Smart data integration and decision support
along the patient pathway
In today’s digitalized healthcare environment, informed
medical decision-making increasingly depends on
the smart integration of data. However, there are many
barriers and challenges along the patient pathway.
Complex decisions may fail because data is inaccessible
or too extensive to evaluate, information is overlooked,
or guidelines are ignored. All this can lead to inefficient
and costly workflows and compromise clinical outcomes.
This paper presents a platform-based approach that lives
up to these challenges and offers holistic decision
support along the continuum of care, bringing together
a wide variety of healthcare data from diverse IT
systems with a vendor-neutral design and preparing
them in a user-friendly and meaningful way.
Such a unifying approach, including digital applications
powered by AI, can support operational decisions
for optimized care processes as well as diagnostic
and therapeutic decisions for optimized outcomes. In
addition, today’s digital solutions enable care teams
and patients to connect more easily, providing a
basis for patient-centered care and shared medical
Decision-making is part of everyday life. It
is a cognitive capacity for solving problems
in the face of various options for action.
In medicine, decisions have a clear goal:
the good of the patient. And these decisions
are shaped by professional standards, expert
knowledge, the wishes of the patient, and
the therapeutic possibilities.
In today’s digitalized healthcare environment,
achieving this goal increasingly depends
on the smart use of medical data. Certainly,
medicine is not data science. The art of
healing consists not least of social interaction.
Nevertheless, the continuously growing,
multidimensional health data from electronic
medical records, image databases, and other
multi-layered, often fragmented IT systems
is becoming more and more important for
making up-to-date, patient-oriented decisions
and designing care processes accordingly.
Of course, not all medical decisions are
necessarily difficult. There are uncomplicated
healthcare situations in which good basic
medical knowledge is sufficient to find an
expedient solution. Decisions are then
straightforward. However, the decision-making
becomes more complex as the number of
diagnoses and management options increase,
and as the amount of relevant patient data
and the risk of complications grow .
The challenge here is to integrate a wide range
of data – from a variety of sources, such as
clinical, radiological, or laboratory information,
genetic and pathological findings, and insights
into behavioral and social conditions – in
such a way that the decision meets the highest
possible quality standards and takes into
account the personal situation and preferences
of the patient (Figure 1).
Medical decisions occur along the continuum
of care, from initial clinical contact to followup. For healthcare providers, the question
• What needs to be done diagnostically and
• How can I use my resources in the process
• And with whom should I share information
and coordinate to achieve the best possible
outcome for the patient?
This paper argues that digital technologies
can indeed improve decision-making in all
these dimensions and provide valuable
decision support along the patient pathway.
Complex decisions often fail because, for
example, patient data is simply not accessible
or is too extensive and unstructured,
or because information is overlooked, or
guidelines are not sufficiently observed.
A digital platform that prepares a wide variety
of data in a user-friendly way and is simple
and flexible enough to bring together patient
information from diverse IT systems and
institutions could help remedy precisely this
situation. The ultimate goal is smart data
integration that provides a more comprehensive picture of the patient and allows holistic
decision-making in medicine.
the patient pathway
Without doubt, the challenges that complex
medical decisions entail are manifold and
can affect various steps in the care process
(Figure 2). A frequent problem is that relevant
patient data may simply not be available or
is too laborious to retrieve at the respective
point of care. According to in-depth studies
by the Mayo Clinic in the U.S., doctors in
intensive care units, for example, may have
to sift through thousands of individual data
points in electronic medical records to
extract the key pieces of information relevant to a patient’s case . Indeed, a substantial
proportion of electronically stored data is
never used in either the inpatient or the
outpatient setting [5,6].
Of course, medical data in itself is meaningless
unless it is transformed into actionable
insights. “Data doesn’t do you any good until
you can turn it into information,” the Stanford
University School of Medicine stated in a
trend report on the growing importance of
data for healthcare .
One reason why a considerable amount of
medical data remains unused may be the lack
of analytics expertise. What is more, the sheer
volume of data that physicians have to deal
with can contribute to distraction, dissatisfaction, and burnout . In a famous article
from the 1950s, U.S. psychologist George A.
