Imperial College London

ProfessorPayamBarnaghi

Faculty of MedicineDepartment of Brain Sciences

Chair in Machine Intelligence Applied to Medicine
 
 
 
//

Contact

 

p.barnaghi Website

 
 
//

Location

 

Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Publication Type
Year
to

165 results found

Huang Y, Zhao Y, Capstick A, Palermo F, Haddadi H, Barnaghi Pet al., 2024, Analyzing entropy features in time-series data for pattern recognition in neurological conditions., Artif Intell Med, Vol: 150

In the field of medical diagnosis and patient monitoring, effective pattern recognition in neurological time-series data is essential. Traditional methods predominantly based on statistical or probabilistic learning and inference often struggle with multivariate, multi-source, state-varying, and noisy data while also posing privacy risks due to excessive information collection and modeling. Furthermore, these methods often overlook critical statistical information, such as the distribution of data points and inherent uncertainties. To address these challenges, we introduce an information theory-based pipeline that leverages specialized features to identify patterns in neurological time-series data while minimizing privacy risks. We incorporate various entropy methods based on the characteristics of different scenarios and entropy. For stochastic state transition applications, we incorporate Shannon's entropy, entropy rates, entropy production, and the von Neumann entropy of Markov chains. When state modeling is impractical, we select and employ approximate entropy, increment entropy, dispersion entropy, phase entropy, and slope entropy. The pipeline's effectiveness and scalability are demonstrated through pattern analysis in a dementia care dataset and also an epileptic and a myocardial infarction dataset. The results indicate that our information theory-based pipeline can achieve average performance improvements across various models on the recall rate, F1 score, and accuracy by up to 13.08 percentage points, while enhancing inference efficiency by reducing the number of model parameters by an average of 3.10 times. Thus, our approach opens a promising avenue for improved, efficient, and critical statistical information-considered pattern recognition in medical time-series data.

Journal article

Capstick A, Palermo F, Zakka K, Fletcher-Lloyd N, Walsh C, Cui T, Kouchaki S, Jackson R, Tran M, Crone M, Jensen K, Freemont P, Vaidyanathan R, Kolanko M, True J, Daniels S, Wingfield D, Nilforooshan R, Barnaghi Pet al., 2024, Digital remote monitoring for screening and early detection of urinary tract infections, npj Digital Medicine, Vol: 7, ISSN: 2398-6352

Urinary Tract Infections (UTIs) are one of the most prevalent bacterial infections in older adults and a significant contributor to unplanned hospital admissions in People Living with Dementia (PLWD), with early detection being crucial due to the predicament of reporting symptoms and limited help-seeking behaviour. The most common diagnostic tool is urine sample analysis, which can be time-consuming and is only employed where UTI clinical suspicion exists. In this method development and proof-of-concept study, participants living with dementia were monitored via low-cost devices in the home that passively measure activity, sleep, and nocturnal physiology. Using 27828 person-days of remote monitoring data (from 117 participants), we engineered features representing symptoms used for diagnosing a UTI. We then evaluate explainable machine learning techniques in passively calculating UTI risk and perform stratification on scores to support clinical translation and allow control over the balance between alert rate and sensitivity and specificity. The proposed UTI algorithm achieves a sensitivity of 65.3% (95% Confidence Interval (CI) = 64.3–66.2) and specificity of 70.9% (68.6–73.1) when predicting UTIs on unseen participants and after risk stratification, a sensitivity of 74.7% (67.9–81.5) and specificity of 87.9% (85.0–90.9). In addition, feature importance methods reveal that the largest contributions to the predictions were bathroom visit statistics, night-time respiratory rate, and the number of previous UTI events, aligning with the literature. Our machine learning method alerts clinicians of UTI risk in subjects, enabling earlier detection and enhanced screening when considering treatment.

