gross, Ananya Dewan, Mario Macis, Eve Budd · 9 authors
Introduction Organoids are living, patient-derived tumor models that are revolutionizing precision medicine and drug development, however current privacy practices strip identifiers, thereby undermining ethics, efficiency, and effectiveness for patients and research enterprises alike. Decentralized biobanking “de-bi” applies non-fungible tokens (NFTs) to empower privacy-preserving specimen tracking and data sharing for networks of scientists, donors, and physicians. We design, develop, and demonstrate a functional de-bi platform for a real-world organoid biobank. Methods Ethnography of the organoid biobanking ecosystem was performed in 2022–2023, with site visits, interviews, focus groups, and structured observations of stakeholder interactions. An initial ERC-721 prototype was developed and tested, informing the design of a comprehensive NFT model. Web and mobile app prototypes were developed with a suite of ERC-1155 protocols representing ecosystem constituents as NFTs. We demonstrated the platform with publicly available Human Cancer Models Initiatives organoids to establish proof-of-concept for decentralized biobanking as the foundation of a democratized biomedical metaverse, or “biomediverse.” Results Scientists revealed key challenges for organoid research and development under policy, scientific, and economic constraints of the life science landscape. We advanced decentralized biobanking as a blockchain overlay network solution with potential to overcome barriers, enhance utility and unlock value by uniting collaborators in a privacy-preserving biomediverse. Dedicated smart contracts created “soulbound” NFTs as de-identified digital twins of patients, physicians, and scientists in a networked organoid ecosystem. We modeled biospecimen collection, processing, and distribution, including generation and expansion of organoids, via an auditable on-chain mechanism. Key features included the ability to bootstrap the digital twin NFT model onto an established organoid biobank, visibility of patient-linked biospecimens and related research activities for all ecosystem participants, as well as tooling for multisided data exchange. Implementing de-bi with ERC-1155 showed potential to minimize gas costs of on-chain activity vs ERC-721, though complementary layer-2 solutions will be essential for economic viability. Conclusion Decentralized biobanking has the potential to enhance efficiency, increase translational impact and drive research discovery through implementation of NFT digital twins for organoid research networks. Importantly, this approach also bolsters ethical practices by fostering inclusion, ensuring transparency, and enhancing accountability across the research ecosystem. Next steps include live pilot testing, market design research to align stakeholder incentives, and technical solutions to support a sustainable, scalable and mutually rewarding biomediverse.
The rapid growth of memecoins within the Web3 ecosystem, driven by platforms like Pump.fun, has made it easier for anyone to create tokens. However, this democratization has also led to an explosion of low-quality or bot-generated projects, often motivated by short-term financial gain. This overwhelming influx of speculative tokens creates a challenge in distinguishing viable memecoins from those that are unlikely to succeed. To address this issue, we introduce CoinVibe, a comprehensive multimodal dataset designed to evaluate the viability of memecoins. CoinVibe integrates textual descriptions, visual content (logos), and community data (user comments, timestamps, and number of likes) to provide a holistic view of a memecoin's potential. In addition, we present CoinCLIP, a novel framework that leverages the Contrastive Language-Image Pre-Training (CLIP) model, augmented with lightweight modules and community data integration, to improve classification accuracy. By combining visual and textual representations with community insights, CoinCLIP provides a robust, data-driven approach to filter out low-quality or bot-driven projects. This research aims to help creators and investors identify high-potential memecoins, while also offering valuable insights into the factors that contribute to their long-term success. The code and dataset are publicly available at https://github.com/hwlongCUHK/CoinCLIP.git.
