Artificial IntelligenceSmart Wearable

Wearable Health Monitoring System

Prognosis: A Wearable Health-Monitoring System

It is a fact that the global population is both growing and ageing [1], [2]. As a consequence of this demographic change, there has also been a corresponding increase in chronic age-related diseases, such as congestive heart failure, dementia, sleep apnea, cancer, diabetes, and chronic obstructive pulmonary disease [1], [3], [4].  We have discovered that our Seniors as well as those who suffer from specific pulmonary and diabetes were at greater risk from the recent Covid 19 pandemic. Furthermore, the total number of people suffering from some type of disability (either life-long, or injury related, or more commonly related to chronic conditions) will continue to rise [5]. In addition to that, approximately 33% of persons over the age of 65 and 50% of persons over the age of 85 experience a fall each year [6], [7]. For this population, healthcare costs are increasing [8], quality of life and productivity are reclining, and in many cases, family members serve as primary-care assistants.

These issues along with the challenges of effectively managing and treating postoperative rehabilitation patients, disabled people, and persons with special abilities, highlight the requirement for new and innovative ways to deliver healthcare to patients. In response to that, information and communication technologies are expected to provide the means to realize personalized, low-cost, and citizen-centered healthcare solutions to address the previously stated challenges [9]. Recent advances in sensor communication, sensor miniaturization, and microelectronics have enabled healthcare providers to monitor and manage chronic diseases and detect potentially urgent or emergent conditions [10]. Health monitoring in the home environment can be accomplished by either or both of the following [11]: 1) ambulatory monitors that utilize wearable sensors and devices to record physiological signals and 2) sensors embedded in the home environment and furnishings to collect behavioral and physiological data unobtrusively. Acceptance and positive psychological impact of monitoring technology have been confirmed in studies that have included people with dementia as well as other chronic conditions [12].

Moving a step further, early detection and diagnosis of critical health changes could enable prevention of most of these problems, saving billions of dollars annually [13], [14]. Early detection, however, requires continual vigilance. Due to the nature of their conditions or the lack of training and experience, many among this population are either disinclined or unable to detect and report the critical observations that could make a difference. Early approaches toward addressing this issue were for healthcare professionals to monitor patients directly or via relatively crude and bulky physiological data collection devices. Obviously, devices of such size and cost, which also include several wires and require the patient to be immobilized to acquire reliable measurements, are unsuitable when ubiquitous, unobtrusive, long-term, and low-cost health monitoring is desired. However, the new generation of inexpensive, unobtrusive wearable/implanted devices [15] could potentially lead to early and automatic detection of critical changes onto a patient’s health condition. In this context, such devices should not just be simple data collection appliances, nor should they only report variations from sampled population norms. Rather, they should be able to learn individual user baselines and employ advanced information processing algorithms and diagnostics in order to discover problems autonomously and detect alarming health trends, and consequently, inform medical professionals for further assistance. These wearable systems should also be engineered to integrate seamlessly both with portable equipment carried by first-responders and with fixed-location systems installed in hospitals.

Furthermore, as it was mentioned in the previous section, the ultimate future goal of employing wearable health-monitoring technology is to perform early identification or even prevention of diseases and health episodes. As a result, advanced inference logic and embedded intelligent information processing are required for the WHMS to be able to identify alarming trends in the health status of the user and to provide patient adaptive alarms or even diagnoses. Some preliminary efforts toward addressing the previously mentioned issues are reported in [17] and [18], where researchers have employed mobile phones to implement machine learning algorithms to detect heart arrhythmias using the recorded ECG signals. However, wearable sensor technology enables the recording of several additional physiological parameters concurrently with the user’s context [16]. By fusing together all this information while employing standard medical knowledge bases, advanced diagnostics, intelligent inference, and learning mechanisms, an overall estimation of the user’s health state can possibly be derived at any given time.

The means by which this information may be collected is by the wearing of a biosensor.  A wearable biosensor is a miniature sensing device, such as a surface electrode or a skin patch, which can measure a certain physiological parameter. A WHMS employing a variety of biosensors is thus capable of collecting real-time measurements of vital signs and other physiological signals. By applying proper signal processing on the measured data, important diagnostic features can be extracted from every individual signal.

