The unprecedented rapid adoption of mobile technology has motivated great interest in using mobile technology for health (mHealth). Bolstering the mHealth promise are three important trends: Firstly, big data—through which there has been unprecedented commoditization and opening up of data through the instrumentation of modern phones and environments (e.g., using the native sensors in mobile phones or using embedded devices in the so-called Internet of Things). This opens up the opportunity of collecting individual level ``small data’’ that can be used to provide personalized healthcare. Secondly, artificial intelligence (AI) and machine learning (ML) advances have democratized diagnostic capabilities to some extent and further significant improvement is expected. With advances in computational capabilities of mobile phones, and with resource augmentation from clouds,  it will be possible to support data and computation intensive mHealth applications. Finally, high-performance communication (e.g., high throughput and low latency) capabilities can change the landscape of healthcare in terms of operational efficiency and accuracy and enable a range of telehealth services. In this talk, we will present the research agenda for bringing the 5G-Enabled Health Revolution.

1. 5G-enabled healthcare:
The promise of big data,AI, and
communication for healthcare
Junaid Qadir
InformationTechnology
University (ITU), Pakistan

2. Healthcare is vital for
human development
“Health is a critically significant
constituent of human capabilities
which we have reason to value.” Amartya Sen

3. Outline
Deficiencies of current healthcare1
2 How technologies can help
3 5G and healthcare:
opportunities and challenges

4. Deficiencies of
current healthcare system
1

5. How healthcare lags other fields
if banking was like health care,ATM transactions would take not
seconds but days as a result of unavailable or misplaced records.
if home building was like health care, carpenters,
electricians, and plumbers each would work with different
blueprints, with very little coordination.
if shopping was like health care, product prices would not be
posted, and the price charged would vary widely within the same
store, depending on the source of payment.
if automobile manufacturing was like health care, warranties that
require manufacturers to pay for defects would not exist. as a
result, few factories would seek to improve production
performance and quality.
if airline travel were like health care, each pilot would design his
or her own preflight safety check, or not to perform one at all.
Institute of Medicine,
(IOM) National Academy
of Sciences (2013)

6. Deficiencies of current health system
Not convenient
Patient to go to
(potentially distant)
doctor’s office
Not personalized
One-size-fits-all
Population based
Medicine
Not equitably
accessible
Health divide
based on
geography,
income & gender
Not holistic/
data driven
Interrupt driven,
and uses doctor’s
ordered point tests

7. Microcosm of the ills in 3 stories
A young man in Boston USA:
MIT graduate student Steven
Keating, whose live was almost
claimed by the sectional rather
than holistic nature of healthcare
Boy from Sahiwal, Pakistan
who died because lack of
sufficient basic
infrastructure
Octogenarian woman in
suburban Madrid, Spain.
(the problem of chronic
disease management)

8. What used to be a population pyramid
The nature of the healthcare challenge
differs throughout the world

9. How technologies can fix the
current healthcare system
2
“80% of what doctors can be done
better through technology”

10. Healthcare can benefit greatly by
incorporating technology like
many other fields have
Autopilot in automobiles and aeroplanes
Technology for human amplification
driverless cars
10–20% of all health cases delayed, missed or incorrectly diagnosed
(Graber et al., Journal of the American Medical Association (JAMA), 2012)
1) MDs have cognitive biases;
2) Not all doctors are top notch; half are below average (median)
Why?

11. Technology to mitigate the scarcity and
imbalance of medical resource distribution
Number of imbalances:
• Geographical (e.g., Urban vs. Rural)
• Specialty based
• Institutional/services based
• Gender based
A striking example of health inequality:
Africa has 25% of the worldwide disease burden but
only 3% of the health workers.

12. How technologies can fix the
current healthcare system
2
2A—big data for development
2B—wireless connectivity
2C—AI, machine learning, algorithms
2D—disruptive health innovations
[the subsections]

13. Big Data for Healthcare
My Data/ Small Data
Exhaust Data
Claims Data
EHR and EMR
Different kinds of data
useful for health
2A
Focus here

14. Data science for medicine
“In the next ten years, data
sciences and software will do
more for medicine than all of
the biological sciences together.’’ Vinod Khosla
Some data science for public healthcare examples:
(1) Statins for in-hospital stroke patients (40% less casualties);
(2) Kaggle data science for HIV research (improved 3yr of research in 1.5wk);
(3) Passive behavior observation to detect mental health disorders (ginger.io);
(4) ITU and PITB’s work on curbing epidemics