Miller spoke of a “magic” number of seven
information units that humans can simultaneously retain and process in short-term
memory . The growing volume of data in
healthcare can therefore easily lead to what
has been described as “information overload”
with regard to digitalization as a whole.
However, some commentators of the digital
transformation have argued that the problem
does not lie in the mass of data itself, but
rather in a “filter failure” – i.e., the lack of
suitable selection and processing mechanisms
. For the case of healthcare, this means
that advanced digital solutions are urgently
needed that automatically analyze patient data
and present it in a user-friendly and clinically
The potential for using intelligent digital
technologies to reduce inefficiencies in workflows and improve patient care should indeed
be considerable. For example, about 30 %
of radiological diagnoses are likely to be errorprone, mostly due to cognitive factors .
Such diagnostic errors can carry through the
decision-making process and compromise
“Data doesn’t do you any good
until you can turn it into information.”
Stanford Medicine 2017 Health Trends Report
In addition, therapeutic decisions may not
comply with clinical guidelines. This, in turn,
can not only increase the risk of complications
and readmissions, but also push up costs and
length of stay . In other words, decisions
that do not take into account the best available
knowledge and information affect operational
efficiency and clinical outcomes alike.
A platform-based approach
to smart data integration and
It is clear that these difficulties are hard to
solve without powerful digital decision
support. The modern concept of clinical decision support not only includes automated
alerts to avoid errors, but also encompasses
clinical guidelines, patient data summaries,
condition-specific order sets, diagnostic
support, and contextually relevant reference
information. The overarching goal is
to digitally provide “general and personspecific information, intelligently filtered
and organized, at appropriate times,
to enhance health and health care” .
A growing number of studies underpin the
value of advanced decision support systems.
For example, a machine-learning algorithm
can help to avoid unnecessary CT scans in
children with only minor head injuries .
AI-based approaches could also facilitate
surgical decision-making . In addition,
higher support systems in oncological care
are likely to increase adherence to guidelines, reduce treatment costs, and ease the
workload of physicians in aftercare .
Siemens Healthineers has recently developed
a comprehensive solution, the “teamplay
digital health platform”, which can combine
many of these advantages. The platform and
applications connected to it support operational decision-making for efficient workflows
as well as diagnostic and therapeutic decisionmaking for optimal outcomes. In addition,
“teamplay” enables doctors, nurses, and
patients to connect more easily, providing
a basis for patient-centered care and shared
decision-making (Figure 3).
Indeed, the “teamplay digital health platform”
can represent a digital backbone for healthcare
providers, as it operates system- and vendorneutral through various interoperability
standards. This means that data from existing
IT systems within an organization can be
integrated and also shared across institutional
boundaries – for example, with other hospitals,
outpatient practices, or pharmacies.
The basic philosophy of the platform is to
support decision-making along the entire
patient pathway with a uniform but flexible
IT solution. Through a wide variety of
individual applications and extensions,
which are available via an integrated digital
marketplace, the platform can address
multiple problems in various clinical fields
(e.g., radiology, oncology, cardiology) and at
different points in the care process (Figure 4).
Some concrete successes can be highlighted
for both operational and clinical decisionmaking. For example, MedStar Health, a large
health network in Maryland and Washington,
D.C., in the U.S., has succeeded in significantly
improving the coordination of image reading
Figure 4: Improving data integration and decision-making along the patient pathway
(examples of Siemens Healthineers applications in brackets)
by subspecialized radiologists using the
“Medicalis Workflow Orchestrator” application.
In the network’s fragmented IT landscape, this
represented a major advance . “We had
a jury-rigged IT system, and had no way to
load-balance the workload across the system,”
recalls Steven Brick, Physician Executive
Director for MedStar Medical Group Radiology.
At that time, 110 radiologists and nuclear
medicine specialists were working with nine
different picture archiving and communication
systems (PACS) and five different radiological
information systems for the 10 hospitals in
the network. The availability of subspecialty
expertise varied greatly depending on the time
of day and location, as images could not be
easily exchanged for reading.
