David A. Clifton

The proliferation of decentralised electronic healthcare records (EHRs) across medical institutions requires innovative federated learning strategies for collaborative data analysis and global model training, prioritising data privacy. A prevalent issue during decentralised model training is the data-view discrepancies across medical institutions that arises from differences or availability of healthcare services, such as blood test panels. The prevailing way to handle this issue is to select a common subset of features across institutions to make data-views consistent. This approach, however, constrains some institutions to shed some critical features that may play a significant role in improving the model performance. This paper introduces a federated learning framework that relies on augmented graph attention networks to address data-view heterogeneity. The proposed framework utilises an alignment augmentation layer over self-attention mechanisms to weigh the importance of neighbouring nodes when updating a node’s embedding irrespective of the data-views. Furthermore, our framework adeptly addresses both the temporal nuances and structural intricacies of EHR datasets. This dual capability not only offers deeper insights but also effectively encapsulates EHR graphs’ time-evolving nature. Using diverse real-world datasets, we show that the proposed framework significantly outperforms conventional FL methodology for dealing with heterogeneous data-views.

Hand foot and mouth disease (HFMD) is caused by a variety of enteroviruses, and occurs in large outbreaks in which a small proportion of children deteriorate rapidly with cardiopulmonary failure. Determining which children are likely to deteriorate is difficult and health systems may become overloaded during outbreaks as many children require hospitalization for monitoring. Heart rate variability (HRV) may help distinguish those with more severe diseases but requires simple scalable methods to collect ECG data.We carried out a prospective observational study to examine the feasibility of using wearable devices to measure HRV in 142 children admitted with HFMD at a children’s hospital in Vietnam. ECG data were collected in all children. HRV indices calculated were lower in those with enterovirus A71 associated HFMD compared to those with other viral pathogens.HRV analysis collected from wearable …

The prevalence of artificial intelligence (AI) has envisioned an era of healthcare democratisation that promises every stakeholder a new and better way of life. However, the advancement of clinical AI research is significantly hurdled by the dearth of data democratisation in healthcare. To truly democratise data for AI studies, challenges are two-fold: 1. the sensitive information in clinical data should be anonymised appropriately, and 2. AI-oriented clinical knowledge should flow freely across organisations. This paper considers a recent deep-learning advent, dataset condensation (DC), as a stone that kills two birds in democratising healthcare data. The condensed data after DC, which can be viewed as statistical metadata, abstracts original clinical records and irreversibly conceals sensitive information at individual levels; nevertheless, it still preserves adequate knowledge for learning deep neural networks (DNNs). More favourably, the compressed volumes and the accelerated model learnings of condensed data portray a more efficient clinical knowledge sharing and flowing system, as necessitated by data democratisation. We underline DC's prospects for democratising clinical data, specifically electrical healthcare records (EHRs), for AI research through experimental results and analysis across three healthcare datasets of varying data types.

Estimation of individualized treatment effects (ITE) from observational studies is a fundamental problem in causal inference and holds significant importance across domains, including healthcare. However, limited observational datasets pose challenges in reliable ITE estimation as data have to be split among treatment groups to train an ITE learner. While information sharing among treatment groups can partially alleviate the problem, there is currently no general framework for end-to-end information sharing in ITE estimation. To tackle this problem, we propose a deep learning framework based on ‘\textit {soft weight sharing}’to train ITE learners, enabling\textit {dynamic end-to-end} information sharing among treatment groups. The proposed framework complements existing ITE learners, and introduces a new class of ITE learners, referred to as\textit {HyperITE}. We extend state-of-the-art ITE learners with\textit {HyperITE} versions and evaluate them on IHDP, ACIC-2016, and Twins benchmarks. Our experimental results show that the proposed framework improves ITE estimation error, with increasing effectiveness for smaller datasets.

