Kezhi Li

Zhijun Guo, Alvina Lai, Emmanouil Korakas et al.

Continuous glucose monitoring (CGM) is central to diabetes care, but explaining CGM patterns clearly and empathetically remains time-intensive. Evidence for retrieval-grounded large language model (LLM) systems in CGM-informed counseling remains limited. To evaluate whether a retrieval-grounded LLM-based conversational agent (CA) could support patient understanding of CGM data and preparation for routine diabetes consultations. We developed a retrieval-grounded LLM-based CA for CGM interpretation and diabetes counseling support. The system generated plain-language responses while avoiding individualized therapeutic advice. Twelve CGM-informed cases were constructed from publicly available datasets. Between Oct 2025 and Feb 2026, 6 senior UK diabetes clinicians each reviewed 2 assigned cases and answered 24 questions. In a blinded multi-rater evaluation, each CA-generated and clinician-authored response was independently rated by 3 clinicians on 6 quality dimensions. Safety flags and perceived source labels were also recorded. Primary analyses used linear mixed-effects models. A total of 288 unique responses (144 CA and 144 clinician) generated 864 ratings. The CA received higher quality scores than clinician responses (mean 4.37 vs 3.58), with an estimated mean difference of 0.782 points (95% CI 0.692-0.872; P<.001). The largest differences were for empathy (1.062, 95% CI 0.948-1.177) and actionability (0.992, 95% CI 0.877-1.106). Safety flag distributions were similar, with major concerns rare in both groups (3/432, 0.7% each). Retrieval-grounded LLM systems may have value as adjunct tools for CGM review, patient education, and preconsultation preparation. However, these findings do not support autonomous therapeutic decision-making or unsupervised real-world use.

Joseph Farrington, Kezhi Li, Wai Keong Wong et al.

Value iteration can find the optimal replenishment policy for a perishable inventory problem, but is computationally demanding due to the large state spaces that are required to represent the age profile of stock. The parallel processing capabilities of modern GPUs can reduce the wall time required to run value iteration by updating many states simultaneously. The adoption of GPU-accelerated approaches has been limited in operational research relative to other fields like machine learning, in which new software frameworks have made GPU programming widely accessible. We used the Python library JAX to implement value iteration and simulators of the underlying Markov decision processes in a high-level API, and relied on this library's function transformations and compiler to efficiently utilize GPU hardware. Our method can extend use of value iteration to settings that were previously considered infeasible or impractical. We demonstrate this on example scenarios from three recent studies which include problems with over 16 million states and additional problem features, such as substitution between products, that increase computational complexity. We compare the performance of the optimal replenishment policies to heuristic policies, fitted using simulation optimization in JAX which allowed the parallel evaluation of multiple candidate policy parameters on thousands of simulated years. The heuristic policies gave a maximum optimality gap of 2.49%. Our general approach may be applicable to a wide range of problems in operational research that would benefit from large-scale parallel computation on consumer-grade GPU hardware.

Jiazhe Wei, Ken Li, Tianyu Lao et al.

Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack the iterative, layer-specific editing required in professional workflows. To address these limitations, we present PosterCopilot, a framework that advances layout reasoning and controllable editing for professional graphic design. Specifically, we introduce a progressive three-stage training strategy that equips LMMs with geometric understanding and aesthetic reasoning for layout design, consisting of Perturbed Supervised Fine-Tuning, Reinforcement Learning for Visual-Reality Alignment, and Reinforcement Learning from Aesthetic Feedback. Furthermore, we develop a complete workflow that couples the trained LMM-based design model with generative models, enabling layer-controllable, iterative editing for precise element refinement while maintaining global visual consistency. Extensive experiments demonstrate that PosterCopilot achieves geometrically accurate and aesthetically superior layouts, offering unprecedented controllability for professional iterative design.

Zhijun Guo, Alvina Lai, Johan Hilge Thygesen et al.

