Missing data resilient decision-making for healthcare IoT through personalization: A case study on maternal health

Remote health monitoring is an effective method to enable tracking of -risk patients outside of conventional clinical settings, providing -detection of diseases and preventive care as well as diminishing costs. Internet-of-Things (IoT) technology facilitates of such monitoring systems although significant challenges to be addressed in the real-world trials. Missing data is a issue in these systems, as data acquisition may be interrupted from time to time in long-term monitoring scenarios. This issue causes and incomplete data and subsequently could lead to failure decision making. Analysis of missing data has been tackled in several studies. However, these techniques are inadequate for real-time health as they neglect the variability of the missing data. This is significant when the vital signs are being missed since they on different factors such as physical activities and surrounding. Therefore, a holistic approach to customize missing data in real-time health monitoring systems is required, considering a wide of parameters while minimizing the bias of estimates. In this, we propose a personalized missing data resilient decision-making to deliver health decisions 24/7 despite missing values. The leverages various data resources in IoT-based systems to impute missing values and provide an acceptable result. We validate our via a real human subject trial on maternity health, in which 20 pregnant women were remotely monitored for 7 months. In this setup, a -time health application is considered, where maternal health status is estimated utilizing maternal heart rate. The accuracy of the approach is evaluated, in comparison to existing methods. The approach results in more accurate estimates especially when the missing window is large.