For medical image segmentation, contrastive learning is the dominant practice to improve the quality of visual representations by contrasting semantically similar and dissimilar pairs of samples. This is enabled by the observation that without accessing ground truth labels, negative examples with truly dissimilar anatomical features, if sampled, can significantly improve the performance. In reality, however, these samples may come from similar anatomical features and the models may struggle to distinguish the minority tail-class samples, making the tail classes more prone to misclassification, both of which typically lead to model collapse. In this paper, we propose , a semi-supervised contrastive learning (CL) framework with stratified group theory for medical image segmentation. In particular, we first propose building through the concept of variance-reduced estimation, and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks with extremely limited labels. Furthermore, we theoretically prove these sampling techniques are universal in variance reduction. Finally, we experimentally validate our approaches on eight benchmarks, ie, five 2D/3D medical and three semantic segmentation datasets, with different label settings, and our methods consistently outperform state-of-the-art semi-supervised methods. Additionally, we augment the CL frameworks with these sampling techniques and demonstrate significant gains over previous methods. We believe our work is an important step towards semi-supervised medical image segmentation by quantifying the limitation of current self …

The design of neural networks typically involves trial-and-error, a time-consuming process for obtaining an optimal architecture, even for experienced researchers. Additionally, it is widely accepted that loss functions of deep neural networks are generally non-convex with respect to the parameters to be optimised. We propose the Layer-wise Convex Theorem to ensure that the loss is convex with respect to the parameters of a given layer, achieved by constraining each layer to be an overdetermined system of non-linear equations. Based on this theorem, we developed an end-to-end algorithm (the AutoNet) to automatically generate layer-wise convex networks (LCNs) for any given training set. We then demonstrate the performance of the AutoNet-generated LCNs (AutoNet-LCNs) compared to state-of-the-art models on three electrocardiogram (ECG) classification benchmark datasets, with further validation on two …

The present invention provides a deep learning-based wearable electro-tonoarteriography method and apparatus for the estimation of continuous arterial blood pressure, which relates to the technical fields of medical detection and artificial intelligence, and is applicable to, such as, tonoarteriogram (TAG, which is continuous arterial blood pressure) signal estimation and cardiac diseases detection. The method comprises: acquiring at least one lead ECG signal collected from a clothing and/or a wearable device worn by a subject of detection; processing the ECG signal based on a deep learning network, determining a signal processing result related to a tonoarteriogram information and/or related to a cardiac disease information. The present invention is advantageous in realizing the acquisition of continuous arterial blood pressure signal and/or the automatic diagnosis of cardiac disease on the basis of ensuring …

Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. As a result, it is necessary to collect and label data-text pairs for training, which is both costly and time-consuming. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled …

Digital measures of health status captured during daily life could greatly augment current in-clinic assessments for rheumatoid arthritis (RA), to enable better assessment of disease progression and impact. This work presents results from weaRAble-PRO, a 14-day observational study, which aimed to investigate how digital health technologies (DHT), such as smartphones and wearables, could augment patient reported outcomes (PRO) to determine RA status and severity in a study of 30 moderate-to-severe RA patients, compared to 30 matched healthy controls (HC). Sensor-based measures of health status, mobility, dexterity, fatigue, and other RA specific symptoms were extracted from daily iPhone guided tests (GT), as well as actigraphy and heart rate sensor data, which was passively recorded from patients’ Apple smartwatch continuously over the study duration. We subsequently developed a machine learning …

BackgroundConducting effective and translational research can be challenging and few trials undertake formal reflection exercises and disseminate learnings from them. Following completion of our multicentre randomised controlled trial, which was impacted by the COVID-19 pandemic, we sought to reflect on our experiences and share our thoughts on challenges, lessons learned, and recommendations for researchers undertaking or considering research in primary care.MethodsResearchers involved in the Prediction of Undiagnosed atriaL fibrillation using a machinE learning AlgorIthm (PULsE-AI) trial, conducted in England from June 2019 to February 2021 were invited to participate in a qualitative reflection exercise. Members of the Trial Steering Committee (TSC) were invited to attend a semi-structured focus group session, Principal Investigators and their research teams at practices involved in the trial were …

