A novel approach for modelling and classifying sit-to-stand kinematics using inertial sensors.

Sit-to-stand transitions are an important part of activities of daily living and play a key role in functional mobility in humans. The sit-to-stand movement is often affected in older adults due to frailty and in patients with motor impairments such as Parkinson's disease leading to falls. Studying kinematics of sit-to-stand transitions can provide insight in assessment, monitoring and developing rehabilitation strategies for the affected populations. We propose a three-segment body model for estimating sit-to-stand kinematics using only two wearable inertial sensors, placed on the shank and back. Reducing the number of sensors to two instead of one per body segment facilitates monitoring and classifying movements over extended periods, making it more comfortable to wear while reducing the power requirements of sensors. We applied this model on 10 younger healthy adults (YH), 12 older healthy adults (OH) and 12 people with Parkinson's disease (PwP). We have achieved this by incorporating unique sit-to-stand classification technique using unsupervised learning in the model based reconstruction of angular kinematics using extended Kalman filter. Our proposed model showed that it was possible to successfully estimate thigh kinematics despite not measuring the thigh motion with inertial sensor. We classified sit-to-stand transitions, sitting and standing states with the accuracies of 98.67%, 94.20% and 91.41% for YH, OH and PwP respectively. We have proposed a novel integrated approach of modelling and classification for estimating the body kinematics during sit-to-stand motion and successfully applied it on YH, OH and PwP groups.

Increasing the safety of unannounced meal detection for artificial pancreas closed-loop with patient's hourly meal schedule.

The daily challenge for people with type 1 diabetes is maintaining glycaemia in the "normal" range after meals, by injecting themselves the correct amount of insulin. Artificial pancreas systems were developed to adjust insulin delivery based on real-time monitoring of glycaemia and meal patient's report. Meal reporting is a heavy burden for patients as it requires carbohydrate estimation several times per day. To improve patient's quality of life and treatment, several methods aim at detecting unannounced meals. While untreated meals lead to hyperglycaemia and in the long-term to comorbidities, treating falsely detected meals can cause hypoglycaemia and coma. In this paper, we propose to customise the meal detection to the patient's hourly meal probability in order to limit false detection of unannounced meals.

Unannounced Meal Detection for Artificial Pancreas Systems Using Extended Isolation Forest.

This study aims at developing an unannounced meal detection method for artificial pancreas, based on a recent extension of Isolation Forest. The proposed method makes use of features accounting for individual Continuous Glucose Monitoring (CGM) profiles and benefits from a two-threshold decision rule detection. The advantage of using Extended Isolation Forest (EIF) instead of the standard one is supported by experiments on data from virtual diabetic patients, showing good detection accuracy with acceptable detection delays.

How can consultant-led childbirth care at time of delivery be maximised? A modelling study.

OBJECTIVE: The Royal College of Obstetricians and Gynaecologists has advised that consolidation of birth centres, where reasonable, into birth centres of at least 6000 admissions per year should allow constant consultant presence. Currently, only 17% of mothers attend such birth centres. The objective of this work was to examine the feasibility of consolidation of birth centres, from the perspectives of birth centre size and travel times for mothers. DESIGN: Computer-based optimisation. SETTING: Hospital-based births. POPULATION OR SAMPLE: 1.91 million admissions in 2014-2016. METHODS: A multiple-objective genetic algorithm. MAIN OUTCOME MEASURES: Travel time for mothers and size of birth centres. RESULTS: Currently, with 161 birth centres, 17% of women attend a birth centre with at least 6000 admissions per year. We estimate that 95% of women have a travel time of 30 min or less. An example scenario, with 100 birth centres, could provide 75% of care in birth centres with at least 6000 admissions per year, with 95% of women travelling 35 min or less to their closest birth centre. Planning at local level leads to reduced ability to meet admission and travel time targets. CONCLUSIONS: While it seems unrealistic to have all births in birth centres with at least 6000 admissions per year, it appears realistic to increase the percentage of mothers attending this type of birth centre from 17% to about 75% while maintaining reasonable travel times. Planning at a local level leads to suboptimal solutions.

Planning and Providing Acute Stroke Care in England: The Effect of Planning Footprint Size.