This research introduces a cutting-edge Web3 literary analysis platform, harnessing the power of blockchain and deep learning technologies. By employing the immutable and transparent nature of blockchain, the platform ensures robust copyright protection while offering readers enhanced interactive features. It applies deep learning techniques for comprehensive analyses of sentiment, topic, and stylistic elements, which are instrumental in predicting potential Nobel Prize laureates. This methodology not only enhances the accuracy of predictions but also sheds light on the evaluation criteria and historical trends associated with the Nobel Prize. Moreover, the platform adopts a directed graph model alongside the struc2vec algorithm to create text vectors for comparative studies, uncovering similarities between works that have won awards and those that have been nominated. Utilizing the LESS model for detailed content examination, the platform delves into sequence relationships within semantic networks, thus improving interpretability and visualization. The integration of blockchain technology guarantees access to unbiased datasets, enabling more precise literary analyses and predictions. This innovative approach has been validated using works that have either won or been nominated for the Nobel Prize, proving its efficacy in identifying the textual characteristics favored by the Nobel Prize committee.
In Ethereum, the ledger exchanges messages along an underlying Peer-to-Peer (P2P) network to reach consistency. Understanding the underlying network topology of Ethereum is crucial for network optimization, security and scalability. However, the accurate discovery of Ethereum network topology is non-trivial due to its deliberately designed security mechanism. Consequently, existing measuring schemes cannot accurately infer the Ethereum network topology with a low cost. To address this challenge, we propose the Distributed Ethereum Network Analyzer (DEthna) tool, which can accurately and efficiently measure the Ethereum network topology. In DEthna, a novel parallel measurement model is proposed that can generate marked transactions to infer link connections based on the transaction replacement and propagation mechanism in Ethereum. Moreover, a workload offloading scheme is designed so that DEthna can be deployed on multiple distributed probing nodes so as to measure a large-scale Ethereum network at a low cost. We run DEthna on Goerli (the most popular Ethereum test network) to evaluate its capability in discovering network topology. The experimental results demonstrate that DEthna significantly outperforms the state-of-the-art baselines. Based on DEthna, we further analyze characteristics of the Ethereum network revealing that there exist more than 50% low-degree Ethereum nodes that weaken the network robustness.
Electronic health records (EHRs) have become the new standard in the healthcare industry, but they have certain disadvantages as well, such as data breaches, data silos, and ownership issues. Blockchain technology, specifically the Ethereum blockchain, offers the potential to resolve these issues by building a decentralized and secure network for the storing and exchanging of health data. This study explores the benefits and drawbacks of using an NFT-based health identification and a decentralized system for storing health records on the Ethereum blockchain. Understanding how these technologies might be applied to build a safe and open system for exchanging and storing health data, is crucial for enhancing the standard of care. In this paper, we propose an open protocol for consent to access the health records of the user using the blockchain network. This consent needs to be given by the user, and no hindrance will be faces while retrieving the medical records of the patient. The study also emphasizes the requirement for a uniform framework in India to enable digital health infrastructure in a safe, decentralized way, with benefits including user consent, portability across national boundaries and ease of access.
Eric Venner, Mullai Murugan, Walker Hale, Jordan M Jones · 7 authors
MOTIVATION: Clinical genome sequencing laboratories return reports containing clinical testing results, signed by a board-certified clinical geneticist, to the ordering physician. This report is often a PDF, but can also be a paper copy or a structured data file. The reports are frequently modified and reissued due to changes in variant interpretation or clinical attributes. MATERIALS AND METHODS: To precisely track report authenticity, we developed ARBoR (Authenticated Resources in a Hashed Block Registry), an application for tracking the authenticity and lineage of versioned clinical reports even when they are distributed as PDF or paper copies. ARBoR tracks clinical reports as cryptographically signed hash blocks in an electronic ledger file, which is then exactly replicated to many clients. RESULTS: ARBoR was implemented for clinical reporting in the Human Genome Sequencing Center Clinical Laboratory, initially as part of the National Institute of Health's Electronic Medical Record and Genomics (eMERGE) project. CONCLUSIONS: To date, we have issued 15 205 versioned clinical reports tracked by ARBoR. This system has provided us with a simple and tamper-proof mechanism for tracking clinical reports with a complicated update history.