Accurate physical activity monitoring is essential to understand the impact of physical activity on one’s physical health and overall well-being. However, advances in human activity recognition algorithms have been constrained by the limited availability of large labelled datasets. This study aims to leverage recent advances in self-supervised learning to exploit the large-scale UK Biobank accelerometer dataset—a 700,000 person-days unlabelled dataset—in order to build models with vastly improved generalisability and accuracy. Our resulting models consistently outperform strong baselines across eight benchmark datasets, with an F1 relative improvement of 2.5–130.9% (median 24.4%). More importantly, in contrast to previous reports, our results generalise across external datasets, cohorts, living environments, and sensor devices. Our open-sourced pre-trained models will be valuable in domains with limited …

The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering task with answer options for evaluation. However, in real clinical settings, many clinical decisions, such as treatment recommendations, involve answering open-ended questions without pre-set options. Meanwhile, existing studies mainly use accuracy to assess model performance. In this paper, we comprehensively benchmark diverse LLMs in healthcare, to clearly understand their strengths and weaknesses. Our benchmark contains seven tasks and thirteen datasets across medical language generation, understanding, and reasoning. We conduct a detailed evaluation of existing sixteen LLMs in healthcare under both zero-shot and few-shot (i.e., 1,3,5-shot) learning settings. We report the results on five metrics (i.e. matching, faithfulness, comprehensiveness, generalizability, and robustness) that are critical in achieving trust from clinical users. We further invite medical experts to conduct human evaluation.

Electronic Health Records (EHRs) play a crucial role in shaping predictive healthcare models, yet they encounter challenges such as significant data gaps and class imbalances. Traditional Graph Neural Networks (GNNs) approaches have limitations in fully leveraging neighbourhood data or demanding intensive computational regularisation. To address this challenge, we introduce CliqueFluxNet, a novel framework that innovatively constructs a patient similarity graph to maximise cliques, thereby highlighting strong inter-patient connections. At the heart of CliqueFluxNet lies its stochastic edge fluxing strategy—a dynamic process involving random edge addition and removal during training. This strategy aims to enhance the model's generalizability and mitigate overfitting. Our empirical analysis, conducted on MIMIC-III and eICU datasets, demonstrates significant progress in representation learning, particularly in scenarios with limited data availability. Qualitative assessments further underscore CliqueFluxNet’s effectiveness in extracting meaningful EHR representations, solidifying its potential for advancing GNN applications in healthcare analytics.

The lack of data democratization and information leakage from trained models hinder the development and acceptance of robust deep learning-based healthcare solutions. This paper argues that irreversible data encoding can provide an effective solution to achieve data democratization without violating the privacy constraints imposed on healthcare data and clinical models. An ideal encoding framework transforms the data into a new space where it is imperceptible to a manual or computational inspection. However, encoded data should preserve the semantics of the original data such that deep learning models can be trained effectively. This paper hypothesizes the characteristics of the desired encoding framework and then exploits random projections and random quantum encoding to realize this framework for dense and longitudinal or time-series data. Experimental evaluation highlights that models trained on …

Utilizing large pre-trained models for specific tasks has yielded impressive results. However, fully finetuning these increasingly large models is becoming prohibitively resource-intensive. This has led to a focus on more parameterefficient transfer learning, primarily within the same modality. But this approach has limitations, particularly in video understanding where suitable pre-trained models are less common. Addressing this, our study introduces a novel cross-modality transfer learning approach from images to videos, which we call parameter-efficient image-to-video transfer learning. We present the Facial-Emotion Adapter (FE-Adapter), designed for efficient fine-tuning in video tasks. This adapter allows pre-trained image models, which traditionally lack temporal processing capabilities, to analyze dynamic video content efficiently. Notably, it uses about 15 times fewer parameters than previous methods, while improving accuracy. Our experiments in video emotion recognition demonstrate that the FE-Adapter can match or even surpass existing fine-tuning and video emotion models in both performance and efficiency. This breakthrough highlights the potential for cross-modality approaches in enhancing the capabilities of AI models, particularly in fields like video emotion analysis where the demand for efficiency and accuracy is constantly rising.