15. Connectivity
(Wireless)2B
Some applications:
Telemedicine
Tactile Internet
Remote Surgery

16. Telemedicine: healing at a distance
Low-cost Video
Conferencing Tele-radiology
Tele-dermatology
Tele-pathology
Tele-ECG
Tele-psychiatry

17. Artificial Intelligence/
Machine Learning/
Probabilistic modeling
2C
Some applications:
Personalized Medicine
—Data-Driven Diagnosis and Prognosis
—Collaborative Filtering for Similar Patient Finding
Cognitive Healthcare Solutions (e.g., IBM Watson)
Deep Learning Health Systems

18. The dawn of patient-centric medicine
“In the future, patients will have the data & analysis to
become the CEO of your own health”—Peter Diamandis

19. Disruptive health innovations2D
Point of Care (POC)
Testing
Wearable Sensors
and Implantable
Nano Sensors
Open Source EHR/
EMR Systems

20. Various health advances with IoT
DIY home monitoring solutions:
AliveCore: Patients can now measure their vitals (e.g., ECG) at home
using mobile devices at a fraction of cost and with great convenience

21. 5G and healthcare:
opportunities and challenges
3

22. 5G and universal coverage
Most of the the 5G prime technology (including ultra-densification,
millimeter wave) don’t necessarily perform well for universal coverage
but massive MIMO can give coverage gains and energy reduction
Extending coverage especially indoor and in
rural areas is key for e-health applications.

23. Virtual Reality + Tactile Internet
Virtual Reality:
Multi-viewing angles
Haptic feedback
Tactile Internet:
1 ms end-to-end latency
Haptic Feedback
Improved latency performance (reduction and guaranteeing latency
below a bound reliably) necessary to unlock this use case.
Haptic feedback devices create the illusion of
substance and force within the virtual world

24. 5G-enabled wearable/implantable devices
Energy consumption optimization (e.g., in air interface via advanced
MIMO and beamforming) is very important for wireless health devices
Interfacing these wireless sensor devices with 5G presents
exciting opportunities and formidable challenges

25. Technology for healthcare:
Insights on challenges/ pitfalls
✗ ✗
Healthcare is a hard nut to crack:
Digital dividends depend on key “analog complements”
(e.g., appropriate policies, regulation, incentives, and capable human workforce).

26. Technology as a tool to aid humans
Big data is not the solution to the
bias problem; it is merely a source
of more subtle (or even bigger)
biases.
Whether you use computer or your brain, one must decide what’s signal and
what’s noise. Human intuition is extremely powerful here.
Human TouchTechnology
“Technology amplifies human intent and capacity; it doesn't
substitute for them.”—KentaroToyama (author of Geek Heresy)
How much control should we cede to algorithms and robots?

27. Where is the bottleneck?
Most of the deaths are due to modern lifestyle (due to chronic
diseases such as cardiovascular disease and diabetes).
Behavioral revolution is as needed as a technological revolution

28. Security and privacy
Hippocratic oath: “first, do no harm”
Iatrogenesis (n): harm or illness caused
by medical examination or treatment.
Some important objectives:
1. Identity management
2. Privacy protection
3. Data and message encryption
and protection
4. Update of security mechanisms
5. Avoiding bioterrorism

29. Concluding remarks
• Democratization of computing
through cloud computing
• Democratization of AI and cognitive
computing (e.g., IBM Watson)
• Commoditization of data through
crowdsourcing and digital exhaust
• High throughput and low latency
connectivity (5G enabled)
Confluence of different technical pushes will
empower a healthcare revolution

30. About 5G enabled healthcare
5G wireless will transform the field of healthcare by
augmenting human capacity and reach in a few years
by allowing:
—resource pooling
—virtualization
—high-performance and reliable telemedicine
—tactile Internet with haptic feedback
There are exciting research & implementation
opportunities in building this future of healthcare but
also substantial challenges and many pitfalls.

31. Books
Figures and Images:
Credits/ Acknowledgments
Various images used in Bertalan Meskó’s presentations
Mesko, Bertalan. “The Guide to the Future of Medicine: Technology And The Human Touch.”
Various images used from Wikipedia and through Google Image Search.
Various images used from IEEE/ACM papers
(Copyright retained by respective users; images are used for educational purposes)
Meskó, Bertalan. “My Health: Upgraded: Revolutionary Technologies To Bring A Healthier Future.”
Mukherjee, Siddhartha, “The Laws of Medicine.”
These resources have been used in these lecture slides for educational purpose under the fair use doctrine.
The ownership of these resources, if copyrighted, is retained by their respective copyright owners.
Topol, Eric, “The Patient Will See You Now.”
Topol, Eric, “Creative Destruction of Medicine.”