By implementing the “Medicalis Workflow
Orchestrator” together with a unified viewing
platform, it was possible to establish a combined worklist, allowing all MedStar radiologists
to work together as one team regardless
of their location. This not only eliminated
staffing problems, but also made radiological
subspecialty expertise constantly available
throughout the network – a prerequisite for
fast and precise clinical decisions.1
Similarly good experiences have been made
with a wide range of other “teamplay”
applications (Figure 5). “Using the teamplay
digital health platform has given us access
to digital solutions that we can trust,” says
Robert Day, COO at Zwanger-Pesiri Radiology,
a multi-site radiology practice in New York,
U.S., performing over 3,500 scans a day.
1 The statements by Siemens Healthineers’ customers described herein are based on results that were achieved in the customer’s
unique setting. Because there is no “typical” hospital or laboratory and many variables exist (e.g., hospital size, samples mix,
case mix, level of IT and/or automation adoption) there can be no guarantee that other customers will achieve the same results.
2 Information is derived from a statement by Siemens Healthineers customer Dr. Ernest Barrientos Manrique,
Health Time Medica, Spain.
3 Barmherzige Brüder and Vinzenz Gruppe, Austria | 4 Weill Cornell Medicine, U.S. | 5 IATROPOLIS, Greece |
6 Zwanger-Pesiri Radiology, U.S. | 7 Massachusetts General Hospital, U.S. | 8 IRMAS, France | 9 MedStar Health, U.S. |
10 HT Médica, Spain | 11 University Hospital Basel, Switzerland | 12 Heart and Diabetes Center North Rhine–Westphalia, Germany
With the performance management app
“teamplay Usage,” Zwanger-Pesiri was able to
increase MRI throughput from two patients
per hour to three, while with “teamplay
Protocols” it saved 90 % of the time spent on
editing and distributing scanning protocols
in the CT and MRI fleet.1
“Using the teamplay digital health
platform has given us access to
digital solutions that we can trust.”
COO, Zwanger-Pesiri Radiology,
New York, USA
The network also uses “AI-Rad Companion,”
which is an AI-supported, cloud-based image
interpretation tool for different modalities
and body regions. The tool is one of the
core apps of Siemens Healthineers’ clinical
AI portfolio and, for example, supports the
analysis of CT scans. The Spanish radiology
service provider HT Médica, for instance,
found that in one out of seven chest CT studies
re-analyzed with the “AI-Rad Companion,”
the software delivered additional valuable
information that had not been noticed during
the initial reading.1,2
In general, AI-based diagnostic support is
increasingly finding its way into clinical use,
with a growing number of approved applications for various clinical questions .
However, AI also holds great potential for
better therapy planning.
Exactly this is the aim of Siemens Healthineers’
“AI-Pathway Companion,” a recently developed
comprehensive software system for data-driven
decision support. “The AI-Pathway Companion
gives a very rapid overview of the patient
and helps to reinforce treatment decisions,”
says Heinz Läubli13, Senior Oncologist and
Head of Cancer Immunology Laboratory at
Basel University Hospital (USB), Switzerland.14
At USB, the “AI-Pathway Companion” is already
being used in clinical routines to improve
the multidisciplinary management of prostate
cancer patients. The digital tool aggregates
patient data from multiple sources15, such as
electronic medical records, imaging archives,
or – via natural language16 processing – even
written texts. The information is automatically
processed and displayed in structured form.
This makes it easier and faster for a multidisciplinary team to prepare and discuss an
individual patient’s case and to decide on
a tailored treatment plan.14
“Software like this will lead to better quality
of care,” agrees Helge Seifert17, Head of the
Department of Urology at USB. A second
clinical implementation project is underway
at Radboud University Medical Center in the
Netherlands. In addition, the “AI-Pathway
Companion” is in development for breast
and lung cancer as well as coronary artery
A major strength of the application is that
it integrates clinical guidelines, individual risk
stratification18, and the patient‘s preferences,
thereby helping to make evidence-based and
transparent recommendations for various
treatment options. By mapping out where
a patient is in the treatment pathway, it also
facilitates discussion between doctor and
patient on how to proceed.
