With connected medical devices, apps and data, life sciences organizations can bridge long-standing gaps in healthcare and deliver a more continuous care experience, says Brian Williams, Cognizant’s Chief Digital Officer for Life Sciences.
Global health systems have traditionally delivered services episodically, by focusing on acute, critical care rather than individual health and well-being. It should come as no surprise, then, that life sciences companies often deliver their solutions following that same model of care.
Sadly, this leads to gaps in data and service alignment, not to mention significant disconnects with the broader healthcare ecosystem. Consumer devices and wellness apps, for example, often exist within their own individual siloes — causing organizations to miss out on valuable data that could inform patient diagnosis, management and treatment.
This lack of orchestration produces sub-optimal outcomes at significant expense to providers, payers and patients alike. It is also at direct odds with patients’ increasing digital expectations when using medical devices and when taking drugs and therapies. Whether they are participating in a clinical trial, living with a chronic condition or recovering from a procedure, patients expect to be informed and cared for with seamless digital experiences on par with what they receive when shopping or banking online.
However, the emergence of integrated, connected devices, apps and data has opened new possibilities for treatments and clinical trials. This new level of connectivity helps bridge a longstanding gap in wellness: the disconnect between an individual’s everyday health behavior and their episodic healthcare. These experiences generate valuable data insights, creating new commercial opportunities and the promise of better patient outcomes.
The impact of life sciences connectivity
Drawing from our recent series on healthcare IoT, here are three stakeholder groups within the healthcare and life sciences ecosystem that stand to benefit greatly from this new level of connectivity and the more continuous, predictive and preventive care it enables.
- Patients with chronic conditions. Chronic diseases are often accompanied by additional conditions, such as depression, that can impede effective treatment. Consequently, information about an individual’s behavioral health status has become increasingly important in treatment decisions, as has information about the individual’s relationships with the people around them.
- Wearable IoT devices that monitor fitness and health conditions can pair with an ever-growing set of apps for health, wellness and nutrition monitoring. Over time, a baseline of physiological indicators such as an individual’s heart rate and blood pressure, as well as activity, diet and sleep patterns, will develop. When additional data from clinical encounters, including diagnostic imaging, lab tests, genomics, stress tests and physician notes, is integrated with that baseline, it increases the ability to predict how an individual may respond to any particular treatment.
- Elderly patients. Quite often, the most effective tools for early detection of a developing condition in elderly patients are not implants or biometric monitors, but devices that monitor changes in activities of daily living (ADL).
- For example, the onset of congestive heart failure can be detected through reduced use of the bed, as patients with trouble breathing when lying down switch to sleeping semi-upright in a recliner. Changes in toilet flushes, meanwhile, can detect a urinary tract infection or incipient dehydration. Moreover, while one in four Americans over 65 falls each year, only half tell their doctor.
- Passive infrared motion detectors, pressure sensors in beds and chairs, sensors for CO2 concentration, sound (vibration) and video — anonymized as necessary for privacy — can all be used to first establish a baseline of normal variability, and then be applied to detect significant deviations from that baseline. This continuous and nearly invisible sensing can be surprisingly effective in assisting in care.
- Hospital clinicians and support staff. Healthcare is increasingly a team enterprise — including not only physicians, nurses, allied health staff and technicians but also AI-enabled equipment. The point of care is also expanding, with shortened hospital stays and more care delivered in outpatient facilities and in-home settings.
- Connected sensors enable every member of the team to access to real-time data relevant to their task. Smart hospitals with a real-time health system (RTHS) can leverage sensors to collect data widely, distill and analyze it — and then quickly distribute curated findings to users. When captured remotely, this eases the transition in care from the hospital to other settings, allowing a more continuous and participatory level of care that extends long past a patient’s physical stay in a healthcare facility.
- An RTHS can improve operations, clinical tasks and patient experience. For example, providers that boost operational effectiveness typically rely on a wide range of IoT-enabled asset management solutions that locate mobile assets, monitor equipment operating conditions and track inventories of consumables, pharmaceuticals and medical devices. This optimizes equipment utilization, reduces waste, increases equipment uptime and ensures optimal inventories.
- Once clinicians and support staff can view how long various steps take in their workflows, where delays occur and what patients experience as a result, they can then evolve solutions based on a combination of their intimate day-to-day knowledge and data on how that workflow interacts with or is used by other functions.
From episodic to continuous care
Too often, the life sciences industry has delivered a one-size-fits-all approach to clinical trials and patient care that may not represent real-life, individual situations — situations that require tailored engagement that wrap therapies and interventions in end-to-end, digital solutions.
This can and should change. Device connectivity and access to data are impacting every aspect of healthcare and life sciences, moving the industry away from acute, episodic care, to a system that is more participatory and predictive.
