Urgent suspected colorectal cancer (CRC) referrals create operational bottlenecks because semi-structured clinical documents often require manual review and transcription. The original RAPTOR system used Large Language Models for structured extraction but relied on a separate OCR stage, making it vulnerable to handwriting, layout variation, and loss of visual evidence linkage. We present RAPTOR+, a multimodal extension that uses Vision-Language Models (VLMs) for end-to-end referral understanding. We evaluate fine-tuned VLMs, commercial and open-source zero-shot VLMs, and the original OCR-based pipeline on 223 clinically curated CRC urgent referral forms. We also introduce a grounding-aware evaluation framework that measures both extraction accuracy and evidence localisation. Results show a clear grounding gap in zero-shot models. Gemini 2.5 Flash achieved 92.6

Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefacts into validated, executable HL7 Clinical Quality Language (CQL) libraries deployable as FHIR CDS Hooks services. Purpose-built agents extract flowchart structure into a typed directed graph, perform deterministic path enumeration, conduct a structured semantic audit of every node's computability, generate terminology-constrained CQL definitions verified by the official Java CQL-to-ELM compiler, and produce routing logic covering 100

In response to the success of proprietary Large Language Models (LLMs) such as OpenAI's GPT-4, there is a growing interest in developing open, non-proprietary LLMs and AI foundation models (AIFMs) for transparent use in academic, scientific, and non-commercial applications. Despite their inability to match the refined functionalities of their proprietary counterparts, open models hold immense potential to revolutionize healthcare applications. In this paper, we examine the prospects of open-source LLMs and AIFMs for developing healthcare applications and make two key contributions. Firstly, we present a comprehensive survey of the current state-of-the-art open-source healthcare LLMs and AIFMs and introduce a taxonomy of these open AIFMs, categorizing their utility across various healthcare tasks. Secondly, to evaluate the general-purpose applications of open LLMs in healthcare, we present a case study on personalized prescriptions. This task is particularly significant due to its critical role in delivering tailored, patient-specific medications that can greatly improve treatment outcomes. In addition, we compare the performance of open-source models with proprietary models in settings with and without Retrieval-Augmented Generation (RAG). Our findings suggest that, although less refined, open LLMs can achieve performance comparable to proprietary models when paired with grounding techniques such as RAG. Furthermore, to highlight the clinical significance of LLMs-empowered personalized prescriptions, we perform subjective assessment through an expert clinician. We also elaborate on ethical considerations and potential risks associated with the misuse of powerful LLMs and AIFMs, highlighting the need for a cautious and responsible implementation in healthcare.

Over the past few years, surgical data science has attracted substantial interest from the machine learning (ML) community. Various studies have demonstrated the efficacy of emerging ML techniques in analysing surgical data, particularly recordings of procedures, for digitising clinical and non-clinical functions like preoperative planning, context-aware decision-making, and operating skill assessment. However, this field is still in its infancy and lacks representative, well-annotated datasets for training robust models in intermediate ML tasks. Also, existing datasets suffer from inaccurate labels, hindering the development of reliable models. In this paper, we propose a systematic methodology for developing robust models for surgical tool classification using noisy endoscopic videos. Our methodology introduces two key innovations: (1) an intelligent active learning strategy for minimal dataset identification and label correction by human experts through collective intelligence; and (2) an assembling strategy for a student-teacher model-based self-training framework to achieve the robust classification of 14 surgical tools in a semi-supervised fashion. Furthermore, we employ strategies such as weighted data loaders and label smoothing to enable the models to learn difficult samples and address class imbalance issues. The proposed methodology achieves an average F1-score of 85.88% for the ensemble model-based self-training with class weights, and 80.88% without class weights for noisy tool labels. Also, our proposed method significantly outperforms existing approaches, which effectively demonstrates its effectiveness.

Delays in processing urgent cancer referrals hinder Faster Diagnostic Standards (FDS), with manual extraction of patient data (demographics, symptoms and test results) remaining a bottleneck in colorectal two-week wait (2WW) pathways. We evaluate generative AI (GenAI) for automating structured data extraction from colorectal cancer (CRC) 2WW referrals, comparing the reasoning capabilities of GPT-4o-Mini and DeepSeek-R1 against clinician-led extraction. Both models achieved near-human precision (GPT-4o-Mini: 94.83

In recent times, surgical data science has emerged as an important research discipline in interventional healthcare. There are many potential applications for analysing endoscopic surgical videos using machine learning (ML) techniques such as surgical tool classification, action recognition, and tissue segmentation. However, the efficacy of ML algorithms to learn robust features drastically deteriorates when models are trained on noise-affected data [1]. Appropriate data preprocessing for endoscopic videos is thus crucial to ensure robust ML training. To this end, we demonstrate the presence of label leakage when surgical tool classification is performed naively and present SegCrop, a dynamic U-Net model with an integrated attention mechanism to dynamically crop the arbitrary field of view (FoV) in endoscopic surgical videos to remove spurious label-related information from the data. In addition, we leverage explainability techniques to demonstrate how the presence of spurious correlations influences the model’s learning capability.

