A Multi-Class Approach for the Automatic Detection of Congestive Heart Failure in Windowed ECG.

Congestive heart failure (CHF) is a chronic heart disease that causes debilitating symptoms and leads to higher mortality and morbidity. In this paper, we present HARPER, a novel automatic detector of CHF episodes able to distinguish between Normal Sinus Rhythm (NSR), CHF, and no-CHF. The main advantages of HARPER are its reliability and its capability of providing an early diagnosis. Indeed, the method is based on evaluating real-time features and observing a brief segment of ECG signal. HARPER is an independent tool meaning that it does not need any ECG annotation or segmentation algorithms to provide detection. The approach was submitted to complete experimentation by involving both the intra- and inter-patient validation schemes. The results are comparable to the state-of-art methods, highlighting the suitability of HARPER to be used in modern IoMT systems as a multi-class, fast, and highly accurate detector of CHF. We also provide guidelines for configuring a temporal window to be used in the automatic detection of CHF episodes.

Postural control assessment via Microsoft Azure Kinect DK: An evaluation study.

BACKGROUND AND OBJECTIVE: Equipments generally used for entertainment, such as Microsoft Kinect, have been widely used for postural control as well. Such systems-compared to professional motion tracking systems-allow to obtain non-invasive and low-cost tracking. This makes them particularly suitable for the implementation of home rehabilitation systems. Microsoft has recently released a new version of Kinect, namely Azure Kinect DK, that is meant for developers, not consumers, and it has been specifically designed to implement professional applications. The hardware of this new version of the Kinect has been substantially improved as compared with previous versions. However, the accuracy of the Azure Kinect DK has not been evaluated yet in the context of the assessment of postural control as done for its predecessors. METHODS: We present a study to compare the motion traces of the Azure Kinect DK with those of a Vicon 3D system, typically considered the gold standard for high-accuracy motion tracking. The study involved 26 subjects performing specific functional reach and functional balance exercises. RESULTS: The results clearly indicates that the Azure Kinect DK provides a very accurate tracking of the main joints of the body for all the recording taken during the lateral reach movement. The Root Mean Square Error (RMSE) between the two tracking systems obtained is approximately 0.2 for the lateral and forward exercises while for the balance exercise it is around 0.47 considering the average of the results among all the joints. The angular Mean Absolute Error is approximately in the range 5-15 degrees for all the upper joints and independently on the exercise. The lower body joints show a higher angular error between the two systems. Not surprisingly, it was found that results are much better in correspondence of slow movements. CONCLUSIONS: The results achieved that the Azure Kinect DK has an incredibly high potential to be used in applications of home rehabilitation, where the assessment of postural control is a fundamental and crucial activity.