Background: Guidelines in England recommend that hyperacute stroke units (HASUs) should have a minimum of 600 confirmed stroke admissions per year in order to sustain expert consultant-led services, and that travel time for patients should ideally be 30 min or less. Currently, 61% of stroke patients attend a unit with at least 600 admissions per year and 56% attend such a unit and have a travel time of no more than 30 min. Objective: We have sought to understand how varying the planning and provision footprint in England affects access to care whilst achieving the recommended admission numbers for hyper-acute stroke care. We have compared two different planning footprints to national-level planning: planning using five NHS Regions in England, and planning using 44 Sustainability and Transformation Partnerships (STPs) in England. Methods: Computer modeling and optimization using a multi-objective genetic algorithm. Results: The number of stroke admissions between STPs varies by seven-fold, while the number of stroke admissions between NHS Regions varies by 2.5-fold. In order to meet stroke admission guidelines (600/year) for all units the maximum possible proportion of patients within 30 min would be 82, 78, and 72% with no boundaries to planning/provision, NHS Region boundaries, and STP boundaries (in these scenarios patients cannot move outside of their own STP or NHS Region). If STP or NHS Region boundaries are removed for provision of service (after planning is performed at these local levels), travel time is improved, but number of admissions to individual hospitals become significantly changed, especially at STP planning level where admission numbers per unit changed by an average of 204 (19%), and not all units maintained 600 admissions after removal of boundaries. Conclusion: Planning and providing services at STP level could lead to sub-optimal service provision compared with using larger and more consistently populated planning areas.

Feasibility of a hyper-acute stroke unit model of care across England: a modelling analysis.

OBJECTIVES: The policy of centralising hyperacute stroke units (HASUs) in England aims to provide stroke care in units that are both large enough to sustain expertise (>600 admissions/year) and dispersed enough to rapidly deliver time-critical treatments (<30 min maximum travel time). Currently, just over half (56%) of patients with stroke access care in such a unit. We sought to model national configurations of HASUs that would optimise both institutional size and geographical access to stroke care, to maximise the population benefit from the centralisation of stroke care. DESIGN: Modelling of the effect of the national reconfiguration of stroke services. Optimal solutions were identified using a heuristic genetic algorithm. SETTING: 127 acute stroke services in England, serving a population of 54 million people. PARTICIPANTS: 238 887 emergency admissions with acute stroke over a 3-year period (2013-2015). INTERVENTION: Modelled reconfigurations of HASUs optimised for institutional size and geographical access. MAIN OUTCOME MEASURE: Travel distances and times to HASUs, proportion of patients attending a HASU with at least 600 admissions per year, and minimum and maximum HASU admissions. RESULTS: Solutions were identified with 75-85 HASUs with annual stroke admissions in the range of 600-2000, which achieve up to 82% of patients attending a stroke unit within 30 min estimated travel time (with at least 95% and 98% of the patients being within 45 and 60 min travel time, respectively). CONCLUSIONS: The reconfiguration of hyperacute stroke services in England could lead to all patients being treated in a HASU with between 600 and 2000 admissions per year. However, the proportion of patients within 30 min of a HASU would fall from over 90% to 80%-82%.

Application of data fusion techniques and technologies for wearable health monitoring.

Technological advances in sensors and communications have enabled discrete integration into everyday objects, both in the home and about the person. Information gathered by monitoring physiological, behavioural, and social aspects of our lives, can be used to achieve a positive impact on quality of life, health, and well-being. Wearable sensors are at the cusp of becoming truly pervasive, and could be woven into the clothes and accessories that we wear such that they become ubiquitous and transparent. To interpret the complex multidimensional information provided by these sensors, data fusion techniques are employed to provide a meaningful representation of the sensor outputs. This paper is intended to provide a short overview of data fusion techniques and algorithms that can be used to interpret wearable sensor data in the context of health monitoring applications. The application of these techniques are then described in the context of healthcare including activity and ambulatory monitoring, gait analysis, fall detection, and biometric monitoring. A snap-shot of current commercially available sensors is also provided, focusing on their sensing capability, and a commentary on the gaps that need to be bridged to bring research to market.

Nonlinear deconvolution of hyperspectral data with MCMC for studying the kinematics of galaxies.

Hyperspectral imaging has been an area of active research in image processing and analysis for more than 10 years, mainly for remote sensing applications. Astronomical ground-based hyperspectral imagers offer new challenges to the community, which differ from the previous ones in the nature of the observed objects, but also in the quality of the data, with a low signal-to-noise ratio and a low resolution, due to the atmospheric turbulence. In this paper, we focus on a deconvolution problem specific to hyperspectral astronomical data, to improve the study of the kinematics of galaxies. The aim is to estimate the flux, the relative velocity, and the velocity dispersion, integrated along the line-of-sight, for each spatial pixel of an observed galaxy. Thanks to the Doppler effect, this is equivalent to estimate the amplitude, center, and width of spectral emission lines, in a small spectral range, for every spatial pixel of the hyperspectral data. We consider a parametric model for the spectral lines and propose to compute the posterior mean estimators, in a Bayesian framework, using Monte Carlo Markov chain algorithms. Various estimation schemes are proposed for this nonlinear deconvolution problem, taking advantage of the linearity of the model with respect to the flux parameters. We differentiate between methods taking into account the spatial blurring of the data (deconvolution) or not (estimation). The performances of the methods are compared with classical ones, on two simulated data sets. It is shown that the proposed deconvolution method significantly improves the resolution of the estimated kinematic parameters.