Injury, hospitalization, and even death are common consequences of falling for elderly people. Therefore, early and robust identification of people at risk of recurrent falling is crucial from a ...preventive point of view. This study aims to evaluate the effectiveness of an interpretable semi-supervised approach in identifying individuals at risk of falls by using the data provided by ankle-mounted IMU sensors. Our method benefits from the cause–effect link between a fall event and balance ability to pinpoint the moments with the highest fall probability. This framework also has the advantage of training on unlabeled data, and one can exploit its interpretation capacities to detect the target while only using patient metadata, especially those in relation to balance characteristics. This study shows that a visual-based self-attention model is able to infer the relationship between a fall event and loss of balance by attributing high values of weight to moments where the vertical acceleration component of the IMU sensors exceeds 5 m/s² during an especially short period. This semi-supervised approach uses interpretable features to highlight the moments of the recording that may explain the score of balance, thus revealing the moments with the highest risk of falling. Our model allows for the detection of 71% of the possible falling risk events in a window of 1 s (500 ms before and after the target) when compared with threshold-based approaches. This type of framework plays a paramount role in reducing the costs of annotation in the case of fall prevention when using wearable devices. Overall, this adaptive tool can provide valuable data to healthcare professionals, and it can assist them in enhancing fall prevention efforts on a larger scale with lower costs.
ObjectivesPersonality differences between doctors and patients can affect treatment outcomes. We examine these trait disparities, as well as differences across medical ...specialities.DesignRetrospective, observational statistical analysis of secondary data.SettingData from two data sets that are nationally representative of doctors and the general population in Australia.ParticipantsWe include 23 358 individuals from a representative survey of the general Australian population (with subgroups of 18 705 patients, 1261 highly educated individuals and 5814 working in caring professions) as well as 19 351 doctors from a representative survey of doctors in Australia (with subgroups of 5844 general practitioners, 1776 person-oriented specialists and 3245 technique-oriented specialists).Main outcome measuresBig Five personality traits and locus of control. Measures are standardised by gender, age and being born overseas and weighted to be representative of their population.ResultsDoctors are significantly more agreeable (a: standardised score −0.12, 95% CIs −0.18 to −0.06), conscientious (c: −0.27 to –0.33 to −0.20), extroverted (e: 0.11, 0.04 to 0.17) and neurotic (n: 0.14, CI 0.08 to 0.20) than the general population (a: −0.38 to –0.42 to −0.34, c: −0.96 to –1.00 to −0.91, e: −0.22 to –0.26 to −0.19, n: −1.01 to –1.03 to −0.98) or patients (a: −0.77 to –0.85 to −0.69, c: −1.27 to –1.36 to −1.19, e: −0.24 to –0.31 to −0.18, n: −0.71 to –0.76 to −0.66). Patients (−0.03 to –0.10 to 0.05) are more open than doctors (−0.30 to –0.36 to −0.23). Doctors have a significantly more external locus of control (0.06, 0.00 to 0.13) than the general population (−0.10 to –0.13 to −0.06) but do not differ from patients (−0.04 to –0.11 to 0.03). There are minor differences in personality traits among doctors with different specialities.ConclusionsSeveral personality traits differ between doctors, the population and patients. Awareness about differences can improve doctor–patient communication and allow patients to understand and comply with treatment recommendations.
(1) Background: Diabetes mellitus (DM) is a chronic, metabolic disease characterized by elevated levels of blood glucose. Recently, some studies approached the diabetes care domain through the ...analysis of the modifications of cardiovascular system parameters. In fact, cardiovascular diseases are the first leading cause of death in diabetic subjects. Thanks to their cost effectiveness and their ease of use, electrocardiographic (ECG) and photoplethysmographic (PPG) signals have recently been used in diabetes detection, blood glucose estimation and diabetes-related complication detection. This review’s aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (2) Method: We performed a systematic review based on articles that focus on the use of ECG and PPG signals in diabetes care. The search was focused on keywords related to the topic, such as “Diabetes”, “ECG”, “PPG”, “Machine Learning”, etc. This was performed using databases, such as PubMed, Google Scholar, Semantic Scholar and IEEE Xplore. This review’s aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (3) Results: A total of 78 studies were included. The majority of the selected studies focused on blood glucose estimation (41) and diabetes detection (31). Only 7 studies focused on diabetes complications detection. We present these studies by approach: traditional, machine learning and deep learning approaches. (4) Conclusions: ECG and PPG analysis in diabetes care showed to be very promising. Clinical validation and data processing standardization need to be improved in order to employ these techniques in a clinical environment.