Journal article

Singh S, Wu Y, Mohan Rao GNS, Joshi K, Barnaghi P, Kanagarathinam MRet al., 2024, AI in Wireless for Beyond 5G Networks, ISBN: 9781032301211

Artificial intelligence (AI) is a game changer in many domains, and wireless communication networks are no exception. With the advent of 5G networks, we have witnessed rapid growth in wireless connectivity, which has led to unprecedented opportunities for innovation and new use cases. However, as we move beyond 5G (B5G), the challenges and opportunities are set to become even more significant, offering new, previously unimaginable services. AI in Wireless for Beyond 5G Networks provides a comprehensive overview of the use of AI in wireless communication for B5G networks. The authors draw on their expertise in the field to explore the latest developments in AI technologies and their applications in B5G wireless communication systems. The book discusses a wide range of topics, including enabling AI technologies, architecture, and applications of AI from smartphones, radio access networks (RANs), edge and core networks, and application service providers. It also discusses the trends in on-device AI for B5G networks. This book is written in an accessible style, making it an ideal resource for academics, researchers, and industry professionals in wireless communication. It provides valuable insights into the latest field trends and developments and practical possibilities for implementing AI technologies in wireless communication systems. Above all, this book is a testament to the power of collaboration and innovation in wireless communication. The authors’ dedication and expertise have produced a valuable resource for anyone interested in the latest AI and wireless communication developments. This book will inspire and inform readers, and we highly recommend it to scholars interested in the future of AI in wireless communication.

Book

Raposo de Lima M, Vaidyanathan R, Barnaghi P, 2023, Discovering behavioural patterns using conversational technology for in-home health and well-being monitoring, IEEE Internet of Things Journal, Vol: 10, Pages: 18537-18552, ISSN: 2327-4662

Advancements in conversational AI have createdunparalleled opportunities to promote the independence andwell-being of older adults, including people living with dementia(PLWD). However, conversational agents have yet to demonstratea direct impact in supporting target populations at home,particularly with long-term user benefits and clinical utility. Weintroduce an infrastructure fusing in-home activity data capturedby Internet of Things (IoT) technologies with voice interactionsusing conversational technology (Amazon Alexa). We collect 3103person-days of voice and environmental data across 14 households with PLWD to identify behavioural patterns. Interactionsinclude an automated well-being questionnaire and 10 topics ofinterest, identified using topic modelling. Although a significantdecrease in conversational technology usage was observed afterthe novelty phase across the cohort, steady state data acquisitionfor modelling was sustained. We analyse household activitysequences preceding or following Alexa interactions throughpairwise similarity and clustering methods. Our analysis demonstrates the capability to identify individual behavioural patterns,changes in those patterns and the corresponding time periods.We further report that households with PLWD continued usingAlexa following clinical events (e.g., hospitalisations), which offersa compelling opportunity for proactive health and well-beingdata gathering related to medical changes. Results demonstratethe promise of conversational AI in digital health monitoringfor ageing and dementia support and offer a basis for trackinghealth and deterioration as indicated by household activity, whichcan inform healthcare professionals and relevant stakeholdersfor timely interventions. Future work will use the bespokebehavioural patterns extracted to create more personalised AIconversations.

Journal article

Palermo F, Chen Y, Capstick A, Fletcher-Lloyd N, Walsh C, Kouchaki S, Jessica T, Balazikova O, Soreq E, Scott G, Rostill H, Nilforooshan R, Barnaghi Pet al., 2023, TIHM: an open dataset for remote healthcare monitoring in dementia, Scientific Data, Vol: 10, Pages: 1-10, ISSN: 2052-4463

Dementia is a progressive condition that affects cognitive and functional abilities. There is a need for reliable and continuous health monitoring of People Living with Dementia (PLWD) to improve their quality of life and support their independent living. Healthcare services often focus on addressing and treating already established health conditions that affect PLWD. Managing these conditions continuously can inform better decision-making earlier for higher-quality care management for PLWD. The Technology Integrated Health Management (TIHM) project developed a new digital platform to routinely collect longitudinal, observational, and measurement data, within the home and apply machine learning and analytical models for the detection and prediction of adverse health events affecting the well-being of PLWD. This work describes the TIHM dataset collected during the second phase (i.e., feasibility study) of the TIHM project. The data was collected from homes of 56 PLWD and associated with events and clinical observations (daily activity, physiological monitoring, and labels for health-related conditions). The study recorded an average of 50 days of data per participant, totalling 2803 days.

