Background In a large randomized trial, Utrecht PROactive Frailty Intervention Trial (U‐PROFIT), we evaluated the effectiveness of an integrated program on the preservation of daily functioning in older people in primary care that consisted of a frailty identification tool and a multicomponent nurse‐led care program. Examination of treatment fidelity is critical to successful translation of evidence‐based interventions into practice. Aims To assess treatment delivery, dose and content of nursing care delivered within the nurse‐led care program, and to explore if the delivery may have influenced the trial results. Methods A mixed‐methods study was conducted. Type and dose of nursing care were collected during the trial. Shortly after the trial, a focus group with nurses was conducted to explore reasons for the observed differences between the type and dose of nursing care delivered. Results A total of 835 older persons were included in the nurse‐led care program. The mean age was 75 years, 64% were female and 53.5% were living alone. The most frequent self‐reported conditions were loneliness (60.8%) and cognitive problems (59.4%). One‐third of the patients with a geriatric condition received an additional assessment (e.g., Mini‐Mental State Examination), and the majority of these patients received at least one nurse intervention (>85%). Most nursing care was delivered to patients at risk of falling and to those with urinary incontinence. Patients with nutrition problems seldom received nursing interventions. The nurses explained that differences in type and dose were influenced by the preference of the patient, the type of geriatric problem, and the time required to apply a nurse intervention. Linking Evidence to Action All intervention components were delivered; however, differences were observed in the type and dose of nursing care delivered across geriatric conditions. The findings better explain the treatment fidelity and suggest that there is room for improvement that may result in more beneficial patient outcomes.
LINK
In this paper, we present a framework for gamified motor learning through the use of a serious game and high-fidelity motion capture sensors. Our implementation features an Inertial Measurement Unit and a set of Force Plates in order to obtain real-time, high-frequency measurements of patients' core movements and centre of pressure displacement during physical rehabilitation sessions. The aforementioned signals enable two mechanisms, namely a) a game avatar controlled through patient motor skills and b) a rich data stream for post-game motor performance analysis. Our main contribution is a fine-grained processing pipeline for sensor signals, enabling the extraction of a reliable and accurate mapping between patient motor movements, in-game avatar controls and overall motor performance. Moreover, we discuss the potential of this framework towards the implementation of personalised therapeutic sessions and present a pilot study conducted in that direction.
LINK
Communicatieprofessionals geven aan dat organisaties geconfronteerd worden met een almaar complexere samenleving en daarmee het overzicht verloren hebben. Zo’n overzicht, een ‘360 graden blik’, is echter onontbeerlijk. Dit vooral, aldus diezelfde communicatieprofessionals, omdat dan eerder kan worden opgemerkt wanneer de legitimiteit van een organisatie ter discussie staat en zowel tijdiger als adequater gereageerd kan worden. Op dit moment is het echter nog zo dat een reactie pas op gang komt als zaken reeds in een gevorderd stadium verkeren. Onderstromen blijven onderbelicht, als ze niet al geheel onzichtbaar zijn. Een van de verklaringen hiervoor is de grote rol van sociale media in de publieke communicatie van dit moment. Die media produceren echter zoveel data dat communicatieprofessionals daartegenover machteloos staan. De enige oplossing is automatisering van de selectie en analyse van die data. Helaas is men er tot op heden nog niet in geslaagd een brug te slaan tussen het handwerk van de communicatieprofessional en de vele mogelijkheden van een datagedreven aanpak. Deze brug dan wel de vertaling van de huidige praktijk naar een hogere technisch niveau staat centraal in dit onderzoeksproject. Daarbij gaat het in het bijzonder om een vroegtijdige herkenning van potentiële issues, in het bijzonder met betrekking tot geruchtvorming en oproepen tot mobilisatie. Met discoursanalyse, AI en UX Design willen we interfaces ontwikkelen die zicht geven op die onderstromen. Daarbij worden transcripten van handmatig gecodeerde discoursanalytische datasets ingezet voor AI, in het bijzonder voor de clustering en classificatie van nieuwe data. Interactieve datavisualisaties maken die datasets vervolgens beter doorzoekbaar terwijl geautomatiseerde patroon-classificaties de communicatieprofessional in staat stellen sociale uitingen beter in te schatten. Aldus wordt richting gegeven aan handelingsperspectieven. Het onderzoek voorziet in de oplevering van een high fidelity ontwerp en een handleiding plus training waarmee analisten van newsrooms en communicatieprofessionals daadwerkelijk aan de slag kunnen gaan.
The bi-directional communication link with the physical system is one of the main distinguishing features of the Digital Twin paradigm. This continuous flow of data and information, along its entire life cycle, is what makes a Digital Twin a dynamic and evolving entity and not merely a high-fidelity copy. There is an increasing realisation of the importance of a well functioning digital twin in critical infrastructures, such as water networks. Configuration of water network assets, such as valves, pumps, boosters and reservoirs, must be carefully managed and the water flows rerouted, often manually, which is a slow and costly process. The state of the art water management systems assume a relatively static physical model that requires manual corrections. Any change in the network conditions or topology due to degraded control mechanisms, ongoing maintenance, or changes in the external context situation, such as a heat wave, makes the existing model diverge from the reality. Our project proposes a unique approach to real-time monitoring of the water network that can handle automated changes of the model, based on the measured discrepancy of the model with the obtained IoT sensor data. We aim at an evolutionary approach that can apply detected changes to the model and update it in real-time without the need for any additional model validation and calibration. The state of the art deep learning algorithms will be applied to create a machine-learning data-driven simulation of the water network system. Moreover, unlike most research that is focused on detection of network problems and sensor faults, we will investigate the possibility of making a step further and continue using the degraded network and malfunctioning sensors until the maintenance and repairs can take place, which can take a long time. We will create a formal model and analyse the effect on data readings of different malfunctions, to construct a mitigating mechanism that is tailor-made for each malfunction type and allows to continue using the data, albeit in a limited capacity.
The bi-directional communication link with the physical system is one of the main distinguishing features of the Digital Twin paradigm. This continuous flow of data and information, along its entire life cycle, is what makes a Digital Twin a dynamic and evolving entity and not merely a high-fidelity copy. There is an increasing realisation of the importance of a well functioning digital twin in critical infrastructures, such as water networks. Configuration of water network assets, such as valves, pumps, boosters and reservoirs, must be carefully managed and the water flows rerouted, often manually, which is a slow and costly process. The state of the art water management systems assume a relatively static physical model that requires manual corrections. Any change in the network conditions or topology due to degraded control mechanisms, ongoing maintenance, or changes in the external context situation, such as a heat wave, makes the existing model diverge from the reality. Our project proposes a unique approach to real-time monitoring of the water network that can handle automated changes of the model, based on the measured discrepancy of the model with the obtained IoT sensor data. We aim at an evolutionary approach that can apply detected changes to the model and update it in real-time without the need for any additional model validation and calibration. The state of the art deep learning algorithms will be applied to create a machine-learning data-driven simulation of the water network system. Moreover, unlike most research that is focused on detection of network problems and sensor faults, we will investigate the possibility of making a step further and continue using the degraded network and malfunctioning sensors until the maintenance and repairs can take place, which can take a long time. We will create a formal model and analyse the effect on data readings of different malfunctions, to construct a mitigating mechanism that is tailor-made for each malfunction type and allows to continue using the data, albeit in a limited capacity.
