Review Article

Healthc Inform Res. 2016 July;22(3):156-163.

http://dx.doi.org/10.4258/hir.2016.22.3.156
pISSN 2093-3681 • eISSN 2093-369X

Medical Internet of Things and Big Data in

Healthcare
Dimiter V. Dimitrov, MD, PhD
Diavita Ltd., Varna, Bulgaria

Objectives: A number of technologies can reduce overall costs for the prevention or management of chronic illnesses. These
include devices that constantly monitor health indicators, devices that auto-administer therapies, or devices that track real-
time health data when a patient self-administers a therapy. Because they have increased access to high-speed Internet and
smartphones, many patients have started to use mobile applications (apps) to manage various health needs. These devices
and mobile apps are now increasingly used and integrated with telemedicine and telehealth via the medical Internet of
Things (mIoT). This paper reviews mIoT and big data in healthcare fields. Methods: mIoT is a critical piece of the digital
transformation of healthcare, as it allows new business models to emerge and enables changes in work processes, productiv-
ity improvements, cost containment and enhanced customer experiences. Results: Wearables and mobile apps today support
fitness, health education, symptom tracking, and collaborative disease management and care coordination. All those platform
analytics can raise the relevancy of data interpretations, reducing the amount of time that end users spend piecing together
data outputs. Insights gained from big data analysis will drive the digital disruption of the healthcare world, business process-
es and real-time decision-making. Conclusions: A new category of “personalised preventative health coaches” (Digital Health
Advisors) will emerge. These workers will possess the skills and the ability to interpret and understand health and well-being
data. They will help their clients avoid chronic and diet-related illness, improve cognitive function, achieve improved mental
health and achieve improved lifestyles overall. As the global population ages, such roles will become increasingly important.

Keywords: Telemedicine, Smartphone, Mobile Applications, Wireless Technology, Disease Management

I. Introduction sors, and network connectivity, which enables these objects

to collect and exchange data [1]. Its impact on medicine
The Internet of Things (IoT) is a network of physical devices will be perhaps the most important, and personal, effect. By
and other items, embedded with electronics, software, sen- 2020, 40% of IoT-related technology will be health-related,
more than any other category, making up a $117 billion
Submitted: June 29, 2016 market [2]. The convergence of medicine and information
Accepted: July 18, 2016
technologies, such as medical informatics, will transform
Corresponding Author healthcare as we know it, curbing costs, reducing inefficien-
Dimiter V. Dimitrov, MD, PhD cies, and saving lives.
Diavita Ltd., Varna, Bulgaria. E-mail: dimiter.v. [email protected] Figure 1 illustrates how this revolution in medicine will
This is an Open Access article distributed under the terms of the Creative Com- look in a typical IoT hospital, in practice. A patient with
mons Attribution Non-Commercial License (http://creativecommons.org/licenses/by- diabetes will have an ID card that, when scanned, links to a
nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduc-
tion in any medium, provided the original work is properly cited. secure cloud which stores their electronic health record vi-
ⓒ 2016 The Korean Society of Medical Informatics tals and lab results, medical and prescription histories. Phy-
sicians and nurses can easily access this record on a tablet or
 IoT and Big Data in Healthcare

Health Cloud

EHR

Medical
tablet Desktop
Body temp
Physician manager Database
sensor
Gateway to
other services
Glucose
sensor Blood pressure
sensor
Insulin
pump

Biobanks Sensor/actuator
with low-power TRx
clinical trials
RFID Reader Network Hub Wearables

Figure 1. ‌An illustration of how this

revolution in medicine will
look in a typical Internet
of Things (IoT) hospital, in
Patient practice.