For example, a patient may be walking a mere 24 hours after a typical hip surgery and could be discharged from the hospital a day or two after the procedure. However, that episodic care experience belies a much longer recovery and rehabilitation period spanning weeks or months.While that care experience today takes place largely outside the purview of the orthopedic surgeon, better device connectivity can enable patient monitoring — and even patient services — to be extended well beyond the length of the initial hospital visit.
Rather than relying on spotty reporting from physical therapists or the patients themselves, an orthopedist can continuously and seamlessly track a patient’s progress, and then decide when and how to intervene if things aren’t going as expected. Zimmer’s mymobility application, which supports patient engagement and monitoring outside the hospital following surgery, is a good example of what this looks like in practice.
A fully orchestrated ecosystem
Sensors and instrumentation — and the hundreds of APIs that connect them — can provide accurate and timely data about many parameters of the human condition. When this is all properly orchestrated, we can better understand how diseases progress and how bodies respond to various interventions.
That’s the intent behind our alliance with Philips and its HealthSuite Digital Platform, which is built on AWS and designed to simplify and standardize device connectivity, data access, identity management, and structured and unstructured data management within a high-trust, HIPAA and GDPR-compliant environment.
We believe that life sciences companies can derive true value from this influx of new data. Not only can the resulting insights inform new services, drugs and therapies and inspire new models of continuous engagement; they can also improve adherence to treatment and patient health.
To learn more, visit the Life Sciences section of our website.
- Wayne, Greg (December 1, 2011). “Tiny Biocomputers Move Closer to Reality”. Scientific American. Retrieved May 10, 2020.
- Flint, Maria Louise; Dreistadt, Steve H. (1998). Clark, Jack K. (ed.). Natural Enemies Handbook: The Illustrated Guide to Biological Pest Control. University of California Press. ISBN 9780520218017.
M. Birkholz; A. Mai; C. Wenger; C. Meliani; R. Scholz (2016). “Technology modules from micro- and nano-electronics for the life sciences”. WIREs Nanomed. Nanobiotech. 8 (3): 355–377. doi:10.1002/wnan.1367. PMID 26391194
- “Third National Report on Human Exposure to Environmental Chemicals” (PDF). Centers for Disease Control and Prevention – National Center for Environmental Health. Retrieved 9 August 2009.
- Tanner, Rene. “LibGuides: Life Sciences: Conservation Biology/Ecology”. libguides.asu.edu. Retrieved 2020-05-30.
- “fermentation | Definition, Process, & Facts”. Encyclopedia Britannica. Retrieved 2020-05-30.
- Geller, Martinne (22 January 2014). “Nestle teams up with Singapore for food science research”. Reuters. Retrieved 9 February 2014.
- “Food science to fight obesity”. Euronews. 9 December 2013. Retrieved 9 February 2014.
- Bhatia, Atish (16 November 2013). “A New Kind of Food Science: How IBM Is Using Big Data to Invent Creative Recipes”. Wired. Retrieved 9 February 2014.
- National Human Genome Research Institute (2010-11-08). “A Brief Guide to Genomics”. Genome.gov. Retrieved 2011-12-03.
- Klug, William S. (2012). Concepts of Genetics. Pearson Education. ISBN 978-0-321-79577-9.
- Pevsner, Jonathan (2009). Bioinformatics and functional genomics (2nd ed.). Hoboken, N.J: Wiley-Blackwell. ISBN 9780470085851.
National Human Genome Research Institute (2010-11-08). “FAQ About Genetic and Genomic Science”
- Sun, Changming; Bednarz, Tomasz; Pham, Tuan D.; Vallotton, Pascal; Wang, Dadong (2014-11-07). Signal and Image Analysis for Biomedical and Life Sciences. Springer. ISBN 978-3-319-10984-8.
- Deisseroth, K.; Feng, G.; Majewska, A. K.; Miesenbock, G.; Ting, A.; Schnitzer, M. J. (2006). “Next-Generation Optical Technologies for Illuminating Genetically Targeted Brain Circuits”. Journal of Neuroscience. 26 (41): 10380–6. doi:10.1523/JNEUROSCI.3863-06.2006. PMC 2820367. PMID 17035522.
- Mancuso, J. J.; Kim, J.; Lee, S.; Tsuda, S.; Chow, N. B. H.; Augustine, G. J. (2010). “Optogenetic probing of functional brain circuitry”. Experimental Physiology. 96 (1): 26–33. doi:10.1113/expphysiol.2010.055731. PMID 21056968. S2CID 206367530.
- Ermak G., Modern Science & Future Medicine (second edition), 164 p., 2013
- Wang L (2010). “Pharmacogenomics: a systems approach”. Wiley Interdiscip Rev Syst Biol Med. 2 (1): 3–22. doi:10.1002/wsbm.42. PMC 3894835. PMID 20836007.Vallance P, Smart TG (January 2006). “The future of pharmacology”. British Journal of Pharmacology. 147 Suppl 1 (S1): S304–7. doi:10.1038/sj.bjp.0706454. PMC 1760753. PMID 16402118.