Journal article

Parkinson M, Doherty R, Curtis F, Soreq E, Lai HHL, Serban A-I, Dani M, Fertleman M, Barnaghi PJ, Sharp DM, Li Let al., 2023, Using home monitoring technology to study the effects of traumatic brain injury in older multimorbid adults, Annals of Clinical and Translational Neurology, Vol: 10, Pages: 1688-1694, ISSN: 2328-9503

Internet of things (IOT) based in-home monitoring systems can passively collect high temporal resolution data in the community, offering valuable insight into the impact of health conditions on patients' day-to-day lives. We used this technology to monitor activity and sleep patterns in older adults recently discharged after traumatic brain injury (TBI). The demographics of TBI are changing, and it is now a leading cause of hospitalisation in older adults. However, research in this population is minimal. We present three cases, showcasing the potential of in-home monitoring systems in understanding and managing early recovery in older adults following TBI.

Journal article

Hine C, Nilforooshan R, Barnaghi P, 2023, Negotiating the capacities and limitations of sensor-mediated care in the home, JOURNAL OF COMPUTER-MEDIATED COMMUNICATION, Vol: 28, ISSN: 1083-6101

Journal article

Papachristou N, Kotronoulas G, Dikaios N, Allison SJ, Eleftherochorinou H, Rai T, Kunz H, Barnaghi P, Miaskowski C, Bamidis PDet al., 2023, Digital transformation of cancer care in the era of big data, artificial intelligence and data-driven interventions: navigating the field, Seminars in Oncology Nursing, Vol: 39, ISSN: 0749-2081

OBJECTIVES: To navigate the field of digital cancer care and define and discuss key aspects and applications of big data analytics, artificial intelligence (AI), and data-driven interventions. DATA SOURCES: Peer-reviewed scientific publications and expert opinion. CONCLUSION: The digital transformation of cancer care, enabled by big data analytics, AI, and data-driven interventions, presents a significant opportunity to revolutionize the field. An increased understanding of the lifecycle and ethics of data-driven interventions will enhance development of innovative and applicable products to advance digital cancer care services. IMPLICATIONS FOR NURSING PRACTICE: As digital technologies become integrated into cancer care, nurse practitioners and scientists will be required to increase their knowledge and skills to effectively use these tools to the patient's benefit. An enhanced understanding of the core concepts of AI and big data, confident use of digital health platforms, and ability to interpret the outputs of data-driven interventions are key competencies. Nurses in oncology will play a crucial role in patient education around big data and AI, with a focus on addressing any arising questions, concerns, or misconceptions to foster trust in these technologies. Successful integration of data-driven innovations into oncology nursing practice will empower practitioners to deliver more personalized, effective, and evidence-based care.

Journal article

Rassam A, Barnaghi P, 2023, Methods and apparatus for adaptive interaction with remote devices, US20200119938A1

Patent

Parkinson M, Dani M, Fertleman M, Soreq E, Barnaghi P, Sharp D, Li LMet al., 2023, Using home monitoring technology to study the effects of traumatic brain Injury in older multimorbid adults: protocol for a feasibility study, BMJ Open, Vol: 13, ISSN: 2044-6055

Introduction:The prevalence of Traumatic Brain Injury (TBI) among older adults is increasing exponentially. The sequelae can be severe in older adults and interacts with age-related conditions such a multimorbidity. Despite this, TBI research in older adults, is sparse. Minder, an in-home monitoring system using developed by the UK DRI Centre for Care Research and Technology, uses infra-red sensors and a bed mat to passively collect sleep and activity data. Similar systems have been used to monitor the health of older adults living with dementia. We will assess the feasibility of using this system to study changes in the health status of older adults in the early period post TBI.Methods and analysis:The study will recruit 15 inpatients (>60 years) with a moderate-severe TBI, who will have their daily activity and sleep patterns monitored using passive and wearable sensors over 6 months. Participants will report on their health during weekly calls, which will be used to validate sensor data. Physical, functional, and cognitive assessments will be conducted across the duration of the study. Activity levels and sleep patterns derived from sensor data will be calculated and visualised using activity maps. Within participant analysis will be performed to determine if participants are deviating from their own routines. We will apply machine learning approaches to activity and sleep data to assess whether these changes in these data can predict clinical events. Qualitative analysis of interviews conducted with participants, carers, and clinical staff will assess acceptability and utility of the system.Ethics and dissemination:Ethical approval for this study has been granted by the London - Camberwell St Giles Research Ethics Committee (REC number: 17/LO/2066). Results will be submitted for publication in peer review journals, presented at conferences and inform the design of a larger trial assessing recovery after TBI.