desktop computer. securely stores private medical data that can be used for can-
It sounds pretty basic, but the adoption of Electronic Health cer research. Though the platform began with cancer, Intel
Records (EHRs) is a game changer. In less than a decade, an intends to open up the federated cloud network to other
ink-and-paper system of managing records that goes back institutions, including ones working on cures to diseases like
thousands of years will be digitized and replaced [3]. The ad- Parkinson’s.
vantages are obvious and many. Paper records, often written Engineering simulation solutions are making medicine
in questionable penmanship, can get stuffed away in filing participatory, personalized, predictive and preventive (P4
cabinets, out of the reach of researchers or other healthcare medicine) via the medical Internet of Things (mIoT) [6].
providers. Instead, by keeping all the important information
in one place, and easily sharable, EHRs will eliminate many II. IoT - The Future of Pharma?
inefficiencies, and save lives.
One of the major challenges to implementing the IoT has Pharma companies long ago realized that just selling tradi-
to do with communication; although many devices now tional medicines will not produce growth nor even sustain
have sensors to collect data, they often talk with the server in competitiveness. This fundamental change, known as mov-
their own language. Manufacturers each have their own pro- ing ‘beyond the pill’, typically arises from one or two realiza-
prietary protocols, which means sensors by different mak- tions: (1) medicines alone are often not enough to achieve
ers can’t necessarily speak with each other. This fragmented optimal clinical outcomes for patients, and (2) as pharma-
software environment, coupled with privacy concerns and ceutical pipelines dry up, ‘beyond-the-pill’ businesses can be
the bureaucratic tendency to hoard all collected information, valuable new sources of revenues. This has created growing
frequently maroons valuable info on data islands, undermin- interest in methods of utilizing the new technologies and
ing the whole idea of the IoT. business processes for development and patient care, leading
Precision medicine, as it’s called, is a term that will be fre- to Pharma IoT.
quently heard in coming years [4]. It begins with genomics The Pharma IoT concept involves digitalization of medical
and goes through the rest of the omics platforms, provid- products and related care processes using smart connected
ing multiscale data for analysis and interpretation [5]. In medical devices and IT services (web, mobile, apps, etc.)
2015, Intel and the Oregon Health and Science University during drug development, clinical trials and patient care.
launched a joint project, the Collaborative Cancer Cloud: The outcomes of Pharma IoT in development and clinical
a high-performance analytics platform that collects and trials can employ combinations of advanced technologies