Retinal fundus imaging is a powerful tool for disease screening and diagnosis in opthalmology. With the advent of machine learning and artificial intelligence, in particular modern computer vision classification algorithms, there is broad scope for technology to improve accuracy, increase accessibility and reduce cost in these processes. In this paper we present the first deep learning model trained on the first Brazilian multi-label opthalmological datatset. We train a multi-label classifier using over 16,000 clinically-labelled fundus images. Across a range of 13 retinal diseases, we obtain frequency-weighted AUC and F1 scores of 0.92 and 0.70 respectively. Our work establishes a baseline model on this new dataset and furthermore demonstrates the applicability and power of artificial intelligence approaches to retinal fundus disease diagnosis in under-represented populations.

Electrocardiogram (ECG) is widely considered the primary test for evaluating cardiovascular diseases. However, the use of artificial intelligence to advance these medical practices and learn new clinical insights from ECGs remains largely unexplored. Utilising a dataset of 2,322,513 ECGs collected from 1,558,772 patients with 7 years of follow-up, we developed a deep learning model with state-of-the-art granularity for the interpretable diagnosis of cardiac abnormalities, gender identification, and hyper- tension screening solely from ECGs, which are then used to stratify the risk of mortality. The model achieved the area under the receiver operating characteristic curve (AUC) scores of 0.998 (95% confidence interval (CI), 0.995-0.999), 0.964 (0.963-0.965), and 0.839 (0.837-0.841) for the three diagnostic tasks separately. Using ECG-predicted results, we find high risks of mortality for subjects with sinus …

BackgroundMulticentre training could reduce biases in medical artificial intelligence (AI); however, ethical, legal, and technical considerations can constrain the ability of hospitals to share data. Federated learning enables institutions to participate in algorithm development while retaining custody of their data but uptake in hospitals has been limited, possibly as deployment requires specialist software and technical expertise at each site. We previously developed an artificial intelligence-driven screening test for COVID-19 in emergency departments, known as CURIAL-Lab, which uses vital signs and blood tests that are routinely available within 1 h of a patient's arrival. Here we aimed to federate our COVID-19 screening test by developing an easy-to-use embedded system—which we introduce as full-stack federated learning—to train and evaluate machine learning models across four UK hospital groups without …

RationaleIntensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with Early Warning Score (EWS) systems being used to identify those at risk of deterioration.ObjectivesWe report the development and validation of an enhanced continuous scoring system for predicting adverse events, which combines vital signs measured routinely on acute care wards (as used by most EWS systems) with a risk score of a future adverse event calculated on discharge from the ICU.DesignA modified Delphi process identified candidate variables commonly available in electronic records as the basis for a ‘static’ score of the patient’s condition immediately after discharge from the ICU. L1-regularised logistic regression was used to estimate the in-hospital risk of future adverse event. We then …

Collaborative efforts in artificial intelligence (AI) are increasingly common between high-income countries (HICs) and low- to middle-income countries (LMICs). Given the resource limitations often encountered by LMICs, collaboration becomes crucial for pooling resources, expertise, and knowledge. Despite the apparent advantages, ensuring the fairness and equity of these collaborative models is essential, especially considering the distinct differences between LMIC and HIC hospitals. In this study, we show that collaborative AI approaches can lead to divergent performance outcomes across HIC and LMIC settings, particularly in the presence of data imbalances. Through a real-world COVID-19 screening case study, we demonstrate that implementing algorithmic-level bias mitigation methods significantly improves outcome fairness between HIC and LMIC sites while maintaining high diagnostic sensitivity. We compare our results against previous benchmarks, utilizing datasets from four independent United Kingdom Hospitals and one Vietnamese hospital, representing HIC and LMIC settings, respectively.