Journal article

David MCB, Kolanko M, Del Giovane M, Lai H, True J, Beal E, Li LM, Nilforooshan R, Barnaghi P, Malhotra PA, Rostill H, Wingfield D, Wilson D, Daniels S, Sharp DJ, Scott Get al., 2023, Remote monitoring of physiology in people living with dementia: an observational cohort study, JMIR Aging, Vol: 6, Pages: 1-14, ISSN: 2561-7605

BACKGROUND: Internet of Things (IoT) technology enables physiological measurements to be recorded at home from people living with dementia and monitored remotely. However, measurements from people with dementia in this context have not been previously studied. We report on the distribution of physiological measurements from 82 people with dementia over approximately 2 years. OBJECTIVE: Our objective was to characterize the physiology of people with dementia when measured in the context of their own homes. We also wanted to explore the possible use of an alerts-based system for detecting health deterioration and discuss the potential applications and limitations of this kind of system. METHODS: We performed a longitudinal community-based cohort study of people with dementia using "Minder," our IoT remote monitoring platform. All people with dementia received a blood pressure machine for systolic and diastolic blood pressure, a pulse oximeter measuring oxygen saturation and heart rate, body weight scales, and a thermometer, and were asked to use each device once a day at any time. Timings, distributions, and abnormalities in measurements were examined, including the rate of significant abnormalities ("alerts") defined by various standardized criteria. We used our own study criteria for alerts and compared them with the National Early Warning Score 2 criteria. RESULTS: A total of 82 people with dementia, with a mean age of 80.4 (SD 7.8) years, recorded 147,203 measurements over 958,000 participant-hours. The median percentage of days when any participant took any measurements (ie, any device) was 56.2% (IQR 33.2%-83.7%, range 2.3%-100%). Reassuringly, engagement of people with dementia with the system did not wane with time, reflected in there being no change in the weekly number of measurements with respect to time (1-sample t-test on slopes of linear fit, P=.45). A total of 45% of people with dementia met criteria for hypertension. People with dem

Journal article

Parkinson M, Doherty R, Curtis F, Dani M, Fertleman M, Kolanko M, Soreq E, Barnaghi P, Sharp D, Li LMet al., 2023, 1415 Novel approaches to post discharge care.remote healthcare monitoring systems following traumatic brain injury in older adults, British Geriatrics Society Autumn Meeting 2022, Publisher: Oxford University Press, ISSN: 0002-0729

Conference paper

Curtis F, Li L, Kolanko M, Lai H, Daniels S, True J, Del Giovane M, Golemme M, Lyall P, Raza S, Hassim N, Patel A, Beal E, Walsh C, Purnell M, Whitethread N, Nilforooshan R, Norman C, Wingfield D, Barnaghi P, Sharp D, Dani M, Fertleman M, Parknson Met al., 2023, 1362 Anticholinergic prescribing habits and its associations in a community population of people living with dementia, British Geriatrics Society Autumn Meeting 2022, Publisher: Oxford University Press, ISSN: 0002-0729

Conference paper

Pourshahrokhi N, Li Y, Kouchaki S, Barnaghi Pet al., 2023, Folded Hamiltonian Monte Carlo for Bayesian Generative Adversarial Networks, Pages: 1103-1118

Probabilistic modelling on Generative Adversarial Networks (GANs) within the Bayesian framework has shown success in estimating the complex distribution in literature. In this paper, we develop a Bayesian formulation for unsupervised and semi-supervised GAN learning. Specifically, we propose Folded Hamiltonian Monte Carlo (F-HMC) methods within this framework to learn the distributions over the parameters of the generators and discriminators. We show that the F-HMC efficiently approximates multi-modal and high dimensional data when combined with Bayesian GANs. Its composition improves run time and test error in generating diverse samples. Experimental results with high-dimensional synthetic multi-modal data and natural image benchmarks, including CIFAR-10, SVHN and ImageNet, show that F-HMC outperforms the state-of-the-art methods in terms of test error, run times per epoch, inception score and Frechet Inception Distance scores.