Vol. 22 • No. 3 • July 2016 www.e-hir.org 157

Dimiter V. Dimitrov

and services to create totally new kinds of disease treatment • ‌Glaxo recently announced that it is investing in electro-
possibilities (e.g., Treatment 2.0). ceuticals, bioelectrical drugs that work by micro-stimula-
In patient care, Pharma IoT will enable patients and health- tion of nerves [13].
care professionals to use medicines with advanced sensor • ‌J&J has teamed up with Google to develop robotic sur-
hardware, and craft personalized care services and processes gery. In addition, they are collaborating with Philips on
(Product 2.0). Good examples of the Pharma IoT solutions wearable devices such as blood pressure monitors [14].
are the connected sensor wearables for Parkinson’s disease • ‌Novartis is working with Google (again) on sensor tech-
and multiple sclerosis patients, which provide medication nologies, such as the smart lens, and a wearable device to
management, improving the patient outcomes and the qual- measure blood glucose levels [15].
ity of life [7]. Sensors can provide a lot of information to support pharma
In addition, existing medical device products such as inhal- development, but it is particularly important to recruit the
ers and insulin pens can be added to the sensor and connec- right patients for the right clinical trials. Body sensors, once
tivity technologies to collect data for further care analytics, gadgets that were mainly used by athletes and runners, are
and even personalized therapy [8]. All this will substantially now rapidly entering the general market, and consumers and
improve personal medication and care processes, because pharma will soon have access to a wealth of information in-
patient care data provides new sources of innovation and cluding not only pulse, blood pressure, ECG and respiratory
competitiveness. rate, but also more advanced data, such as inflammation,
The transformation also involves some challenges: at the sleep patterns, etc.
same time, pharma companies need to take into account the A number of mobile apps which support device handling
forthcoming European Union (EU) data protection and pri- have emerged, including myDario and SleepBot among
vacy legislation, which will give patients control of their care others [16,17]. The Hacking Medicine Institute recently an-
data [9]. For example, patients will be allowed to transfer nounced RANKED Health, a program to critically evaluate
their care and health data across multiple service providers, and rank health-focused applications and connected devices
leading to the emergence of totally new kinds of service plat- [18].
forms and business models, e.g., data brokers [10]. It has been predicted that in the near future we will look at
our phone or smart watch to check health outcomes more
III. ‌Devices and Mobile Apps for often than we do now to check our mail or WhatsApp. A
Healthcare typical situation might involve an elderly person, recovering
from a medical condition at home, linked to a combination
We are heading into the age of information, where knowl- of several connected services streaming data towards differ-
edge and data will be key. We are also entering the age of the ent parties, such as family members, tele-carer and physi-
customer, in which more than ever the customer is going to cians (Figure 2).
determine what they want. myTomorrows is one example of Recently it was announced that Medtronic will be partner-
the changing look of business models, in this case, directly ing with a digital health app company named Canary Health
connecting customers and pharma [11]. to be a re-seller of its digital chronic disease management
In this new age, devices and apps will be used to create a programs, including its CDC-recognized Diabetes Preven-
“health selfie”. For example: tion Program, which is aimed at changing behaviors in pre-
• The
‌ Myo, originally a motion controller for games, is now diabetic people. But the partnership goes beyond just resell-
being used in orthopedics for patients who need to ex- ing Canary Health’s digital tools. In fact, both Canary Health
ercise after a fracture. With the aid of the Myo, patients and Medtronic plan to develop solutions that “leverage
can monitor their progress and doctors can measure the Medtronic’s devices, services and infrastructure as well as
angle of movement. Canary Health’s suite of behavior-change programs, design
• The
‌ Zio Patch measures heart rate and electrocardiogram expertise, and deep user engagement experience,” according
(ECG) and is the US Food and Drug Administration ap- to a Canary Health news release [19].
proved [12]. One reason that Medtronic must have been attracted to Ca-
Where is pharma in all this turmoil? Interestingly, there nary Health is that the company’s digital tools are reimburs-
are signs that pharma is reaching out from its traditional able. As digital health programs mature, payers are looking
medicine-centric approach. at innovative, yet proven, ways to reduce their cost burden

158 www.e-hir.org http://dx.doi.org/10.4258/hir.2016.22.3.156

 IoT and Big Data in Healthcare

Bio samples
Telehealth

Vital signs Food

Career
a Stress
Health coach
Service can Figure 2. ‌A typical situation involved
help you
Relationships
with... Exercise an elderly person, recover-
Rehab
tracking Sleep
ing from a medical condi-
todiforfitness.com
tion at home, linked to
Telemedicine

a combination of several
Medication connected services stream-
tracking ing data towards differ-
ent parties, such as family
members, tele-carer and
physicians.