Over the past few years, surgical data science has attracted substantial interest from the machine learning (ML) community. Various studies have demonstrated the efficacy of emerging ML techniques in analysing surgical data, particularly recordings of procedures, for digitizing clinical and non-clinical functions like preoperative planning, context-aware decision-making, and operating skill assessment. However, this field is still in its infancy and lacks representative, well-annotated datasets for training robust models in intermediate ML tasks. Also, existing datasets suffer from inaccurate labels, hindering the development of reliable models. In this paper, we propose a systematic methodology for developing robust models for surgical tool detection using noisy data. Our methodology introduces two key innovations: (1) an intelligent active learning strategy for minimal dataset identification and label correction by human experts; and (2) an assembling strategy for a student-teacher model-based self-training framework to achieve the robust classification of 14 surgical tools in a semi-supervised fashion. Furthermore, we employ weighted data loaders to handle difficult class labels and address class imbalance issues. The proposed methodology achieves an average F1-score of 85.88\% for the ensemble model-based self-training with class weights, and 80.88\% without class weights for noisy labels. Also, our proposed method significantly outperforms existing approaches, which effectively demonstrates its effectiveness.

Coronary angiography analysis is a common clinical task performed by cardiologists to diagnose coronary artery disease (CAD) through an assessment of atherosclerotic plaque's accumulation. This study introduces an end-to-end machine learning solution developed as part of our solution for the MICCAI 2023 Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) challenge, which aims to benchmark solutions for multivessel coronary artery segmentation and potential stenotic lesion localisation from X-ray coronary angiograms. We adopted a robust baseline model training strategy to progressively improve performance, comprising five successive stages of binary class pretraining, multivessel segmentation, fine-tuning using class frequency weighted dataloaders, fine-tuning using F1-based curriculum learning strategy (F1-CLS), and finally multi-target angiogram view classifier-based collective adaptation. Unlike many other medical imaging procedures, this task exhibits a notable degree of interobserver variability. %, making it particularly amenable to automated analysis. Our ensemble model combines the outputs from six baseline models using the weighted ensembling approach, which our analysis shows is found to double the predictive accuracy of the proposed solution. The final prediction was further refined, targeting the correction of misclassified blobs. Our solution achieved a mean F1 score of $37.69\%$ for coronary artery segmentation, and $39.41\%$ for stenosis localisation, positioning our team in the 5th position on both leaderboards. This work demonstrates the potential of automated tools to aid CAD diagnosis, guide interventions, and improve the accuracy of stent injections in clinical settings.

This study is to present a structural framework for selecting cloud services for implementing Conversational AI system in the construction industry using Design Thinking Methodology. A focus group discussion approach was used to get user requirements from construction workers to implement the Conversational AI for BIM. This resulted in five factors: cost, speed of operation, security, functionality, and visualisation as the requirements for implementing Conversational AI for the construction industries. The user specifications were mapped into technical modules which were used to select cloud services employed to implement the virtual assistant for the construction industry. Furthermore, the study presented the architecture of ConvBIM using AWS.

The growth of the construction industry is severely limited by the myriad complex challenges it faces such as cost and time overruns, health and safety, productivity and labour shortages. Also, construction industry is one the least digitized industries in the world, which has made it difficult for it to tackle the problems it currently faces. An advanced digital technology, Artificial Intelligence (AI), is currently revolutionising industries such as manufacturing, retail, and telecommunications. The subfields of AI such as machine learning, knowledge-based systems, computer vision, robotics and optimisation have successfully been applied in other industries to achieve increased profitability, efficiency, safety and security. While acknowledging the benefits of AI applications, numerous challenges which are relevant to AI still exist in the construction industry. This study aims to unravel AI applications, examine AI techniques being used and identify opportunites and challenges for AI applications in the construction industry. A critical review of available literature on AI applications in the construction industry such as activity monitoring, risk management, resource and waste optimisation was conducted. Furthermore, the opportunities and challenges of AI applications in construction were identified and presented in this study. This study provides insights into key AI applications as it applies to construction-specific challenges, as well as the pathway to realise the acrueable benefits of AI in the construction industry.

The outbreak of a pandemic of global concern, the Corona Virus Disease 2019 (COVID-19) has tested the capacity of healthcare facilities to the brim in many developed countries. In a minacious fashion of rapid spread and extreme transmission rate, COVID-19 has triggered a shortage of healthcare facilities such as hospital bed spaces and ventilators. Various strategies have been adopted by the worst-hit countries to slacken or halt the spread of the virus. Common Isolation Space Creation (ISC) measures for the COVID-19 pandemic containment includes self-isolation at home, isolation at regular hospitals, isolation at existing epidemic hospitals, isolation at retrofitted buildings for an emergency, isolation at Temporary Mobile Cabins (TMCs), isolation at newly constructed temporary hospitals for COVID-19. This study evaluates the ISC measures and proposes offsite and modular solutions for the construction industry and built environment to respond to emergencies. While this study has proposed a solution for creating emergency isolation spaces for effective containment of such pandemic, other critical COVID-19 challenges such as the shortage of healthcare staff and other facilities are not addressed in this study.

Purpose The purpose of this paper is to identify challenges faced in resource management in the UK construction industry and to propose some solutions to these problems. Design/methodology/approach Based on a qualitative research methodology, 14 experts from the UK construction industry were chosen to be participants in the study. The participants were equally divided into two focus groups to discuss resource management using five projects as case studies. Thematic analysis of the discussion reveals seven key factors that affect resource management. Findings The results show that most of the problems identified are due to poor data management processes and the practice of having data in silos. Overcoming this challenge requires the adoption of big data approaches for resource management to allow the integration of large and different forms of data. Originality/value This study seeks to bring to the fore challenges faced in resource management by the UK construction industry and to outline some solutions to address them.