Conference paper

Fletcher-Lloyd N, Serban A-I, Kolanko M, Wingfield D, Wilson D, Nilforooshan R, Barnaghi P, Soreq Eet al., 2023, A Markov chain model for identifying changes in daily activity patterns of people living with dementia, IEEE Internet of Things Journal, ISSN: 2327-4662

Malnutrition and dehydration are strongly associated with increased cognitive and functional decline in people living with dementia (PLWD), as well as an increased rate of hospitalisations in comparison to their healthy counterparts. Extreme changes in eating and drinking behaviours can often lead to malnutrition and dehydration, accelerating the progression of cognitive and functional decline and resulting in a marked reduction in quality of life. Unfortunately, there are currently no established methods by which to objectively detect such changes. Here, we present the findings of an extensive quantitative analysis conducted on in-home monitoring data collected from 73 households of PLWD using Internet of Things technologies. The Coronavirus 2019 (COVID-19) pandemic has previously been shown to have dramatically altered the behavioural habits, particularly the eating and drinking habits, of PLWD. Using the COVID-19 pandemic as a natural experiment, we conducted linear mixed-effects modelling to examine changes in mean kitchen activity within a subset of 21 households of PLWD that were continuously monitored for 499 days. We report an observable increase in day-time kitchen activity and a significant decrease in night-time kitchen activity (t(147) = -2.90, p < 0.001). We further propose a novel analytical approach to detecting changes in behaviours of PLWD using Markov modelling applied to remote monitoring data as a proxy for behaviours that cannot be directly measured. Together, these results pave the way to introduce improvements into the monitoring of PLWD in naturalistic settings and for shifting from reactive to proactive care.

Journal article

Lima MR, Wairagkar M, Gupta M, Baena FRY, Barnaghi P, Sharp DJ, Vaidyanathan Ret al., 2022, Conversational affective social robots for ageing and dementia support, IEEE Transactions on Cognitive and Developmental Systems, Vol: 14, Pages: 1378-1397, ISSN: 2379-8920

Socially assistive robots (SAR) hold significant potential to assist older adults and people with dementia in human engagement and clinical contexts by supporting mental health and independence at home. While SAR research has recently experienced prolific growth, long-term trust, clinical translation and patient benefit remain immature. Affective human-robot interactions are unresolved and the deployment of robots with conversational abilities is fundamental for robustness and humanrobot engagement. In this paper, we review the state of the art within the past two decades, design trends, and current applications of conversational affective SAR for ageing and dementia support. A horizon scanning of AI voice technology for healthcare, including ubiquitous smart speakers, is further introduced to address current gaps inhibiting home use. We discuss the role of user-centred approaches in the design of voice systems, including the capacity to handle communication breakdowns for effective use by target populations. We summarise the state of development in interactions using speech and natural language processing, which forms a baseline for longitudinal health monitoring and cognitive assessment. Drawing from this foundation, we identify open challenges and propose future directions to advance conversational affective social robots for: 1) user engagement, 2) deployment in real-world settings, and 3) clinical translation.

Journal article

Soreq E, Kolanko MA, Monica CD, Ravindran KKG, Revell VL, de Villèle P, Barnaghi P, Dijk D-J, Sharp DJ, CRT groupet al., 2022, Monitoring abnormal nocturnal behaviour in the homes of patients living with dementia., Alzheimers Dement, Vol: 18 Suppl 2

BACKGROUND: People living with dementia (PLWD) often exhibit marked sleep disturbances. These cause substantial care challenges and may be causally related to dementia progression. Collecting ecologically valid data on sleep disturbance in naturalistic settings has been difficult. As a result, sleep assessments in PLWD are generally limited to short studies in sleep laboratories or data collection from wearables, where compliance is problematic. Here, we demonstrate how passive internet of things (IoT) sensors can be used to monitor the effects of dementia on nocturnal behaviour and physiology. METHOD: Using the Withings under-mattress pressure sensor, we validated bed occupancy and physiological measures in 35 older adults tested both at home and in the laboratory. We then examined data collected between 2019 and 2021 from the general population (N=13,663) and from a cohort of PLWD taking part in the UK DRI study of home monitoring for PLWD (N=46). More than 4 million unique bed mat observations were analysed. RESULT: Arise time across all subjects was negatively correlated with time to bed (Fig.1a, r(13,617) =-0.5, p<.0001). Bed occupancy increased with age, but PLWD spent more time in bed than age-matched controls (Fig.1b) and had more nocturnal awakenings (Fig.1c). Explainable gradient boosting machine learning was successfully used to classify data from individual nights (PLWD vs. general population). PLWD probability was related to specific changes, such as increased awakenings, high or low time spent in bed, high heart rate and low breathing rate (Fig.2). We also explored variations in night-time behaviour and physiology over time for individual PLWD (Fig.3a). High within-subject variability was present, which related to disease progression, intercurrent illness and changes in medication. Data from each night was transformed into a risk score for each metric (Fig.3b) and a compound risk score. These quantify the risk of abnormal night-time behaviour and ph