Here lies an important focus of the “teamplay
digital health platform” to better network
not only data but also people. For instance,
the “eHealth Solutions,” a family of various
software packages, allow patient-specific
data exchange across institutions on the
one hand, and enable closer and expanded
communication between care teams and
patients on the other.
This is in line with a general trend: patients
are developing a new, more responsible selfimage – and consequently want to participate
in medical decision-making.
13 Heinz Läubli is employed by an institution that receives financial support from Siemens Healthineers for collaborations.
14 The statements by Siemens Healthineers’ customers described herein are based on results that were achieved in the customer’s
unique setting. Because there is no “typical” hospital or laboratory and many variables exist (e.g., hospital size, samples mix,
case mix, level of IT and/or automation adoption) there can be no guarantee that other customers will achieve the same results.
15 This function is supported by AI-Pathway Companion Connector.
16 NLP supported languages: English, German, Dutch.
17 Helge Seifert is employed by an institution that receives financial support from Siemens Healthineers for collaborations.
18 This function is supported by AI-Pathway Companion Prostate Cancer. Prerequisite: All data is available as required by guideline;
Feature dependent on quality of input data. AI-Pathway Companion Prostate Cancer VA10B supports NCCN and EAU guidelines.
Changing roles in healthcare:
involving patients through
Digitalization comes along with changing roles
of doctors and patients. For example, online
searches for health information by patients are
commonplace today and complement visits to
the doctor. At the same time, the increasing
importance of chronic diseases, the ubiquitous
spread of mobile devices, and the development of connected wearable sensors are key
drivers of mobile health . Particularly in
the case of complex chronic conditions such
as diabetes or inflammatory bowel disease,
which affect the entire social life, digital health
applications can contribute to improved selfmanagement and reduction of fears, stronger
patient empowerment, and shared decisionmaking [24–26]. Finally, from a consumer’s
point of view, the digitalization of everyday life
naturally raises the expectation of being able
to ask providers questions or booking appointments online .
While not all social and age groups are
adopting digital health technologies to the
same extent or at the same speed, digitalization can ideally contribute to a cultural shift
from traditional to collaborative care, with
shared decision-making as a new norm .
Indeed, research evidence suggests that digital
health, for example in chronic heart disease,
can not only empower patients and enhance
communication with caregivers, but may also support health-promoting behaviors, improve
medication adherence, and reduce the number
of hospital stays [29–31].
An exemplary project is a telemonitoring
program for heart failure patients
(“HerzConnect”) at the Heart and Diabetes
Center North Rhine–Westphalia in Germany.
Patients are equipped with mobile ECG
monitors and blood pressure sensors.
The collected data, together with the patient’s
weight and subjective well-being, is transmitted via smartphone to the care team in
the clinic, which tracks the parameters on
a user-friendly dashboard. For their part,
doctors can reach patients directly via text messages. The networking becomes possible
through Siemens Healthineers’ “teamplay”
app “myCare Companion”.
A major goal of the project is to prevent cardiac
decompensation and hospital admissions by
early intervention and therapy adjustments,
thereby improving patients’ quality of life. In
a second step, an AI-powered central worklist
can be used to prioritize those patients who
require special support.
Siemens Healthineers also developed a related
app during the COVID-19 pandemic. This
app allows patients in quarantine to remotely
transmit their body temperature and oxygen
saturation, thus keeping infectious persons
away from hospitals (see also excursus “Telehealth in the COVID-19 pandemic, and beyond”).
Other applications to advance remote
communication with patients are part of
the Siemens Healthineers’ family of “eHealth
Solutions,” including a patient portal for
uploading and downloading of medical
data and “Virtual Visit,” which enables video
Regardless of the specific application, however,
the digital involvement of patients has a
general effect: it creates a constant feedback
loop between the care teams and the people
they care for. The patient pathway becomes a
cycle of care (Figure 6).
