Early Detection and Self-management of Long-term Conditions Using Wearable Technologies
Baig, Mirza Mohsin
MetadataShow full metadata
Worldwide spending on the long-term or chronic care conditions is increasing to a point that requires immediate interventions and advancements to reduce the burden of the healthcare cost. Managing people with long-term conditions is a global challenge and it is mostly driven by the shifts in demographics and disease status. Today, long-term conditions engage by far the largest and growing share of healthcare budgets globally. From the literature, it is evident that an immediate intervention is required to slow down the epidemic of long-term conditions. The three time-based priorities for the long-term conditions are; (1) self-management of long-term conditions using advanced technology is identified as one of the immediate recommended actions. (2) In the medium-term, a robust mechanism of early detection and prediction of pre-long-term conditions is required to delay the onset of long-term condition; and (3) as a long-term strategy, in-depth research and investigations are required to reduce and make a positive impact by taking a holistic approach and multiple domain-intervention such as diet, education, cultural, physical, lifestyle, environmental, economic and more. This research is focused on one of the immediate approaches required to tackle long-term conditions - involving early detection and self-management of pre-long-term condition of diabetes using advanced technology and tools. This study deals with the three important areas of long-term conditions: wearable/remote and real-time monitoring; interpreting and detection for pre-diabetes and self-management of diabetes as a long-term condition. This research collected heart rate, heart rate variability, breathing rate, breathing volume, activity (steps, cadence and calories), using the advanced body wearable vest/sensors in real-time, and combined (the collected data) with manually collected blood glucose, height, weight, age and sex for individualised trend, baseline values and early detection. The collected data was fed through the clinical knowledge-base to set the baseline values using the existing interventions, guidelines and protocols. The artificial intelligence model using adaptive-neuro fuzzy interference system was developed to early detect pre-long-term conditions, individualised monitoring and self-management of diabetes. The performance of the system was validated through off-line tests with a high-level of agreement between the system and the physicians.