The increased scrutiny on public health brought upon by the ongoing COVID-19 pandemic provides a strong impetus for a renewal of public health systems. This paper seeks to understand priorities of ...public health decision-makers for reforms to public health financing, organization, interventions, and workforce.
We used an online 3-round real-time Delphi method of reaching consensus on priorities for public health systems reform. Participants were recruited among individuals holding senior roles in Canadian public health institutions, ministries of health and regional health authorities. In Round 1, participants were asked to rate 9 propositions related to public health financing, organization, workforce, and interventions. Participants were also asked to contribute up to three further ideas in relation to these topics in open-ended format. In Rounds 2 and 3, participants re-appraised their ratings in the view of the group's ratings in the previous round.
Eighty-six public health senior decision-makers from various public health organizations across Canada were invited to participate. Of these, 25/86 completed Round 1 (29% response rate), 19/25 completed Round 2 (76% retention rate) and 18/19 completed Round 3 (95% retention rate). Consensus (defined as more than 70% of importance rating) was achieved for 6 out of 9 propositions at the end of the third round. In only one case, the consensus was that the proposition was not important. Proposition rated consensually important relate to targeted public health budget, time frame for spending this budget, and the specialization of public health structures. Both interventions related and not related to the COVID-19 pandemic were judged important. Open-ended comments further highlighted priorities for renewal in public health governance and public health information management systems.
Consensus emerged rapidly among Canadian public health decision-makers on prioritizing public health budget and time frame for spending. Ensuring that public health services beyond COVID-19 and communicable disease are maintained and enhanced is also of central importance. Future research shall explore potential trade-offs between these priorities.
Although the role of an internal model of gravity for the predictive control of the upper limbs is quite well established, evidence is lacking regarding an internal model of friction. In this study, ...33 male and female human participants performed a striking movement (with the index finger) to slide a plastic cube-like object to a given target distance. The surface material (aluminum or balsa wood) on which the object slides, the surface slope (-10°, 0, or +10°) and the target distance (25 cm or 50 cm) varied across conditions, with ten successive trials in each condition. Analysis of the object speed at impact and spatial error suggests that: 1) the participants chose to impart a similar speed to the object in the first trial regardless of the surface material to facilitate the estimation of the coefficient of friction; 2) the movement is parameterized across repetitions to reduce spatial error; 3) an internal model of friction can be generalized when the slope changes. Biomechanical analysis showed interindividual variability in the recruitment of the upper limb segments and in the adjustment of finger speed at impact in order to transmit the kinetic energy required to slide the object to the target distance. In short, we provide evidence that the brain builds an internal model of friction that makes it possible to parametrically control a striking movement in order to regulate the amount of kinetic energy required to impart the appropriate initial speed to the object.
Due to the sensitive nature of diabetes-related data, preventing them from being easily shared between studies, and the wide discrepancies in their data processing pipeline, progress in the field of ...glucose prediction is hard to assess. To address this issue, we introduce GLYFE (GLYcemia Forecasting Evaluation), a benchmark of machine learning-based glucose predictive models. We present the accuracy and clinical acceptability of nine different models coming from the literature, from standard autoregressive to more complex neural network-based models. These results are obtained on two different datasets, namely UVA/Padova Type 1 Diabetes Metabolic Simulator (T1DMS) and Ohio Type-1 Diabetes Mellitus (OhioT1DM), featuring artificial and real type 1 diabetic patients respectively. By providing extensive details about the data flow as well as by providing the whole source code of the benchmarking process, we ensure the reproducibility of the results and the usability of the benchmark by the community. Those results serve as a basis of comparison for future studies. In a field where data are hard to obtain, and where the comparison of results from different studies is often irrelevant, GLYFE gives the opportunity of gathering researchers around a standardized common environment.