Telehealth in the COVID-19
pandemic, and beyond
COVID-19 is transforming healthcare.
Given the concern that infectious patients
could introduce the coronavirus into
hospitals, video consultations in particular
have experienced an unanticipated boom
at many hospitals.
“A sizeable proportion of outpatient visits
in various settings can be clinically managed
effectively from a distance,” stated a
recent editorial on the lessons learned
from current changes .
For example, in a rapid response to the
COVID-19 crisis, NYU Langone Health,
a large academic healthcare system in New
York City, increased the number of videobased emergency consultations between the
beginning and middle of March 2020 from
about 80 to over 1,300 visits per day .
According to the case report, the increase
was even larger in non-urgent care, where
virtual visits represented more than 70 % of
all ambulatory encounters at the beginning
of April. Patients of all ages quickly became
used to sharing their biometric data via a
patient portal, tightly integrated into the
network’s electronic health record. What
is more, patient satisfaction with the video
visits remained constantly high despite
the rapid adoption of telemedicine, also
by inexperienced physicians.
Langone Health had already introduced
its virtual care infrastructure, including a
dedicated patient app, in 2018, and the case
may indeed seem particularly successful,
but it is no exception. According to a recent
study on telehealth adoption in Europe,
Onkologikoa, a cancer center in the Basque Country in Spain, deployed Zoom
for video consultations at each of its
30,000 workstations shortly after the
pandemic began . Likewise, the Hospital
of Dénia in the Valencia Region in Southern
Spain also introduced Zoom to manage
patients at home, with an astonishing 80 %
of them agreeing to virtual visits and
finding them easily accessible. Hospitals
in Italy and Denmark have had similar
What will remain of it
in the future?
On the one hand, video-based care will
hardly be used to the same extent as in
the exceptional situation of the incipient
COVID-19 pandemic. Nor will traditional
barriers to telemedicine such as reimbursement, interoperability, and data
privacy issues simply disappear in the
post-COVID-19 world. On the other hand,
observers agree that the pandemic has
led to a new culture and acceptance
of remote care among both patients and
doctors, with a shift from the primary
use of telemedicine for chronic diseases
toward everyday care situations and
It is likely that the positive experiences
will raise future expectations among
patients regarding the comfort and digital
accessibility of healthcare services.
Providers, for their part, could make greater
use of telemedicine as a triage instrument
to avoid unnecessary treatments and
channel patients more effectively.
“A sizeable proportion of outpatient
visits in various settings can be
clinically managed effectively
from a distance.”
Bashshur et al. 2020
Not least, the digital and less traditional
forms of communication in telecare could
further reduce the hierarchies between doctors and patients and lead to their increased
involvement in medical decision-making.
Staying flexible during
Digitalization is a continuous transformation.
It is clear that today’s IT architectures must
be able to grow with changing needs and
integrate new features. Indeed, according
to an international survey, three out of four
healthcare executives believe that digital
platforms – fundamental IT solutions that
incorporate previously disparate functionalities, connect things and people, and foster
innovation – enable their organization’s
business strategy or even are at its core .
Siemens Healthineers has designed its
digital health platform as a flexible tool that
meets the increasing importance of data for
healthcare. Its integrated marketplace provides
one-stop access to a growing number of
proprietary as well as curated and pre-vetted
partner applications. Siemens Healthineers
alone currently provides more than 40 apps,
a third of which are AI-powered, for six
different clinical specialties. This enables
advanced and customized digitalization for
a wide range of healthcare providers and
Digitalization is certainly not only a technological but also a conceptual issue. If medicine
wants to harness the increasing abundance
and complexity of health data – and this is
precisely what is emerging – then this means
a threefold paradigm change:
• First, as outlined above, healthcare providers
need a digital infrastructure that is as simple
as possible, yet versatile and adaptable,
ideally in the form of a system-wide platform
for networking data.