Oct 1, 2018·2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)
Asoke K. Talukder, M. Chaitanya, David Arnold, Kouichi Sakurai
Studies suggest that a significant proportion of the diagnosis in non-communicable diseases (NCD) is erroneous, unwanted, or unnecessary. To reduce the disease burden and improve public health, algorithmic support is essential. To realize this, health data must be computer understandable, secured, ubiquitous, and interoperable. Medical and disease data entered into computers are unstructured natural language texts with medical jargons which a computer normally cannot understand. EMR (Electronic Medical Records) are data silos in the hospital and do not interoperate. In this paper we present Ethereum based future ready Proof of Disease (PoD) consensus protocol with a computer understandable single instance of truth. It will solve many challenges that electronic health records (EHR) or health information exchange (HIE) have failed to address. This medical system will help achieve all the complex needs of P6 (Participatory, Personalized, Proactive, Preventive, Predictive and Precision) medicine and finally reduce the disease burden.
Representing the semantic relations that exist between two given words (or entities) is an important first step in a wide-range of NLP applications such as analogical reasoning, knowledge base completion and relational information retrieval. A simple, yet surprisingly accurate method for representing a relation between two words is to compute the vector offset (\PairDiff) between the corresponding word embeddings. Despite its empirical success, it remains unclear whether \PairDiff is the best operator for obtaining a relational representation from word embeddings. In this paper, we conduct a theoretical analysis of the \PairDiff operator. In particular, we show that for word embeddings where cross-dimensional correlations are zero, \PairDiff is the only bilinear operator that can minimise the $\ell_{2}$ loss between analogous word-pairs. We experimentally show that for word embedding created using a broad range of methods, the cross-dimensional correlations in word embeddings are approximately zero, demonstrating the general applicability of our theoretical result. Moreover, we empirically verify the implications of the proven theoretical result in a series of experiments where we repeatedly discover \PairDiff as the best bilinear operator for representing semantic relations between words in several benchmark datasets.
Web 3.0, the web of social and semantic cooperation, calls for a methodological multidisciplinary architecture in order to reach its mainstream objectives. With the lack of such an architecture and the reliance of existing efforts on lightweight semantics and RDF graphs, this thesis proposes "Web3.OWL", an ontology-driven framework towards a Web 3.0 knowledge architecture. \nMeanwhile, the online social parenting data and their corresponding websites users known as "mommy bloggers" undergo one of the fastest online demographics growth, \nand the available literature reflects the very little attention this growth has so far been given and the various deficiencies the parenting domain suffers from; these deficiencies all fall under the umbrella of the scarcity of parenting sociomedical analysis and decision-support systems. \nThe Web3.OWL framework puts forward an approach that relies on the Meta-Object Facility for Semantics standard (SMOF) for the management of its modeled OWL (Web Ontology Language) expressive domain ontologies on the one hand, and the coordination of its various underlined Web 3.0 prerequisite disciplines on the other. \nSetting off with a holistic portrayal of Web3.OWL’s components and workflow, the thesis progresses into a more analytic exploration of its main paradigms. Out of its \ndifferent ontology-aware paradigms are notably highlighted both its methodology for expressiveness handling through modularization and projection techniques and algorithms, \nand its facilities for tagging inference, suggestion and processing. \n \nWeb3.OWL, albeit generic by conception, proves its efficiency in solving the deficiencies and meeting the requirements of the sociomedical domain of interest. Its conceived ontology for parenting analysis and surveillance, baptised "ParOnt", strongly contributes to the backbone metamodel and the various constituents of this ontology-driven framework. \nAccordingly, as the workflow revolves around Description Logics principles, OWL 2 profiles along with standard and beyond-standard reasoning techniques, conducted experiments and competency questions are illustrated, thus establishing the required Web 3.0 outcomes. The empirical results of the diverse preliminary decision-support and recommendation services targeting parenting public awareness, orientation and education do ascertain, in conclusion, the value and potentials of the proposed conceptual framework.