Human Movement Representation on Multivariate Time Series for Recognition of Professional Gestures and Forecasting Their Trajectories.

Human-centered artificial intelligence is increasingly deployed in professional workplaces in Industry 4.0 to address various challenges related to the collaboration between the operators and the machines, the augmentation of their capabilities, or the improvement of the quality of their work and life in general. Intelligent systems and autonomous machines need to continuously recognize and follow the professional actions and gestures of the operators in order to collaborate with them and anticipate their trajectories for avoiding potential collisions and accidents. Nevertheless, the recognition of patterns of professional gestures is a very challenging task for both research and the industry. There are various types of human movements that the intelligent systems need to perceive, for example, gestural commands to machines and professional actions with or without the use of tools. Moreover, the interclass and intraclass spatiotemporal variances together with the very limited access to annotated human motion data constitute a major research challenge. In this paper, we introduce the Gesture Operational Model, which describes how gestures are performed based on assumptions that focus on the dynamic association of body entities, their synergies, and their serial and non-serial mediations, as well as their transitioning over time from one state to another. Then, the assumptions of the Gesture Operational Model are translated into a simultaneous equation system for each body entity through State-Space modeling. The coefficients of the equation are computed using the Maximum Likelihood Estimation method. The simulation of the model generates a confidence-bounding box for every entity that describes the tolerance of its spatial variance over time. The contribution of our approach is demonstrated for both recognizing gestures and forecasting human motion trajectories. In recognition, it is combined with continuous Hidden Markov Models to boost the recognition accuracy when the likelihoods are not confident. In forecasting, a motion trajectory can be estimated by taking as minimum input two observations only. The performance of the algorithm has been evaluated using four industrial datasets that contain gestures and actions from a TV assembly line, the glassblowing industry, the gestural commands to Automated Guided Vehicles as well as the Human-Robot Collaboration in the automotive assembly lines. The hybrid approach State-Space and HMMs outperforms standard continuous HMMs and a 3DCNN-based end-to-end deep architecture.

Long-term impact of acute kidney injury on prognosis in patients with acute myocardial infarction.

BACKGROUND: Little evidence exists regarding the long-term impact of acute kidney injury (AKI) during index hospitalisation for acute myocardial infarction (AMI). We prospectively assessed the long-term prognostic significance of the occurrence of in-hospital AKI in a multicentre cohort of patients admitted with AMI. METHODS: Data were obtained from 518 AMI patients with a median follow-up of 5.6 (IQR 4.6-6.5) years. Patients were followed up regarding the occurrence of death, major adverse cardiovascular events (MACE), and any deterioration in kidney function. RESULTS: From the study cohort, 84 patients (16%) had developed AKI at discharge during index hospitalisation. 96 patients died during follow-up, MACE occurred in 90 patients, and 30 patients showed evidence of deterioration in kidney function. Patients with AKI at hospital discharge had a three-fold increased mortality risk (HR 3.2, 95% CI 2.1-4.8; P < 0.001). This association was independent of possible confounding by variables that could influence prognosis (HR 1.9 95% CI 1.1-3.2; P = 0.028) evident only up to three years during follow-up. During long-term follow-up, patients with AKI during their index hospitalisation had a significantly (P = 0.027) higher incidence of MACE (26%) than those who did not develop AKI (15%). Patients with AKI had a higher incidence of deteriorating kidney function (10%) than those without AKI (5%) during follow-up, but this difference was not significant (P = 0.124). CONCLUSIONS: Our findings emphasise in addition to the need for appropriate long term follow-up in such patients, an increased mortality and morbidity during the first three years after the index event.

Spot urine albumin to creatinine ratio outperforms novel acute kidney injury biomarkers in patients with acute myocardial infarction.

BACKGROUND: Acute kidney injury (AKI) is a frequent complication in patients hospitalized for acute myocardial infarction (AMI), and is associated with in-hospital and long-term morbidity and mortality. We prospectively assessed the diagnostic performance of spot urine albumin to creatinine ratio (uACR) in an adequately sized multicenter cohort of patients admitted to hospital with AMI. We further compared uACR to novel renal injury associated biomarkers regarding their diagnostic ability. METHODS: We enrolled 805 consecutive patients presenting with acute ST-elevation and non-ST elevation AMI. Patients were assessed for presence of AKI at 48h post-admission and at hospital discharge using the Acute Kidney Injury Network (AKIN), the Acute Dialysis Quality Initiative [Risk, Injury and Failure (RIFLE)] criteria and the Kidney Disease: Improving Global Outcomes (KDIGO) criteria. Blood and urine sampling for neutrophil gelatinase-associated lipocalin (NGAL), interleukin-18 (IL-18), cystatin-C, and uACR assessment was performed during admission. RESULTS: The predictive accuracy of uACR was good (Area Under the Curve (AUC), 0.725; 95% CI 0.676-0.774) and was better compared to urine NGAL (P=0.007), urine (P<0.001) and plasma Cystatin-C (P=0.001). ROC analysis identified concentrations of ≥66.7µg/mg as having the best diagnostic accuracy. The use of uACR exhibited good discriminating ability independent to possible cofounders and additive regarding the use of novel biomarkers. CONCLUSIONS: The use of uACR can easily be applied in the clinical setting, allows for robust risk assessment and offers the potential to improve the management of AMI patients at risk for acute kidney injury.