• Second, a steadily growing number of
intelligent applications are needed that can meaningfully prepare networked data for
specific operational and clinical questions.
A number of relevant examples have already
been illustrated here.
• Third, however, digitalization is also
changing the very nature of medical decision-making itself. Medical decisions will
continue to be the responsibility of doctors –
and patients. Nevertheless, the individual
human actors in the care process will
increasingly have to make use of advanced
digital decision support in order to bring the
wealth of data into their deliberations and
use it in a profitable way.
Medicine is not data science. But we believe
that medicine in the future cannot do without
a data science perspective. A flexible platform
that is capable of integrating more and more
data is vital here. Flexibility is the greatest
asset in a digital world.
Naturally, transformative processes do not
happen overnight. Siemens Healthineers’
“teamplay digital health platform” takes this
into account. It allows a quick start that does
not require major investments and restructuring. Through an interoperable, system- and
vendor-neutral design, the platform integrates
existing and very different IT components and
enables a step-by-step approach. Data silos
do not need to disappear immediately (which
is unrealistic), but can be tapped, and data
treasures can be extracted bit by bit.
Moving toward smart data integration in
medicine is thus a somewhat longer way
forward. Holistic decision-making for the
benefit of the patient is the rewarding goal.
- CMS – Center for Medicare and & Medicaid Services (2020)
Evaluation and management services guide (MLN booklet)
https://www.cms.gov/Outreach-and-Education/MedicareLearning-Network-MLN/MLNProducts/Downloads/eval-mgmt-servguide-ICN006764.pdf (accessed 4 September 2020)
- Lynn LA (2019) Artificial intelligence systems for complex
decision-making in acute care medicine: a review.
Patient Saf Surg 13:6
- Topol EJ (2019) High-performance medicine: the convergence of
human and artificial intelligence. Nat Med 25:44-56
- Herasevich V, Pickering B, Gajic O (2018)
How Mayo Clinic Is Combating Information
Overload in Critical Care Units. Harvard Business Review.
https://hbr.org/2018/03/how-mayo-clinic-is-combating-information-overload-in-critical-care-units (accessed 4 September 2020)
- Pickering BW, Gajic O, Ahmed A (2013) Data utilization for
medical decision making at the time of patient admission
to ICU. Crit Care Med 41:1502-10
- Hribar MR, Biermann D, Goldstein IH, Chiang MF (2018) Clinical
Documentation in Electronic Health Record Systems: Analysis of
Patient Record Review during Outpatient Ophthalmology Visits.
AMIA Annu Symp Proc 2018:584-591. eCollection 2018
- Stanford Medicine 2017 Health Trends Report: Harnessing the
Power of Data in Health. http://med.stanford.edu/content/dam/
sm/sm-news/documents/StanfordMedicineHealthTrendsWhitePaper2017.pdf (accessed 4 September 2020).
- Ruppel H, Bhardwaj A, Manickam RN et al. (2020) Assessment of
Electronic Health Record Search Patterns and Practices by Practitioners in a Large Integrated Health Care System.
JAMA Netw Open 3:e200512.
- Miller GA (1956) The magical number seven, plus or minus two:
some limits on our capacity for processing information.
Psychological Review 63:81-97
- Shirky C (2008) “It’s Not Information Overload. It’s Filter Failure”.
Lecture at the Web 2.0 Expo in New York.
(accessed 4 September 2020)
- Lee CS, Nagy PG, Weaver SJ, Newman-Toker DE (2013)
Cognitive and system factors contributing to diagnostic
errors in radiology. AJR Am J Roentgenol 201:611-7
- Heekin AM, Kontor J, Sax HC et al. (2018) Choosing Wisely
clinical decision support adherence and associated inpatient
outcomes. Am J Manag Care 24:361-366
- Institute of medicine (2013) Best care at lower cost: the path to
continuously learning healthcare in America
- Nolan ME, Siwani R, Helmi H et al. (2017)
Health IT Usability Focus Section: Data Use and Navigation
Patterns among Medical ICU Clinicians during Electronic
Chart Review. Appl Clin Inform 8:1117-1126
- Kahn K, Hussey P, Nyweide D et al. (2014)
Medicare Imaging Demonstration Evaluation Report for the
Report to Congress. https://innovation.cms.gov/Files/reports/
- Forastiere AA, Flood WA, Yedwab E et al. (2013) The cost per
patient of deviations from evidence-based standards of oncology
care. Journal of Clinical Oncology 31(15)suppl:6515
- PwC Health Research Institute (2019) Top health industry issues
of 2019:The New Health Economy comes of age. https://www.