for chronic diseases like diabetes. tions Salesforce to be able to bridge the gap between patient’s
According to the Centers for Disease Control and Preven- medical data and pharma.
tion (CDC), people with prediabetes who take part in a “Big data” is a phrase that has been used pervasively by
structured lifestyle change program—like the one Canary the media and the lay public in the last several years. While
Health has developed, or programs championed by Omada many definitions have been proposed, the common de-
Health and Noom Health, among others—“can cut their risk nominator seems to include the “three V’s”—Volume (vast
of developing type 2 diabetes by 58% (71% for people over amounts of data), Variety (significant heterogeneity in the
60 years old)” [20]. The CDC adds that “this finding was the type of data available in the set), and Velocity (speed at
result of a program helping people lose 5% to 7% of their which a data scientist or user can access and analyze the
body weight through healthier eating and 150 minutes of data) [23].
physical activity a week” [21]. Defined as such, healthcare has become one of the key
Given that diabetes is an expensive, chronic disease, hos- emerging users of big data. For example, Fitbit and Apple’s
pitals, doctors, patients, and payers are equally keen to tame ResearchKit can provide researchers access to vast stores of
this epidemic. In other words, the move is helping to trans- biometric data on users, which can then be used to test hy-
form companies from simply providing care to the sick to potheses on nutrition, fitness, disease progression, treatment
actually delivering healthcare. success, and the like.
Most complex high dimensional data sets include imag-
IV. Data, Data, Data ing (photos, X-rays, MRIs, and slides), wave analysis such as
EEG and ECG, audio files with associated transcripts, free
The driver behind all these wearable sensors is the data that text notes with natural language processing (NLP) outputs,
is generated, and various parties are trying to bundle the and mappings between structured concepts such as lab tests
data streams and obtain control. Microsoft developed the and the Logical Observation Identifiers Names and Codes
Health Vault, an e-health safe, acting as an EMR. In Holland (LOINC) codes or the International Classification of Dis-
the Radboud University Medical Center collaborated with eases-9 (ICD9) and ICD10 codes. Among the things that the
Philips and Salesforce on HereIsMyData, a database where data analysis should provide is the means to continuously
patients can store their health data and determine who can update the annotations based on acquired knowledge, while
access them [22]. The role of Salesforce is interesting. The keeping the location of the data in place.
Salesforce platform powers Veeva, the customer relationship The Centers for Medicare & Medicaid Services (CMS) have
management (CRM) now widely used in pharma. This posi- vast stores of billing data that can be mined to promote high

Vol. 22 • No. 3 • July 2016 www.e-hir.org 159

Dimiter V. Dimitrov

value care; the same is true of private health insurers. And easy to connect devices and perform device management
hospitals have attempted to reduce re-admission rates by functions, scaled through cloud-based services, and to apply
targeting patients where predictive artificial intelligence (AI) analytics to gain insight and achieve organizational transfor-
algorithms indicate people who may be at highest risk based mation.
on an analysis of available data collected from existing pa- (2) Easy device management: A thoughtful approach to
tient records (Figure 3). device management enables improved asset availability,
Underlying these and many other potential uses, however, increased throughput, minimized unplanned outages and
are a series of technology, legal and ethical challenges relat- reduced maintenance costs.
ing to, among other things, privacy, discrimination, intellec- (3) Information ingestion: Intelligently transform and store
tual property, tort, and informed consent, as well as research IoT data. APIs bridge the divide between the data and the
and clinical ethics [24]. cloud, making it easy to pull in the data that’s needed. Data
is ingested from diverse data sources and platforms, then the
V. Challenges for mIoT essential values are extracted using rich analytics.
(4) Informative analytics: Gain insight from huge volumes
Leading IoT platforms must provide simple, powerful ap- of IoT data to make better decisions and optimize opera-
plication access to IoT devices and data to help designers tions. Apply real-time analytics to monitor current condi-
rapidly compose analytics applications, visualization dash- tions and respond accordingly. Leverage cognitive analytics
boards and mIoT apps. The following are 5 key capabilities with both structured and unstructured data to understand
that leading platforms must enable: situations, reason through options, and learn as conditions
(1) Simple connectivity: A good IoT platform makes it change. An intuitive dashboard makes it all easy to under-

Clinical data
EHR data
Molecular omics data
Wearables data

Medical apps
developers

Billions Big data Data warehouse Study centric

Region Architecture
Subject of matter Variables
Millions Segmentation
Product category
State Big
Big data
Dimensionality reduction Principal components analysis
toolbox
Data
K nearest neighbors
Hundreds of thousands Extraction of groups Support vector machines Warehouse
Factor analysis

Missing values & outliers Repository

Prescriptive analysis Generalize
Descriptive analysis Predictive analysis
ANOVA, T test, etc.
Compare
Thousands Define training set Define fitness function f(x)

Squared error
Correlations
ID causes and effects Accuracy
Linear regression
Machine Likelihood
Probability
learning Cost/utility
Pattern recognition Real-time data Simulation
Recursive
Markov chain monte carlo Neural networks Symbolic artificial intelligence
Random forests Gradient descent Agent-based models
Recommender systems Cellular automata
Neural networks Discrete event simulation
Logistic regression
Data
visualization
Figure 3. The Centers for Medicare & Medicaid Services (CMS) data system.