Large language models (LLMs) have attracted significant attention for potential applications in digital health, while their application in mental health is subject to ongoing debate. This systematic review aims to evaluate the usage of LLMs in mental health, focusing on their strengths and limitations in early screening, digital interventions, and clinical applications. Adhering to PRISMA guidelines, we searched PubMed, IEEE Xplore, Scopus, JMIR, and ACM using keywords: 'mental health OR mental illness OR mental disorder OR psychiatry' AND 'large language models'. We included articles published between January 1, 2017, and April 30, 2024, excluding non-English articles. 30 articles were evaluated, which included research on mental health conditions and suicidal ideation detection through text (n=15), usage of LLMs for mental health conversational agents (CAs) (n=7), and other applications and evaluations of LLMs in mental health (n=18). LLMs exhibit substantial effectiveness in detecting mental health issues and providing accessible, de-stigmatized eHealth services. However, the current risks associated with the clinical use might surpass their benefits. The study identifies several significant issues: the lack of multilingual datasets annotated by experts, concerns about the accuracy and reliability of the content generated, challenges in interpretability due to the 'black box' nature of LLMs, and persistent ethical dilemmas. These include the lack of a clear ethical framework, concerns about data privacy, and the potential for over-reliance on LLMs by both therapists and patients, which could compromise traditional medical practice. Despite these issues, the rapid development of LLMs underscores their potential as new clinical aids, emphasizing the need for continued research and development in this area.

Chengzhe Piao, Taiyu Zhu, Stephanie E Baldeweg et al.

Accurate prediction of future blood glucose (BG) levels can effectively improve BG management for people living with diabetes, thereby reducing complications and improving quality of life. The state of the art of BG prediction has been achieved by leveraging advanced deep learning methods to model multi-modal data, i.e., sensor data and self-reported event data, organised as multi-variate time series (MTS). However, these methods are mostly regarded as ``black boxes'' and not entirely trusted by clinicians and patients. In this paper, we propose interpretable graph attentive recurrent neural networks (GARNNs) to model MTS, explaining variable contributions via summarizing variable importance and generating feature maps by graph attention mechanisms instead of post-hoc analysis. We evaluate GARNNs on four datasets, representing diverse clinical scenarios. Upon comparison with twelve well-established baseline methods, GARNNs not only achieve the best prediction accuracy but also provide high-quality temporal interpretability, in particular for postprandial glucose levels as a result of corresponding meal intake and insulin injection. These findings underline the potential of GARNN as a robust tool for improving diabetes care, bridging the gap between deep learning technology and real-world healthcare solutions.

Chengzhe Piao, Ken Li

In the UK, approximately 400,000 people with type 1 diabetes (T1D) rely on insulin delivery due to insufficient pancreatic insulin production. Managing blood glucose (BG) levels is crucial, with continuous glucose monitoring (CGM) playing a key role. CGM, tracking BG every 5 minutes, enables effective blood glucose level prediction (BGLP) by considering factors like carbohydrate intake and insulin delivery. Recent research has focused on developing sequential models for BGLP using historical BG data, incorporating additional attributes such as carbohydrate intake, insulin delivery, and time. These methods have shown notable success in BGLP, with some providing temporal explanations. However, they often lack clear correlations between attributes and their impact on BGLP. Additionally, some methods raise privacy concerns by aggregating participant data to learn population patterns. Addressing these limitations, we introduced a graph attentive memory (GAM) model, combining a graph attention network (GAT) with a gated recurrent unit (GRU). GAT applies graph attention to model attribute correlations, offering transparent, dynamic attribute relationships. Attention weights dynamically gauge attribute significance over time. To ensure privacy, we employed federated learning (FL), facilitating secure population pattern analysis. Our method was validated using the OhioT1DM'18 and OhioT1DM'20 datasets from 12 participants, focusing on 6 key attributes. We demonstrated our model's stability and effectiveness through hyperparameter impact analysis.

Joseph Farrington, Samah Alimam, Martin Utley et al.

Efforts to reduce platelet wastage in hospital blood banks have focused on ordering policies, but the predominant practice of issuing the oldest unit first may not be optimal when some units are returned unused. We propose a novel, machine learning (ML)-guided issuing policy to increase the likelihood of returned units being reissued before expiration. Our ML model trained to predict returns on 17,297 requests for platelets gave AUROC 0.74 on 9,353 held-out requests. Prior to ML model development we built a simulation of the blood bank operation that incorporated returns to understand the scale of benefits of such a model. Using our trained model in the simulation gave an estimated reduction in wastage of 14%. Our partner hospital is considering adopting our approach, which would be particularly beneficial for hospitals with higher return rates and where units have a shorter remaining useful life on arrival.

