https://bura.brunel.ac.uk/handle/2438/8642 2026-10-04T18:30:07Z 2026-10-04T18:30:07Z Zebin, Tahmina Wu, Jinyan Colecchia, Federico Shinhmar, Sonia Bondaronek, Paulina Potts, Henry WW Tucker, Allan Spinelli, Gabriella https://bura.brunel.ac.uk/handle/2438/33916 2026-10-01T02:00:31Z 2026-08-24T00:00:00Z

Title: Healthcare AI risk management: an innovator-informed approach from frameworks to practical worksheets for proportionate regulatory evidence capture Authors: Zebin, Tahmina; Wu, Jinyan; Colecchia, Federico; Shinhmar, Sonia; Bondaronek, Paulina; Potts, Henry WW; Tucker, Allan; Spinelli, Gabriella Abstract: Introduction: Artificial intelligence (AI)-enabled healthcare systems introduce clinical safety, operational and governance risks across development, deployment and post deployment stages. Although multiple AI risk assessment frameworks exist, they are often cross-sector, lengthy and difficult to operationalise in ways that support proportionate evidence generation and regulatory use. Methods: We conducted a targeted evidence synthesis and framework mapping exercise drawing on review-level evidence, scientific databases and regulatory sources. Three core review studies informed framework identification and mapping. Selected frameworks and guidance, including NIST AI RMF, the Fraunhofer IAIS AI Assessment Catalogue, ALTAI, the ICO AI and Data Protection Risk Toolkit, MHRA guidance, the NICE Evidence Standards Framework, SPIRIT-AI and CONSORT-AI, were mapped across lifecycle stages using a structured extraction matrix. Framework concepts were translated into healthcare-oriented worksheets and refined through structured engagement with healthcare AI innovators. Results: Frameworks varied substantially in scope, lifecycle coverage, terminology and implementation approach. Innovator feedback identified recurring themes including cognitive burden, usability, need for clearer intended purpose, lifecycle support, actionable examples and improved regulatory traceability. Participants highlighted challenges applying frameworks across diverse healthcare contexts and AI roles. Worksheet refinement introduced simplified domains, healthcare-specific context prompts, evidence and action fields and stage-aware guidance. Discussion: AI risk frameworks are necessary but not sufficient for healthcare innovation unless translated into practical tools. A codesigned worksheet approach can support proportionate evidence capture and iterative risk management while remaining adaptable across use cases and maturity levels. Description: Data availability statement: All data relevant to the study are included in the article or uploaded as supplementary information. The framework mapping and worksheet development are fully described in the manuscript; example worksheet templates are available from the RADIANTCERSI’s official website. The underlying stakeholder consultation data are not publicly available because they contain potentially identifiable or confidential information.

2026-08-24T00:00:00Z Colecchia, Federico https://bura.brunel.ac.uk/handle/2438/33874 2026-09-18T02:02:03Z 2026-08-15T00:00:00Z

Title: Towards Engram Memory Machines. A Feasibility Study of Image Classification Using Warping and Low-dimensional Class Prototypes Authors: Colecchia, Federico Abstract: Against the backdrop of ongoing green AI research to reduce the environmental footprint of artificial intelligence technology, a new supervised machine learning approach is presented with potential to contribute to the development of artificial systems capable of learning incrementally from new data. This article reports results from a feasibility study on image classification using the Modified National Institute of Standards and Technology data set. Training consists of producing class-level image prototypes, referred to as engrams, using a single-pass method. At inference stage, previously unseen images are warped to match the engrams individually, using a continuous transformation including a tuneable rigidity parameter. The images are classified by maximising similarity to the engrams across classes following warping. Unlike alternative approaches recording binary feature coincidences in highdimensional spaces, this method operates on low-dimensional data representations. In addition to enhancing interpretability, this has the advantage of circumventing memory scaling bottlenecks. A test accuracy above 90% was observed in this study, which is a promising result considering that the engrams exclusively encoded average data patterns. Future work will focus on reducing inference time, enhancing classification accuracy and estimating the performance of the method on additional datasets.

2026-08-15T00:00:00Z Wang, Xiang Li, Liang Tassou, Savvas A https://bura.brunel.ac.uk/handle/2438/33729 2026-08-20T02:00:56Z 2026-07-11T00:00:00Z

Title: Pressure-regulated pool boiling for lithium-ion batteries based on a thermo-lifetime-economic coupling framework Authors: Wang, Xiang; Li, Liang; Tassou, Savvas A Abstract: Pool boiling cooling offers strong potential for lithium-ion battery thermal management due to its high-efficiency phase-change heat transfer. However, most existing studies are limited to atmospheric pressure, and the coupled effects of pressure on thermal behaviour, battery lifetime, and economic performance remain unclear. In this study, a thermo-lifetime-economic coupling model is developed and experimentally validated through pressure-controlled pool boiling cooling of a battery module over a pressure range of 20–100 kPa. The results show that pool boiling significantly outperforms natural air-cooling, reducing the maximum temperature from 88.8 °C to 45.6 °C (48.6%) and the temperature difference from 9.3 °C to 3.1 °C (66.7%) at 2.5C. Further pressure reduction enhances thermal performance by lowering the saturation temperature and promoting earlier nucleate boiling. When the pressure decreases from 100 kPa to 20 kPa, the maximum temperature and temperature difference are further reduced by 26.3% and 38.7%, respectively, leading to a lifetime improvement of up to 65.1%. However, this improvement is accompanied by a substantial increase in auxiliary power consumption, which rises by more than 14.6 times, resulting in a strong thermo-economic trade-off with diminishing returns at low pressures. Furthermore, system scale critically affects economic feasibility. Pressure reduction increases cost at small scales but becomes favourable beyond a critical scale due to the growing contribution of lifetime-related cost. These results show that pressure regulation can improve pool boiling battery cooling, but the operating pressure should balance thermal performance, lifetime, and energy consumption. Description: Data availability: Data will be made available on request.

2026-07-11T00:00:00Z Dong, Hua Cifter, Abdusselam Selami::0000-0001-9807-1197 Boess, Stella Nickpour, Farnaz Dong, Yumei Ning, Weining::0000-0002-1229-7468 https://bura.brunel.ac.uk/handle/2438/33719 2026-08-19T02:00:36Z 2026-07-05T00:00:00Z

Title: New Agenda for Inclusive Design Authors: Dong, Hua; Cifter, Abdusselam Selami::0000-0001-9807-1197; Boess, Stella; Nickpour, Farnaz; Dong, Yumei; Ning, Weining::0000-0002-1229-7468 Abstract: The Inclusive Design Special Interest Group of the Design Research Society (InclusiveSIG-with Professor Hua Dong as its Convenor, and Dr Weining Ning as its co-convenor) organised the “New Agenda for Inclusive Design” Track for DRS2026. The Track has attracted more than 50 submissions from 16 countries. In total 19 papers were selected after blind peer-review, and three further papers added, forming four sessions: 1) Rethinking Inclusive Design; 2) Studying Older People: Theories and Methods; 3) Neurodivergent Groups: Adults and Children; 4) Assessing Accessibility and Inclusion. New agenda and trends include “relations as inclusion”, “aesthetics as a driver for dignity”, valuing older people’s resources in design, and “predictable unpredictability” for neurodivergent groups. Description: Editorial.

2026-07-05T00:00:00Z