160 www.e-hir.org http://dx.doi.org/10.4258/hir.2016.22.3.156

 IoT and Big Data in Healthcare

stand. suggestions from billions of record options). (2) It is also

(5) Reduced risk: Act on notifications and isolate incidents sufficiently flexible to allow machine learning, and AI will be
generated anywhere in the company environment from a able to function in a real-time fashion.
single console.
VII. ‌New Generation of Digital Health Ad-
VI. Challenges for Big Data in Healthcare visors
The challenges fall into two main categories: fiscal/policy Once a data store has been built from many different
and technology. sources—EHR data, payer data, device and IoT data, patient
Fiscal and policy issues: In a fee-for-service environment, survey responses, consumer health data—and has been inte-
the only way that healthcare practitioners get paid is to have grated into a unified data structure, then AI can yield mean-
face-to-face encounters with patients. This creates heavy bias ingful insights. AI, after all, is about pattern recognition,
against promoting technologies that streamline non-face- comparing a particular pattern of data around a given indi-
to-face interactions. However, as we move away from that vidual with similar (not necessarily identical) patterns found
model and more towards value-based care, where global elsewhere, and making predictive recommendations based
risk-based payments are made to delivery organizations on what happened in those other situations. This is very
(hospitals, patient centered medical homes, accountable care much what clinicians do when exercising “clinical judge-
organizations, etc.), then there is more incentive to use new ment”—identifying a pattern, taking into account medical
technologies that reduce unnecessary in-office encounters. problems, medications, labs values, personal and family his-
In such an environment, face-to-face encounters are actually tory, and comparing it to similar patterns from the clinician’s
a cost center, not a profit center, and positive health out- experience.
comes of populations are rewarded. A new generation of “Health Coaches”, Tele-Carers or Digi-
Technology issues: The biggest technical barrier to achiev- tal Health Advisors can be trained to make these AI-derived
ing this vision is the state of health data. Created by legacy recommendations useful [26]. They need to be easy-to-use,
EHR systems, health data is largely fragmented into institu- consumer-orientated persons who can connect to the aggre-
tion-centered silos. Sometimes those silos are large, but they gated data store and the AI analytics engines that sit on top
are still silos. Exchanging individual records between silos, of that. They can empower consumers/patients, and reduce
using increasingly standardized vocabularies (code sets) the demand burden on clinicians. Will they replace clini-
and message formats (ADT messages, C-CDAs, even FHIR cians? No, of course not. But they will help filter the demand
objects), is where much current effort is being directed. But to those who truly need to be seen, while empowering pa-
that does not solve the problem of data fragmentation. More tients with real-time, believable and personalized guidance
and more people in the health information exchange arena for the more common things in day-to-day life [27].
are seeing that the next generation of health technology is So what stands in the way of Digital Health Advisors? Pol-
around aggregating data, not simply exchanging copies of in- icy (how we pay for healthcare) needs to encourage self-care
dividual records (the traditional query-response approach). and facilitate healthy behaviors, rather than encourage in-
Only by collecting the data from many different sources, office doctor visits. And, simultaneously, health data needs
normalizing that data into a consistent structure, resolving to become reorganized in order to empower AI and drive the
the data around unique patient identifiers as well as unique emergence of new apps and related technologies. It will be
provider identifiers—only then can the data become truly a while before we get there, but we can see the path to that
useful [25]. new generation of healthcare technology.
Aggregated data has two additional advantages. (1) It solves
the interoperability problem. Systems and institutions no VIII. Conclusion
longer need to build data bridges, and translate how the data
is structured between two proprietary systems; everyone The mIoT is revamping healthcare services, as people have
instead simply connects to a central standard API “plug.” If started using IoT to manage their health requirements. For
built right, the aggregated data can be the basis for very ef- example, people can use IoT devices to remind them about
fective AI technology. Such technology is very fast (consider appointments, changes in blood pressure, calories burnt and
Google suggestions as-you-type in a search bar, retrieving much more. One of the best parts of the IoTs in the health-