Journal article

Kolanko MA, Soreq E, Lai H, Barnaghi P, Dijk D-J, Sharp DJet al., 2022, Clinically relevant monitoring of long-term night-time behaviour and physiology from the homes of people living with dementia., Alzheimers Dement, Vol: 18 Suppl 2

BACKGROUND: Disturbances of sleep and night-time behaviours are amongst the most disabling symptoms of dementia. They often increase carers' burden and the risk of institutionalization. The causes are complex and are difficult to investigate because of a lack of acceptable methods for monitoring behaviours in the home. Here we show that a passive under-mattress can be used to track changes in night-time behaviour and physiology, and that a range of digital biomarkers produced are informative in understanding the effects of medication changes, disease progression and intercurrent illness in patients living with dementia (PLWD). METHOD: We used contactless Withings Sleep Mattress (WSM) to monitor bed-occupancy in 4 PLWD (age 74-93, 3males) enrolled into the CR&T MINDER cohort study. Each participant was tracked over 1000 nights between 2019 and 2021. Minute-to-minute timeseries were extracted from WSM to calculate bed occupancy metrics and nocturnal physiology measures (heart and breathing rates (HR/BR)). Raw measures were standardized within subjects by comparing each time point to the mean of the time points that preceded it. We then investigated the relationship between these metrics and clinical events such as infections and medication. RESULT: The 4 case studies illustrate the potential of this technology for passive health monitoring in PLWD. High levels of intraindividual variability in behavioural and physiological metrics were observed. Progressive changes in bed occupancy were observed in two patients with frontotemporal dementia and Alzheimer's disease (Cases 1&2). Intercurrent illness and medications changes influenced the measures. For example, Patient 1 showed progressive night-time wandering with increasing time spent out of bed, which improved following the initiation of risperidone. Case 2 showed recurrent episodes of heart failure accompanied by increased nocturnal HR. Cases 3 and 4 showed urinary tract infections, which were accompanied by t

Journal article

Huang Y, Zhao Y, Haddadi H, Barnaghi Pet al., 2022, Using entropy measures for monitoring the evolution of activity patterns, IEEE 8th World Forum on Internet of Things, Publisher: IEEE

In this work, we apply information theory inspired methods to quantifychanges in daily activity patterns. We use in-home movement monitoring data andshow how they can help indicate the occurrence of healthcare-related events.Three different types of entropy measures namely Shannon's entropy, entropyrates for Markov chains, and entropy production rate have been utilised. Themeasures are evaluated on a large-scale in-home monitoring dataset that hasbeen collected within our dementia care clinical study. The study uses Internetof Things (IoT) enabled solutions for continuous monitoring of in-homeactivity, sleep, and physiology to develop care and early interventionsolutions to support people living with dementia (PLWD) in their own homes. Ourmain goal is to show the applicability of the entropy measures to time-seriesactivity data analysis and to use the extracted measures as new engineeredfeatures that can be fed into inference and analysis models. The results of ourexperiments show that in most cases the combination of these measures canindicate the occurrence of healthcare-related events. We also find thatdifferent participants with the same events may have different measures basedon one entropy measure. So using a combination of these measures in aninference model will be more effective than any of the single measures.

Conference paper

Serban A-I, Soreq E, Barnaghi P, Daniels S, Calvo R, Sharp Det al., 2022, The effect of COVID-19 on the home behaviours of people affected by dementia, npj Digital Medicine, Vol: 5, ISSN: 2398-6352

The COVID-19 pandemic has dramatically altered the behaviour of most of the world’s population, particularly affecting the elderly, including people living with dementia (PLwD). Here we use remote home monitoring technology deployed into 31 homes of PLwD living in the UK to investigate the effects of COVID-19 on behaviour within the home, including social isolation. The home activity was monitored continuously using unobtrusive sensors for 498 days from 1 December 2019 to 12 April 2021. This period included six distinct pandemic phases with differing public health measures, including three periods of home ‘lockdown’. Linear mixed-effects modelling is used to examine changes in the home activity of PLwD who lived alone or with others. An algorithm is developed to quantify time spent outside the home. Increased home activity is observed from very early in the pandemic, with a significant decrease in the time spent outside produced by the first lockdown. The study demonstrates the effects of COVID-19 lockdown on home behaviours in PLwD and shows how unobtrusive home monitoring can be used to track behaviours relevant to social isolation.