Zhijun Guo, Alvina Lai, Julia Ive et al.

Static tools like the Patient Health Questionnaire-9 (PHQ-9) effectively screen depression but lack interactivity and adaptability. We developed HopeBot, a chatbot powered by a large language model (LLM) that administers the PHQ-9 using retrieval-augmented generation and real-time clarification. In a within-subject study, 132 adults in the United Kingdom and China completed both self-administered and chatbot versions. Scores demonstrated strong agreement (ICC = 0.91; 45% identical). Among 75 participants providing comparative feedback, 71% reported greater trust in the chatbot, highlighting clearer structure, interpretive guidance, and a supportive tone. Mean ratings (0-10) were 8.4 for comfort, 7.7 for voice clarity, 7.6 for handling sensitive topics, and 7.4 for recommendation helpfulness; the latter varied significantly by employment status and prior mental-health service use (p < 0.05). Overall, 87.1% expressed willingness to reuse or recommend HopeBot. These findings demonstrate voice-based LLM chatbots can feasibly serve as scalable, low-burden adjuncts for routine depression screening.

Chengzhe Piao, Taiyu Zhu, Yu Wang et al.

Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain effective Blood Glucose (BG) prediction models due to the lack of sufficient BG data from Continuous Glucose Monitoring (CGM), presenting a significant "cold start" problem in patient care. Utilizing population models to address this challenge is a potential solution, but collecting patient data for training population models in a privacy-conscious manner is challenging, especially given that such data is often stored on personal devices. Considering the privacy protection and addressing the "cold start" problem in diabetes care, we propose "GluADFL", blood Glucose prediction by Asynchronous Decentralized Federated Learning. We compared GluADFL with eight baseline methods using four distinct T1D datasets, comprising 298 participants, which demonstrated its superior performance in accurately predicting BG levels for cross-patient analysis. Furthermore, patients' data might be stored and shared across various communication networks in GluADFL, ranging from highly interconnected (e.g., random, performs the best among others) to more structured topologies (e.g., cluster and ring), suitable for various social networks. The asynchronous training framework supports flexible participation. By adjusting the ratios of inactive participants, we found it remains stable if less than 70% are inactive. Our results confirm that GluADFL offers a practical, privacy-preserving solution for BG prediction in T1D, significantly enhancing the quality of diabetes management.

Robert Spence, Chukwuma Uduku, Kezhi Li et al.

The paper describes the interaction design of a hand-held interface supporting the self-management of Type 1 diabetes. It addresses well-established clinical and human-computer interaction requirements. The design exploits three opportunities. One is associated with visible context, whether conspicuous or inconspicuous. A second arises from the design freedom made possible by the user's anticipated focus of attention during certain interactions. A third opportunity to provide valuable functionality arises from wearable sensors and machine learning algorithms. The resulting interface permits ``What if?'' questions: it allows a user to dynamically and manually explore predicted short-term (e.g., 2 hours) relationships between an intended meal, blood glucose level and recommended insulin dosage, and thereby readily make informed food and exercise decisions. Design activity has been informed throughout by focus groups comprising people with Type 1 diabetes in addition to experts in diabetes, interaction design and machine learning. The design is being implemented prior to a clinical trial.

Taiyu Zhu, Kezhi Li, Pantelis Georgiou

We propose a dual-hormone delivery strategy by exploiting deep reinforcement learning (RL) for people with Type 1 Diabetes (T1D). Specifically, double dilated recurrent neural networks (RNN) are used to learn the hormone delivery strategy, trained by a variant of Q-learning, whose inputs are raw data of glucose \& meal carbohydrate and outputs are dual-hormone (insulin and glucagon) delivery. Without prior knowledge of the glucose-insulin metabolism, we run the method on the UVA/Padova simulator. Hundreds days of self-play are performed to obtain a generalized model, then importance sampling is adopted to customize the model for personal use. \emph{In-silico} the proposed strategy achieves glucose time in target range (TIR) $93\%$ for adults and $83\%$ for adolescents given standard bolus, outperforming previous approaches significantly. The results indicate that deep RL is effective in building personalized hormone delivery strategy for people with T1D.