Vol. 22 • No. 3 • July 2016 www.e-hir.org 161

Dimiter V. Dimitrov

care industry is the remote health monitoring system, where kinet 2013;52(10):833-54.
patients can be monitored and advised from anywhere. 6. Flores M, Glusman G, Brogaard K, Price ND, Hood L.
Real-time location services are another major approach IoT P4 medicine: how systems medicine will transform the
offers. By using the service, doctors can easily track device healthcare sector and society. Per Med 2013;10(6):565-76.
locations, which directly reduces excess time spent. Smart- 7. van Uem JM, Maier KS, Hucker S, Scheck O, Hobert
phone usage is increasing rapidly, and people have started MA, Santos AT, et al. Twelve-week sensor assessment
using mobile apps for almost everything. When it comes to in Parkinson’s disease: impact on quality of life. Mov
the healthcare industry, mobile apps can improve communi- Disord 2016 May 31 [Epub]. http://dx.doi.org/10.1002/
cations between patients and doctors over a secured connec- mds.26676.
tion. 8. Dzubur E, Li M, Kawabata K, Sun Y, McConnell R, Intil-
The primary duty of Digital Health Advisors and the clini- le S, et al. Design of a smartphone application to monitor
cians will be to work collaboratively when the organization is stress, asthma symptoms, and asthma inhaler use. Ann
shifting towards IoT-enabled infrastructure. Proper training Allergy Asthma Immunol 2015;114(4):341-2.e2.
and feedback are mandatory for better deployment. The tra- 9. European Commission. Clinical trials - regulation EU
ditional method of recording a patient’s details, i.e., a pad of No 536/2014 [Internet]. Brussels: European Commis-
paper hanging on the patient’s bed, is not going to work any- sion; c2016 [cited at 2016 Jul 1]. Available from: http://
more, since such records are only accessible to a limited few, ec.europa.eu/health/human-use/clinical-trials/regula-
and can be lost or scrambled. This is an application where tion/index_en.htm.
on-field mobile/tablet technology might work, since they of- 10. INNT Foundation [Internet]. Amsterdam: INNT
fer hassle-free record management on the applications in the Foundation; c2016 [cited at 2016 Jul 1]. Available from:
device. Health data information will be available in just a tap https://www.innit.foundation.
when information is recorded electronically, once security 11. MyTomorrows [Internet]. Amsterdam: MyTomorrows;
and privacy issues are met. c2016 [cited at 2016 Jul 1]. Available from: https://myto-
morrows.com.
Conflict of Interest 12. Tung CE, Su D, Turakhia MP, Lansberg MG. Diagnostic
yield of extended cardiac patch monitoring in patients
No potential conflict of interest relevant to this article was with stroke or TIA. Front Neurol 2015;5:266.
reported. 13. Famm K, Litt B, Tracey KJ, Boyden ES, Slaoui M. Drug
discovery: a jump-start for electroceuticals. Nature
References 2013;496(7444):159-61.
14. Cuba-Gyllensten I, Gastelurrutia P, Riistama J, Aarts R,
1. Zanella A, Bui N, Castellani A, Vangelista L, Zorzi M. Nunez J, Lupon J, et al. A novel wearable vest for track-
Internet of things for smart cities. IEEE Internet Things ing pulmonary congestion in acutely decompensated
J 2014;1(1):22-32. heart failure. Int J Cardiol 2014;177(1):199-201.
2. Bauer H, Patel M, Veira J. The Internet of Things: sizing 15. Senior M. Novartis signs up for Google smart lens. Nat
up the opportunity [Internet]. New York (NY): McK- Biotechnol 2014;32(9):856.
insey & Company; c2016 [cited at 2016 Jul 1]. Avail- 16. MyDario.com [Internet]. Burlington (MA): MyDario.
able from: http://www.mckinsey.com/industries/high- com; c2016 [cited at 2016 Jul 1]. Available from: http://
tech/our-insights/the-internet-of-things-sizing-up-the- mydario.com/.
opportunity. 17. SleepBot [Internet]. New York (NY): SleepBot; c2013
3. Kruse CS, Kothman K, Anerobi K, Abanaka L. Adop- [cited at 2016 Jul 1]. Available from: https://mysleepbot.
tion factors of the electronic health record: a systematic com/.
review. JMIR Med Inform 2016;4(2):e19. 18. RANKED Health [Internet]. [place unknown: publisher
4. Scheen AJ. Precision medicine: the future in diabetes unknown]; [cited at 2016 Jul 1]. Available from: http://
care? Diabetes Res Clin Pract 2016;117:12-21. www.rankedhealth.com/about/.
5. van Leeuwen N, Swen JJ, Guchelaar HJ, 't Hart LM. The 19. Canary Health [Internet]. Los Angeles (CA): Canary
role of pharmacogenetics in drug disposition and re- Health Inc.; c2016 [cited at 2016 Jul 1]. Available from:
sponse of oral glucose-lowering drugs. Clin Pharmaco- http://www.canaryhealth.com/.