Journal article

Kalantari E, Kouchaki S, Miaskowski C, Kober K, Barnaghi Pet al., 2022, Network analysis to identify symptoms clusters and temporal interconnections in oncology patients, Scientific Reports, Vol: 12, ISSN: 2045-2322

Oncology patients experience numerous co-occurring symptoms during their treatment. The identification of sentinel/core symptoms is a vital prerequisite for therapeutic interventions. In this study, using Network Analysis, we investigated the inter-relationships among 38 common symptoms over time (i.e., a total of six time points over two cycles of chemotherapy) in 987 oncology patients with four different types of cancer (i.e., breast, gastrointestinal, gynaecological, and lung). In addition, we evaluated the associations between and among symptoms and symptoms clusters and examined the strength of these interactions over time. Eight unique symptom clusters were identified within the networks. Findings from this research suggest that changes occur in the relationships and interconnections between and among co-occurring symptoms and symptoms clusters that depend on the time point in the chemotherapy cycle and the type of cancer. The evaluation of the centrality measures provides new insights into the relative importance of individual symptoms within various networks that can be considered as potential targets for symptom management interventions.

Journal article

Soreq E, Kolanko M, Guruswamy Ravindran KK, Monica CD, Revell V, Lai H, Barnaghi P, Malhotra P, Dijk D-J, Sharp Det al., 2022, Longitudinal assessment of sleep/wake behaviour in dementia patients living at home, Association-of-British-Neurologists (ABN) Annual Meeting, Publisher: BMJ PUBLISHING GROUP, ISSN: 0022-3050

Conference paper

Parkinson M, Curtis F, Dani M, Fertleman M, Kolanko M, Soreq E, Barnaghi P, Sharp D, Li Let al., 2022, MTBI PREDICT: A PROSPECTIVE BIOMARKER STUDY TO PREDICT OUTCOMES IN MILD TRAUMATIC BRAIN INJURY, Association-of-British-Neurologists (ABN) Annual Meeting, Publisher: BMJ PUBLISHING GROUP, ISSN: 0022-3050

Conference paper

Ngai ECH, Barnaghi P, Kanhere S, Leung VCM, Liu Jet al., 2022, Guest Editorial Special Issue on Green Communications and Networking With Machine Intelligence for Smart Cities, IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING, Vol: 6, Pages: 1588-1590, ISSN: 2473-2400

Journal article

Parkinson M, Curtis F, Dani M, Fertleman M, Kolanko M, Soreq E, Barnaghi P, Sharp D, Li Let al., 2022, EXPLORING INTERACTIONS BETWEEN TRAUMATIC BRAIN INJURY AND COGNITIVE CO-MORBIDITY: DESCRIPTIVE CASE ANALYSIS FROM REAL-WORLD MONITORING, Association-of-British-Neurologists (ABN) Annual Meeting, Publisher: BMJ PUBLISHING GROUP, ISSN: 0022-3050

Conference paper

Zhao Y, Barnaghi P, Haddadi H, 2022, Multimodal federated learning on IoT data, 2022 IEEE/ACM Seventh International Conference on Internet-of-Things Design and Implementation (IoTDI), Publisher: IEEE

Federated learning is proposed as an alternative to centralized machine learning since its client-server structure provides better privacy protection and scalability in real-world applications. In many applications, such as smart homes with Internet-of-Things (IoT) devices, local data on clients are generated from different modalities such as sensory, visual, and audio data. Existing federated learning systems only work on local data from a single modality, which limits the scalability of the systems. In this paper, we propose a multimodal and semi-supervised federated learning framework that trains autoencoders to extract shared or correlated representations from different local data modalities on clients. In addition, we propose a multimodal FedAvg algorithm to aggregate local autoencoders trained on different data modalities. We use the learned global autoencoder for a downstream classification task with the help of auxiliary labelled data on the server. We empirically evaluate our framework on different modalities including sensory data, depth camera videos, and RGB camera videos. Our experimental results demonstrate that introducing data from multiple modalities into federated learning can improve its classification performance. In addition, we can use labelled data from only one modality for supervised learning on the server and apply the learned model to testing data from other modalities to achieve decent F1 scores (e.g., with the best performance being higher than 60%), especially when combining contributions from both unimodal clients and multimodal clients.

