An Internet of Medical Things-Based Model for Real-Time Monitoring and Averting Stroke Sensors

Abstract

In recent years, neurological diseases have become a standout amongst all the other diseases and are the most important reasons for mortality and morbidity all over the world. The current study's aim is to conduct a pilot study for testing the prototype of the designed glove-wearable technology that could detect and analyze the heart rate and EEG for better management and avoiding stroke consequences. The qualitative, clinical experimental method of assessment was explored by incorporating use of an IoT-based real-time assessing medical glove that was designed using heart rate-based and EEG-based sensors. We conducted structured interviews with 90 patients, and the results of the interviews were analyzed by using the Barthel index and were grouped accordingly. Overall, the proportion of patients who followed proper daily heart rate recording behavior went from 46.9% in the first month of the trial to 78.2% after 3-10 months of the interventions. Meanwhile, the percentage of individuals having an irregular heart rate fell from 19.5% in the first month of the trial to 9.1% after 3-10 months of intervention research. In T5, we found that delta relative power decreased by 12.1% and 5.8% compared with baseline at 3 and at 6 months and an average increase was 24.3 ± 0.08. Beta-1 remained relatively steady, while theta relative power grew by 7% and alpha relative power increased by 31%. The T1 hemisphere had greater mean values of delta and theta relative power than the T5 hemisphere. For alpha (p < 0.05) and beta relative power, the opposite pattern was seen. The distinction was statistically significant for delta (p < 0.001), alpha (p < 0.01), and beta-1 (p < 0.05) among T1 and T5 patient groups. In conclusion, our single center-based study found that such IoT-based real-time medical monitoring devices significantly reduce the complexity of real-time monitoring and data acquisition processes for a healthcare provider and thus provide better healthcare management. The emergence of significant risks and controlling mechanisms can be improved by boosting the awareness. Furthermore, it identifies the high-risk factors besides facilitating the prevention of strokes. The EEG-based brain-computer interface has a promising future in upcoming years to avert DALY.

Figure 1

Overview of work process.

Figure 2

Concept of infrastructure developed for the remote CNS patient monitoring system.

Figure 3

T1–T5: percentage efficacy of monitoring normal and anomalous heart rates, as evaluated in an intervention study.

Figure 4

Graphs showing the accuracy percentage of delta, theta, and alpha electroencephalographic (EEG) bands and correlation with heart rate (T1–T5).