However, the fact is that for an accurate estimation of one’s health condition and the diagnosis of many, if not the most, diseases several symptoms than just the ones detected from biosensor measurements, need to be taken into consideration [19]. These symptoms, like cough, malaise, or chest discomfort for example, are not quantifiable or measurable via sensors. On the contrary, to get feedback from the patient about the possible existence of these symptoms, the patient himself needs to indicate their occurrence.

Getting ahead of chronic diseases, costly acute events, and sudden deterioration is the goal of every provider – and reimbursement structures are finally allowing them to develop the processes that will enable proactive, predictive interventions.

Artificial intelligence will provide much of the bedrock for that evolution by powering predictive analytics and clinical decision support tools that clue providers into problems long before they might otherwise recognize the need to act.

AI can provide earlier warnings for conditions like seizures or sepsis, which often require intensive analysis of extraordinarily complex datasets.

Machine learning can also help support decisions around whether or not to continue care for critically ill patients, such as those who have entered a coma after cardiac arrest, says Brandon Westover, MD, PhD, Director of the MGH Clinical Data Animation Center.

Typically, providers must visually inspect EEG data from these patients, he explained.  The process is time-consuming and subjective, and the results may vary with the skill and experience of the individual clinician.

“In these patients, trends might be slowly evolving,” he states.  “Sometimes when we’re looking to see if someone is recovering, we take the data from ten seconds of monitoring at a time.  But trying to see if it changed from ten seconds of data taken 24 hours ago is like trying to look if your hair is growing longer.”

“But if you have an AI algorithm and lots and lots of data from many patients, it’s easier to match up what you’re seeing to long term patterns and maybe detect subtle improvements that would impact your decision around care.”

Leveraging AI for clinical decision support, risk scoring, and early alerting is one of the most promising areas of development for this revolutionary approach to data analysis.

By powering a new generation of tools and systems that make clinicians more aware of nuances, more efficient when delivering care, and more likely to get ahead of developing problems, AI will usher in a new era of clinical quality and exciting breakthroughs in patient care.

As a result, VitalKey Medical Innovations – a Wyoming Corporation – is, at the time of this writing, in the early stages of development of a VitalKey wearable “early warning device” capable of continuously capturing data, organizing it into customized patient and condition models, and communicate each wearer/patient’s unique information. When released to the public in Phase I VitalKey will be capable of notifying vital early warning information to specific Family Members as well as medical staff who subscribe to the VitalKey Detection Network.

Within the VitalKey architecture its Smart AI evaluates the language of the Human Body, its Vitals looking for variations, patterns weighed against acceptable standards.  Every two minutes it evaluates Body Temperature, Respiration rates, Blood Pressure, ECG, Pulse, HRV or Heart Rate Variables, Stress Signals, Oxygen levels and compares it to previous data evaluating for variations to the wearers “norms”.  VitalKey goes well beyond providing insights into the “language of the human body” by also evaluating their wearers sleep patterns and exercise patterns.  Lastly, fall detection and the ability to notify and seek assistance when the wearer is non-responsive is within each early warning devise.  Should the wearer become incapable of summoning assistance within specific time frames the AI shares the location of the wearer through a unique Global Positioning monitoring network thus providing access to location and condition of the wearer.

It is the intention in Phase II of VitalKey to transform the Phase I “early warning device” into a Class II Medical Devise with the capability of making this valuable information available to medical personnel, first-responders and in Phase III hospital personnel. Thus, the value of incorporating the MyDoc Telemedicine Portal within the VitalKey Phase II devise. When the VitalKey AI determines specific metrics and algorithms are indictive of potential risks it will send an alert to the MyDoc Portal where specific family members (Phase I), as well as medical professionals assigned by region are able to evaluate patterns and proactively contact the wearer of VitalKey to schedule remote, visual interaction thus gaining additional visual, verbal insights from the wearer himself concerning what they are experiencing.  The MyDoc Medical Network will provide Physician Telemedicine professionals for those who subscribe to the MyDoc medical services.

For more information concerning VitalKey Medical Innovations and its VitalKey Wearable devise visit: www.Vitalkey.cc.

