Data Analytics Research and Technology in Healthcare
(DARTH group)
10 October 2021
New journal article accepted for publication in Diagnostics
Many studies have reported high accuracy using voice tasks towards remote assessment and monitoring of Parkinson’s disease (PD). Most of these studies, however, report findings using a small number of recordings, often collected under acoustically controlled conditions and therefore cannot scale at large. In this study, we extend our previous work using the Parkinson's Voice Initiative data to demonstrate the potential of using voice as a population-based PD screening tool in resource-constrained settings.
17 September 2021
New journal article accepted for publication in Pediatric Research
An estimated 15 million infants are born preterm (before 37 weeks of gestation) annually worldwide. Preterm birth can lead to impaired language development and is associated with a range of negative sequelae across the life span, including poor social, emotional and behavioural functioning. We collected data from 89 children born preterm who underwent diffusion MRI along with clinical and demographic characteristics. The resulting model can accurately identify preterm infants who are likely to develop language impairment in early childhood.
23 August 2021
New journal article accepted for publication in npj Digital Medicine
Surgical treatment is increasing globally, with approximately one in ten people undergoing a surgical procedure each year in high-income countries. Following discharge, patients take charge on monitoring their own recovery. Mobile and wearable digital health interventions provide an opportunity to monitor and support patients during their postoperative recovery. We conducted this review study to assess current use and effectiveness of mobile and wearable digital health interventions following surgery.
4 July 2021
New journal article accepted for publication in Scientific Reports
Cardiorespiratory fitness is well-known to be associated with diverse clinical outcomes. We used iPhones to passively record physical activity longitudinally and associated it to measured metabolic equivalent of task (METs) recorded during stress test. This work strongly supports the use of smartphones to routinely monitor physical activity towards risk stratification and disease management. The study builds on an international collaboration with Harvard colleagues.
12 May 2021
New journal article accepted for publication in Clinical Chemistry
Cardiac troponin is a widely used biomarker and has been associated with cardiovascular events. It is unclear whether sex-specific troponin thresholds should be considered in clinical guidelines to inform cardiovascular events. We used data from the Generation Scotland, a well-phenotyped family-based cohort with more than 24,000 participants, and demonstrate that cardiac troponin concentrations are stronger predictors of cardiovascular events in women.
1 May 2021
Andres wins the Edinburgh Branch of Parkinson’s UK (ERIG) talk prize
ERIG had invited PhD supervisors to nominate students who work in this research area and Andres has won this award for his presentation: “An engineering approach as a support tool for Parkinson’s". In his talk he had highlighted some of his recent PhD findings capitalizing on voice as a robust tool towards providing new insights into Parkinson's disease. The panel commented Andres for making the talk accessible to a lay audience. This engagement work was started by Prof. Ken Bowler with the establishment of the annual Edinburgh Parkinson’s Lecture.
30 March 2021
Evi wins the SPR MD/PhD student research award in the Pediatrics conference
Evi has won this award at the Society for Pediatrics Research conference (one of the biggest international academic meetings in the area of Pediatrics) for her research paper: “Machine Learning for Stratification of children at risk of language delay following Preterm Birth". This is work that Evi publishes as lead author, and is a multi-centre collaboration with colleagues across the University of Edinburgh. She will be presenting her work at the conference in May.
17 February 2021
New journal article accepted for publication in Frontiers in Human Neuroscience
"A neuromotor to acoustical jaw-tongue projection model with application in Parkinson’s disease hypokinetic dysarthria". We explored concurrent speech, surface electromyography, and three-dimensional accelerometry signals to assess the neuromotor activity of the massseter-jaw-tongue articulation in Parkinson's disease (PD). We demonstrate that there are important cross-correlations which may serve as useful acoustic biomarkers of hypokinetic dysarthria in PD.
13 February 2021
Thanasis won the Biosignals 2021 best paper award
"Assessing Parkinson’s disease speech signal generalization of clustering results across three countries: findings in the Parkinson’s voice initiative". We demonstrated that we can identify four robust clusters of Parkinson's disease using sustained vowels which generalize well on three cohorts collected across three countries as part of the Parkinson's Voice Initiative. These findings have important implications for cost-effective group membership assignment.
1 February 2021
Minhong has successfully defended her PhD thesis
"New insights into probabilistic pattern formation of embryonic stem cells using agent-based modelling”. Minhong proposed an agent-based modelling approach to identify biologically plausible rules acting at the meso-scale within stem cell collectives that may explain spontaneous patterning. She introduced a new distance-based metric to assess the deviation between probabilistic ground truth and probabilistic simulated outcomes. Her work provides some useful key insights into stem cell understanding, facilitating further investigations towards the development of novel treatments.
27 January 2021
New journal article accepted for publication in IEEE Access
"Smartphone speech testing for symptom assessment in rapid eye movement sleep behavior disorder and Parkinson's disease”. We analyzed 4242 smartphone voice recordings from people diagnosed with REM sleep behavior disorder and Parkinson's disease, and contrasted findings with data from controls. We demonstrate the potential of our approach towards a novel digital biomarker facilitating intervention in the early and prodromal stages of Parkinson's disease.
11 January 2021
New journal article accepted for publication in Biomedical Signal Processing and Control
"Acoustic to kinematic projection in Parkinson’s disease dysarthria”. We investigated the effects of neuromotor activity during muscular exertion that translates formant acoustics into speech articulatory movements affected by hypokinetic dysarthria in Parkinson’s Disease (PD). The study provides new mechanistic insights into the biomechanical system of voice production and the understanding of PD effects.