arXiv subjects

Richard JB Dobson

Publications and source records attributed to Richard JB Dobson.

25 records · Page 2Linked to original sources

arXiv2021

Fitbeat: COVID-19 Estimation based on Wristband Heart Rate

This study investigates the potential of deep learning methods to identify individuals with suspected COVID-19 infection using remotely collected heart-rate data. The study utilises data from the ongoing EU IMI RADAR-CNS research project that is investigating the feasibility of wearable devices and smart phones to monitor individuals with multiple sclerosis (MS), depression or epilepsy. Aspart of the project protocol, heart-rate data was collected from participants using a Fitbit wristband. The presence of COVID-19 in the cohort in this work was either confirmed through a positive swab test, or inferred through the self-reporting of a combination of symptoms including fever, respiratory symptoms, loss of smell or taste, tiredness and gastrointestinal symptoms. Experimental results indicate that our proposed contrastive convolutional auto-encoder (contrastive CAE), i. e., a combined architecture of an auto-encoder and contrastive loss, outperforms a conventional convolutional neural network (CNN), as well as a convolutional auto-encoder (CAE) without using contrastive loss. Our final contrastive CAE achieves 95.3% unweighted average recall, 86.4% precision, anF1 measure of 88.2%, a sensitivity of 100% and a specificity of 90.6% on a testset of 19 participants with MS who reported symptoms of COVID-19. Each of these participants was paired with a participant with MS with no COVID-19 symptoms.

eess.SP↗

arXiv2021

Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkit

Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of Information Extraction (IE) technologies to enable clinical analysis. We present the open-source Medical Concept Annotation Toolkit (MedCAT) that provides: a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; b) a feature-rich annotation interface for customising and training IE models; and c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performance in extracting UMLS concepts from open datasets (F1:0.448-0.738 vs 0.429-0.650). Further real-world validation demonstrates SNOMED-CT extraction at 3 large London hospitals with self-supervised training over ~8.8B words from ~17M clinical records and further fine-tuning with ~6K clinician annotated examples. We show strong transferability (F1 > 0.94) between hospitals, datasets, and concept types indicating cross-domain EHR-agnostic utility for accelerated clinical and research use cases.

cs.CL↗

arXiv2020

The Relationship between Major Depression Symptom Severity and Sleep Collected Using a Wristband Wearable Device: Multi-centre Longitudinal Observational Study

Research in mental health has implicated sleep pathologies with depression. However, the gold standard for sleep assessment, polysomnography, is not suitable for long-term, continuous, monitoring of daily sleep, and methods such as sleep diaries rely on subjective recall, which is qualitative and inaccurate. Wearable devices, on the other hand, provide a low-cost and convenient means to monitor sleep in home settings. The main aim of this study was to devise and extract sleep features, from data collected using a wearable device, and analyse their correlation with depressive symptom severity and sleep quality, as measured by the self-assessed Patient Health Questionnaire 8-item. Daily sleep data were collected passively by Fitbit wristband devices, and depressive symptom severity was self-reported every two weeks by the PHQ-8. The data used in this paper included 2,812 PHQ-8 records from 368 participants recruited from three study sites in the Netherlands, Spain, and the UK.We extracted 21 sleep features from Fitbit data which describe sleep in the following five aspects: sleep architecture, sleep stability, sleep quality, insomnia, and hypersomnia. Linear mixed regression models were used to explore associations between sleep features and depressive symptom severity. The z-test was used to evaluate the significance of the coefficient of each feature. We tested our models on the entire dataset and individually on the data of three different study sites. We identified 16 sleep features that were significantly correlated with the PHQ-8 score on the entire dataset. Associations between sleep features and the PHQ-8 score varied across different sites, possibly due to the difference in the populations.

stat.AP↗

arXiv2020

Measuring the effect of Non-Pharmaceutical Interventions (NPIs) on mobility during the COVID-19 pandemic using global mobility data