Conference paper

Wu Y, Pan Y, Barnaghi P, Tan Z, Ge J, Wang Het al., 2022, Editorial: Big data technologies and applications, WIRELESS NETWORKS, Vol: 28, Pages: 1163-1167, ISSN: 1022-0038

Journal article

Parkinson M, Doherty R, Curtis C, Dani M, Fertleman M, Kolanko MA, Soreq E, Capstick A, Barnaghi P, Sharp D, Li Let al., 2022, Exploring interactions between traumatic brain injury, Association of British Neurologists

Conference paper

Wairagkar M, Lima MR, Bazo D, Craig R, Weissbart H, Etoundi AC, Reichenbach T, Iyenger P, Vaswani S, James C, Barnaghi P, Melhuish C, Vaidyanathan Ret al., 2022, Emotive response to a hybrid-face robot and translation to consumer social robots, IEEE Internet of Things Journal, Vol: 9, Pages: 3174-3188, ISSN: 2327-4662

We present the conceptual formulation, design, fabrication, control and commercial translation of an IoT enabled social robot as mapped through validation of human emotional response to its affective interactions. The robot design centres on a humanoid hybrid-face that integrates a rigid faceplate with a digital display to simplify conveyance of complex facial movements while providing the impression of three-dimensional depth. We map the emotions of the robot to specific facial feature parameters, characterise recognisability of archetypical facial expressions, and introduce pupil dilation as an additional degree of freedom for emotion conveyance. Human interaction experiments demonstrate the ability to effectively convey emotion from the hybrid-robot face to humans. Conveyance is quantified by studying neurophysiological electroencephalography (EEG) response to perceived emotional information as well as through qualitative interviews. Results demonstrate core hybrid-face robotic expressions can be discriminated by humans (80%+ recognition) and invoke face-sensitive neurophysiological event-related potentials such as N170 and Vertex Positive Potentials in EEG. The hybrid-face robot concept has been modified, implemented, and released by Emotix Inc in the commercial IoT robotic platform Miko (‘My Companion’), an affective robot currently in use for human-robot interaction with children. We demonstrate that human EEG responses to Miko emotions are comparative to that of the hybrid-face robot validating design modifications implemented for large scale distribution. Finally, interviews show above 90% expression recognition rates in our commercial robot. We conclude that simplified hybrid-face abstraction conveys emotions effectively and enhances human-robot interaction.

Journal article

Hine C, Nilforooshan R, Barnaghi P, 2022, Ethical considerations in design and implementation of home-based smart care for dementia, Nursing Ethics: an international journal for health care professionals, Vol: 29, Pages: 1035-1046, ISSN: 0969-7330

It has now become a realistic prospect for smart care to be provided at home for those living with long-term conditions such as dementia. In the contemporary smart care scenario, homes are fitted with an array of sensors for remote monitoring providing data that feed into intelligent systems developed to highlight concerning patterns of behaviour or physiological measurements and to alert healthcare professionals to the need for action. This paper explores some ethical issues that may arise within such smart care systems, focusing on the extent to which ethical issues can be addressed at the system design stage. Artificial intelligence has been widely portrayed as an ethically risky technology, posing challenges for privacy and human autonomy and with the potential to introduce and exacerbate bias and inequality. While broad principles for ethical artificial intelligence have become established, the mechanisms for governing ethical artificial intelligence are still evolving. In healthcare settings the implementation of smart technologies falls within the existing frameworks for ethical review and governance. Feeding into this ethical review there are many practical steps that designers can take to build ethical considerations into the technology. After exploring the pre-emptive steps that can be taken in design and governance to provide for an ethical smart care system, the paper reviews the potential for further ethical challenges to arise within the everyday implementation of smart care systems in the context of dementia, despite the best efforts of all concerned to pre-empt them. The paper concludes with an exploration of the dilemmas that may thus face healthcare professionals involved in implementing this kind of smart care and with a call for further research to explore ethical dimensions of smart care both in terms of general principles and lived experience.

Journal article

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=01038862&limit=30&person=true