- CMS – Center for Medicare and & Medicaid Services (2014)
Clinical decision support: more than just ‘alerts’ tipsheet.
Tipsheet-.pdf (accessed 4 September 2020).
- Bertsimas D, Dunn J, Steele DW et al. (2019) Comparison of
Machine Learning Optimal Classification Trees With the Pediatric
Emergency Care Applied Research Network Head Trauma
Decision Rules. JAMA Pediatr 173:648-656
- Loftus TJ, Filiberto AC, Li Y et al. (2020) Decision analysis
and reinforcement learning in surgical decision-making.
- Klarenbeek SE, Weekenstroo HHA, Michiel Sedelaar JPM et al.
(2020) The Effect of Higher Level Computerized Clinical
Decision Support Systems on Oncology Care: A Systematic
Review. Cancers 12:1032
- Daher N, Ruppar D (2018) Optimizing Medical Imaging Service
Lines in an Evolving Healthcare Landscape. A Frost & Sullivan
Case Study (commissioned by Siemens Healthineers)
- Bhavnani SP, Narula J, Sengupta PP (2016)
Mobile technology and the digitization of healthcare.
European Heart Journal 37:1428-1438
- Wake DJ, He J, Czesak AM et al. (2016)
MyDiabetesMyWay: An Evolving National Data Driven
Diabetes Self-Management Platform.
Journal of Diabetes Science and Technology 10: 1050-1058
- Atreja A, Otobo E, Ramireddy K, Deorocki A (2018) Remote
Patient Monitoring in IBD: Current State and Future Directions.
Current Gastroenterology Reports 20:6
- Khan S, Dasrath F, Farghaly S et al. (2016)
Unmet Communication and Information Needs for Patients
with IBD: Implications for Mobile Health Technology.
Br J Med Med Res 12:12119
- Featherall J, Lapin B, Chaitoff A (2018) Characterization of
Patient Interest in Provider-Based Consumer Health Information
Technology: Survey Study. J Med Internet Res 20:e128
- Meskó B, Drobni Z, Éva Bényei E et al. (2017) Digital health is a
cultural transformation of traditional healthcare. mHealth 3:38
- Kambhampati S, Ashvetiya T, Stone NJ et al. (2016) Shared Decision-Making and Patient Empowerment in Preventive
Cardiology. Curr Cardiol Rep 18: 49
- Steinmetz M, Rammos C, Rassaf T, Lortz J (2020)
Digital interventions in the treatment of cardiovascular
risk factors and atherosclerotic vascular disease.
IJC Heart & Vasculature 26:100470
- Singhal A, Cowie MR (2020) The Role of Wearables in Heart
Failure. Curr Heart Fail Rep 17:125-132
- Bashshur R, Doarn CR, Frenk JM et al. (2020)
Telemedicine and the COVID-19 Pandemic, Lessons for the
Future. Telemed J E Health 26:571-573
- Mann DV, Chen J, Chunara R et al. (2020)
COVID-19 transforms health care through telemedicine: Evidence
from the field. Journal of the American Medical
Informatics Association 27: 1132-1135
- HIMMS Insights (2020) E-Health Trendbarometer: Telehealth
Adoption in Europe (supported by Siemens Healthineers)
- Elliott J, Nguyen C, Tanguturi P (2018) Digital platforms will
define the winners and losers in the new economy. Accenture
digital platforms survey. https://www.accenture.com/_acnmedia/
(accessed 4 September 2020)