[1] Y. Hao and R. Foster, “Wireless body sensor networks for health monitoring applications,” Physiol. Meas., vol. 29, pp. R27–R56, Nov. 2008.

[2] G. Beets, “EU Demographics: Living longer and reproducing less,” Pharmaceuticals Policy Law, vol. 9, pp. 29–40, 2007.

[3] A. H. Abdelhafiz, “Heart failure in older people: Causes, diagnosis and treatment,” Age Ageing, vol. 31, pp. 29–36, 2002.

[4] L. Fass, “Patient-centric healthcare,” in Proc. 3rd IET Int. Conf. Med. Electr. Devices Technol., Oct. 2007, pp. 77–109.

[5] G. Zhao, E. S. Ford, C. Li, J. E. Crews, and A. H. Mokdad, “Disability and its correlates with chronic morbidities among U.S. adults aged d 50-<65 years,” Prev. Med., vol. 48, pp 117-121, 2009.

[6] J. West, J. Hippisley-Cox, C. A. C. Coupland, G. M. Price, L. M. Groom, D. Kendrick, and E. Webber, “Do rates of hospital admission for falls and hip fracture in elderly people vary by socioeconomic status?” Public Health, vol. 118, pp. 576–581, Dec. 2004.

[7] I. Melzer, N. Benjuya, and J. Kaplanski, “Postural stability in the elderly: A comparison between fallers and non-fallers,” Age Ageing, vol. 33, pp. 602–607, Nov. 2004.

[8] G. Troster, “The agenda of wearable healthcare,” in ¨ IMIA Yearbook of Medical Informatics. Stuttgart/NY: Schattauer-Verlag, 2005, pp. 125– 138.

[9] The World Health Organization. (2009, Oct. 9). The World Health Report 2008, Primary Health Care, Now More Than Ever. World Health Org., Geneva, Switzerland. [Online]. Available: www.who.int

[10] B. G. Celler, N. H. Lovell, and D. K. Chan, “The potential impact of home telecare on clinical practice,” Med. J. Aust., vol. 171, pp. 518–521, 1999.

[11] N. Maglaveras, V. Koutkias, I. Chouvarda, and D. Goulis, “Home care delivery though mobile telecommunication platform: The citizen health system,” Int. J. Med. Inf., vol. 68, pp. 99–111, 2002.

[12] M. Alwan, J. Leachtenauer, S. Dalal, D. Mack, S. Kell, B. Turner, and R. Felder, “Physiological impact of monitoring technology in assisted living: A pilot study,” in Proc. 2nd IEEE ICTTA, Apr. 2006, pp. 998– 1002.

[13] C. Kalb, “Fixing America’s hospitals,” Newsweek Mag., vol. 148, pp. 44– 46, Oct. 2006.

[14] N. Bourbakis and J. Gallagher, “DIAGNOSIS: A synergistic co-operative framework of new generation health diagnosis systems for people with disabilities and the elderly,” in Proc. Int. Conf. CS, 2008, pp. 730–735.

[15] A. Lymperis and A. Dittmar, “Advanced wearable health systems and applications, research and development efforts in the European Union,” IEEE Eng. Med. Biol. Mag., vol. 26, no. 3, pp. 29–33, May/Jun. 2007.

[16] A. Pantelopoulos and N. Bourbakis, “A survey on wearable sensor-based systems for health monitoring and prognosis,” IEEE Trans. Syst., Man Cybern. C, Appl. Rev., vol. 40, pp. 1–12, Jan. 2010.

[17] Z. Jin, J. Oresko, S. Huang, and A. C. Cheng, “HeartToGo: A personalized medicine technology for cardiovascular disease prevention and detection,” in Proc. IEEE/NIH LiSSA, 2009, pp. 80–83.

[18] J. Rodriguez, A. Goni, and A. Illarramendi, “Real-time classification of ECGs on a PDA,” IEEE Trans. Inf. Technol. Biomed., vol. 9, no. 1, pp. 23–34, Mar. 2005.

[19] L. M. Tierney, Jr., S. J. McPhee, and M. A. Papadakis, Current Medical Diagnosis & Treatment, 45th ed. New York: McGraw-Hill, 2006.

Leave a Reply

Your email address will not be published. Required fields are marked *