Kezhi Li, John Daniels, Chengyuan Liu et al.

Control of blood glucose is essential for diabetes management. Current digital therapeutic approaches for subjects with Type 1 diabetes mellitus (T1DM) such as the artificial pancreas and insulin bolus calculators leverage machine learning techniques for predicting subcutaneous glucose for improved control. Deep learning has recently been applied in healthcare and medical research to achieve state-of-the-art results in a range of tasks including disease diagnosis, and patient state prediction among others. In this work, we present a deep learning model that is capable of forecasting glucose levels with leading accuracy for simulated patient cases (RMSE = 9.38$\pm$0.71 [mg/dL] over a 30-minute horizon, RMSE = 18.87$\pm$2.25 [mg/dL] over a 60-minute horizon) and real patient cases (RMSE = 21.07$\pm$2.35 [mg/dL] for 30-minute, RMSE = 33.27$\pm$4.79\% for 60-minute). In addition, the model provides competitive performance in providing effective prediction horizon ($PH_{eff}$) with minimal time lag both in a simulated patient dataset ($PH_{eff}$ = 29.0$\pm$0.7 for 30-min and $PH_{eff}$ = 49.8$\pm$2.9 for 60-min) and in a real patient dataset ($PH_{eff}$ = 19.3$\pm$3.1 for 30-min and $PH_{eff}$ = 29.3$\pm$9.4 for 60-min). This approach is evaluated on a dataset of 10 simulated cases generated from the UVa/Padova simulator and a clinical dataset of 10 real cases each containing glucose readings, insulin bolus, and meal (carbohydrate) data. Performance of the recurrent convolutional neural network is benchmarked against four algorithms. The proposed algorithm is implemented on an Android mobile phone, with an execution time of $6$ms on a phone compared to an execution time of $780$ms on a laptop.

Kezhi Li, Daniel Holland

A new iterative image reconstruction algorithm for electrical capacitance tomography (ECT) is proposed that is based on iterative soft thresholding of a total variation penalty and adaptive reweighted compressive sensing. This algorithm encourages sharp changes in the ECT image and overcomes the disadvantage of the $l_1$ minimization by equipping the total variation with an adaptive weighting depending on the reconstructed image. Moreover, the non-linear effect is also partially reduced due to the adoption of an updated sensitivity matrix. Simulation results show that the proposed algorithm recovers ECT images more precisely than existing state-of-the-art algorithms and therefore is suitable for the imaging of multiphase systems in industrial or medical applications.

Kezhi Li

To study the fundamental physics of complex multiphase flow systems using advanced measurement techniques, especially the electrical capacitance tomography (ECT) approach, this article carries out an initial literature review of the ECT method from a point of view of signal processing and algorithm design. After introducing the physical laws governing the ECT system, we will focus on various reconstruction techniques that are capable to recover the image of the internal characteristics of a specified region based on the measuring capacitances of multi-electrode sensors surrounding the region. Each technique has its own advantages and limitations, and many algorithms have been examined by simulations or experiments. Future researches in 3D reconstruction and other potential improvements of the system are discussed in the end.

Kezhi Li, Lu Gan, Cong Ling

In this paper, a new class of circulant matrices built from deterministic sequences is proposed for convolution-based compressed sensing (CS). In contrast to random convolution, the coefficients of the underlying filter are given by the discrete Fourier transform of a deterministic sequence with good autocorrelation. Both uniform recovery and non-uniform recovery of sparse signals are investigated, based on the coherence parameter of the proposed sensing matrices. Many examples of the sequences are investigated, particularly the Frank-Zadoff-Chu (FZC) sequence, the \textit{m}-sequence and the Golay sequence. A salient feature of the proposed sensing matrices is that they can not only handle sparse signals in the time domain, but also those in the frequency and/or or discrete-cosine transform (DCT) domain.