The implementation of governmental Non-Pharmaceutical Interventions (NPIs) has been the primary means of controlling the spread of the COVID-19 disease. The intended effect of these NPIs has been to reduce mobility. A strong reduction in mobility is believed to have a positive effect on the reduction of COVID-19 transmission by limiting the opportunity for the virus to spread in the population. Due to the huge costs of implementing these NPIs, it is essential to have a good understanding of their efficacy. Using global mobility data, released by Apple and Google, and ACAPS NPI data, we investigate the proportional contribution of NPIs on i) size of the change (magnitude) of transition between pre- and post-lockdown mobility levels and ii) rate (gradient) of this transition. Using generalized linear models to find the best fit model we found similar results using Apple or Google data. NPIs found to impact the magnitude of the change in mobility were: Lockdown measures (Apple, Google Retail and Recreation (RAR) and Google Transit and Stations (TS)), declaring a state of emergency (Apple, Google RAR and Google TS), closure of businesses and public services (Google RAR) and school closures (Apple). Using cluster analysis and chi square tests we found that closure of businesses and public services, school closures and limiting public gatherings as well as border closures and international flight suspensions were closely related. The implementation of lockdown measures and limiting public gatherings had the greatest effect on the rate of mobility change. In conclusion, we were able to quantitatively assess the efficacy of NPIs in reducing mobility, which enables us to understand their fine grained effects in a timely manner and therefore facilitate well-informed and cost-effective interventions.

physics.soc-ph↗

arXiv2020

Using smartphones and wearable devices to monitor behavioural changes during COVID-19

We aimed to explore the utility of the recently developed open-source mobile health platform RADAR-base as a toolbox to rapidly test the effect and response to NPIs aimed at limiting the spread of COVID-19. We analysed data extracted from smartphone and wearable devices and managed by the RADAR-base from 1062 participants recruited in Italy, Spain, Denmark, the UK, and the Netherlands. We derived nine features on a daily basis including time spent at home, maximum distance travelled from home, maximum number of Bluetooth-enabled nearby devices (as a proxy for physical distancing), step count, average heart rate, sleep duration, bedtime, phone unlock duration, and social app use duration. We performed Kruskal-Wallis tests followed by post-hoc Dunns tests to assess differences in these features among baseline, pre-, and during-lockdown periods. We also studied behavioural differences by age, gender, body mass index (BMI), and educational background. We were able to quantify expected changes in time spent at home, distance travelled, and the number of nearby Bluetooth-enabled devices between pre- and during-lockdown periods. We saw reduced sociality as measured through mobility features, and increased virtual sociality through phone usage. People were more active on their phones, spending more time using social media apps, particularly around major news events. Furthermore, participants had lower heart rate, went to bed later, and slept more. We also found that young people had longer homestay than older people during lockdown and fewer daily steps. Although there was no significant difference between the high and low BMI groups in time spent at home, the low BMI group walked more. RADAR-base can be used to rapidly quantify and provide a holistic view of behavioural changes in response to public health interventions as a result of infectious outbreaks such as COVID-19.

q-bio.QM↗

arXiv2020

Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset

Clinical coding is currently a labour-intensive, error-prone, but critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new state of the art results. A popular dataset used in this task is MIMIC-III, a large intensive care database that includes clinical free text notes and associated codes. We argue for the reconsideration of the validity MIMIC-III's assigned codes that are often treated as gold-standard, especially when MIMIC-III has not undergone secondary validation. This work presents an open-source, reproducible experimental methodology for assessing the validity of codes derived from EHR discharge summaries. We exemplify the methodology with MIMIC-III discharge summaries and show the most frequently assigned codes in MIMIC-III are under-coded up to 35%.

cs.LG↗

arXiv2019

Efficiently Reusing Natural Language Processing Models for Phenotype-Mention Identification in Free-text Electronic Medical Records: Methodology Study

Background: Many efforts have been put into the use of automated approaches, such as natural language processing (NLP), to mine or extract data from free-text medical records to construct comprehensive patient profiles for delivering better health-care. Reusing NLP models in new settings, however, remains cumbersome - requiring validation and/or retraining on new data iteratively to achieve convergent results. Objective: The aim of this work is to minimize the effort involved in reusing NLP models on free-text medical records. Methods: We formally define and analyse the model adaptation problem in phenotype-mention identification tasks. We identify "duplicate waste" and "imbalance waste", which collectively impede efficient model reuse. We propose a phenotype embedding based approach to minimize these sources of waste without the need for labelled data from new settings. Results: We conduct experiments on data from a large mental health registry to reuse NLP models in four phenotype-mention identification tasks. The proposed approach can choose the best model for a new task, identifying up to 76% (duplicate waste), i.e. phenotype mentions without the need for validation and model retraining, and with very good performance (93-97% accuracy). It can also provide guidance for validating and retraining the selected model for novel language patterns in new tasks, saving around 80% (imbalance waste), i.e. the effort required in "blind" model-adaptation approaches. Conclusions: Adapting pre-trained NLP models for new tasks can be more efficient and effective if the language pattern landscapes of old settings and new settings can be made explicit and comparable. Our experiments show that the phenotype-mention embedding approach is an effective way to model language patterns for phenotype-mention identification tasks and that its use can guide efficient NLP model reuse.

cs.CL↗