162 www.e-hir.org http://dx.doi.org/10.4258/hir.2016.22.3.156

 IoT and Big Data in Healthcare

20. Sepah SC, Jiang L, Peters AL. Long-term outcomes of a 24. Filkins BL, Kim JY, Roberts B, Armstrong W, Miller MA,
Web-based diabetes prevention program: 2-year results Hultner ML, et al. Privacy and security in the era of digi-
of a single-arm longitudinal study. J Med Internet Res tal health: what should translational researchers know
2015;17(4):e92. and do about it? Am J Transl Res 2016;8(3):1560-80.
21. Centers for Disease Control and Prevention. Lifestyle 25. Hackl WO. Intelligent re-use of nursing routine data:
change program details [Internet]. Atlanta (GA): Cen- opportunities and challenges. Stud Health Technol In-
ters for Disease Control and Prevention; c2016 [cited form 2016;225:727-8.
at 2016 Jul 1]. Available from: http://www.cdc.gov/dia- 26. Foley P, Steinberg D, Levine E, Askew S, Batch BC,
betes/prevention/lifestyle-program/experience/index. Puleo EM, et al. Track: a randomized controlled trial of
html. a digital health obesity treatment intervention for medi-
22. HereIsMyData [Internet]. Nijmegen: Radboud Universi- cally vulnerable primary care patients. Contemp Clin
ty Medical Center; c2015 [cited at 2016 Jul 1]. Available Trials 2016;48:12-20.
from: http://www.hereismydata.com/. 27. Giraldo-Rodriguez L, Torres-Castro S, Martinez-Ramirez
23. Auffray C, Balling R, Barroso I, Bencze L, Benson M, D, Gutierrez-Robledo LM, Perez-Cuevas R. Tele-care and
Bergeron J, et al. Making sense of big data in health re- tele-alarms for the elderly: preliminary experiences in
search: towards an EU action plan. Genome Med 2016; Mexico. Rev Saude Publica 2013;47(4):711-7.
8(1):71.

Vol. 22 • No. 3 • July 2016 www.e-hir.org 163