A Data Quality Measurement Framework Using Distribution-Based Modeling and Simulation in Real-Time Telemedicine Systems

In modern telemedicine systems, the data path can be exceedingly complex, with data passing through a number of phases and processes before reaching its ultimate state. It is extremely difficult to predict the effects of lacking data or improperly processed data on the final outcome. In real-time systems, and particularly in the field of telemedicine, it is crucial to rapidly identify and rectify issues in order to prevent the loss of large amounts of data and the degradation of data quality. A basic simulation is insufficient for a comprehensive examination of the system; instead, modeling approaches are required. However, a minor system's state space can be immense. We present a methodology and a hybrid framework that incorporate simulation, emulation, and modeling in order to evaluate the state space and potential consequences of a sufficiently large system in a more targeted and condensed manner. In this paper, we demonstrate the structure and operation of our framework using an actively researched telemedicine use case, as well as how data quality can fluctuate and new anomalies can emerge if data is corrupted during an intermediate phase. According to our real-time Atrial Fibrillation (AF) and classification use case, data loss can be as high as 15%.