Photopletysmography (PPG) is a non-invasive and well known technology that enables the recording of the digital volume pulse (DVP). Although PPG is largely employed in research, several aspects ...remain unknown. One of these is represented by the lack of information about how many waveform classes best express the variability in shape. In the literature, it is common to classify DVPs into four classes based on the dicrotic notch position. However, when working with real data, labelling waveforms with one of these four classes is no longer straightforward and may be challenging. The correct identification of the DVP shape could enhance the precision and the reliability of the extracted bio markers. In this work we proposed unsupervised machine learning and deep learning approaches to overcome the data labelling limitations. Concretely we performed a K-medoids based clustering that takes as input 1) DVP handcrafted features, 2) similarity matrix computed with the Derivative Dynamic Time Warping and 3) DVP features extracted from a CNN AutoEncoder. All the cited methods have been tested first by imposing four medoids representative of the Dawber classes, and after by automatically searching four clusters. We then searched the optimal number of clusters for each method using silhouette score, the prediction strength and inertia. To validate the proposed approaches we analyse the dissimilarities in the clinical data related to obtained clusters.
The world of fluid mechanics is increasingly generating a large amount of data, thanks to the use of numerical simulation techniques. This offers interesting opportunities for incorporating machine ...learning methods to solve data-related problems such as model calibration. One of the applications that machine learning can offer to the world of Engineering and Fluid Mechanics in particular is the calibration of models making it possible to approximate a phenomenon. Indeed, the computational cost generated by some models of fluid mechanics pushes scientists to use other models close to the original models but less computationally intensive in order to facilitate their handling. Among the different approaches used: machine learning coupled with some optimization methods and algorithms in order to reduce the computation cost induced. In this paper, we propose a framework which is a new flexible, optimized and improved method, to calibrate a physical model, called the wake oscillator (WO), which simulates the vibratory behaviors of overhead line conductors. an approximation of a heavy and complex model called the strip theory (ST) model. OPTI-ENS is composed of an ensemble machine learning algorithm (ENS) and an optimization algorithm of the WO model so that the WO model can generate the adequate training data as input to the ENS model. ENS model will therefore take as input the data from the WO model and output the data from the ST model. As a benchmark, a series of Machine learning models have been implemented and tested. The OPTI-ENS algorithm was retained with a best Coefficient of determination (R2 Score) of almost 0.7 and a Root mean square error (RMSE) of 7.57e−09. In addition, this model is approximately 170 times faster (in terms of calculation time) than an ENS model without optimization of the generation of training data by the WO model. This type of approach therefore makes it possible to calibrate the WO model so that simulations of the behavior of overhead line conductors are carried out only with the WO model.
In this paper, we present a new approach to use machine learning (ML) for the calibration of a physical model allowing the reproduction of the vibratory behavior of an overhead line conductor. This ...physical model known as Strip Theory (ST) has the advantage of being very precise but very complicated and cumbersome in its software operations and manipulations. A second model known as the Wake Oscillator (WO) has been implemented in order to meet the limitations of the ST model. In order to be able to use the WO model instead of the ST model, very heavy manual adjustments are required, which makes its use complicated. Precisely, the WO must be able to generate a time series similar to a time series generated by the ST model. In order to respond to this limitation, a machine learning model known as ENS has been proposed. The machine learning model will therefore take as input the data from the WO model and output the data from the ST model. A series of Machine learning models have been implemented and tested. The ENS algorithm was retained with a best Pearson's linear coefficient of determination (R2 Score) of almost 0.7 and a Root mean square deviation (RMSE) of 7.57e-09. This type of approach therefore makes it possible to calibrate the WO model so that simulations of the behavior of overhead line conductors are carried out only with the WO model.
Photoplethysmography (PPG) is a non-invasive and cost-efficient optical technique used to assess blood volume variations in the microcirculation. PPG technology is widely used in a variety of ...wearable sensors to investigate the cardiovascular system. Recent studies have demonstrated the utility of PPG analysis for carrying out large-scale screening to prevent and detect diabetes. However, most of these studies require feature extraction and/or several pre-processing steps. Over the past few years, the advent of deep learning has significantly impacted the analysis of biomedical signals. Despite their success in other fields, however, very few studies have focused on the application of deep learning to raw PPG signals for detecting diabetes. Existing studies have proposed large models trained on large amounts of data. In this paper, we present a Light CNN-based model for screening the presence of type 2 diabetes using a single raw pulse extracted from photoplethysmographic signals. In addition to the baseline architecture, we evaluate different model architectures that take as input age and biological sex or PPG handcrafted features. Furthermore, we apply transfer learning to all the tested architectures to evaluate the effectiveness of harnessing pre-trained models in detecting diabetes. We tested a model pre-trained on a general PPG shape dataset and another model pre-trained on a dataset containing hypertension PPG signals. Our model scored an AUC of 75.5 when trained with raw PPG waves, age, and biological sex without applying transfer learning, which is competitive with current state of the art.